{ "benchmark_line": "gamebench2", "generated_at": "2026-07-27T14:02:29Z", "public_release_id": "gb2-20260727-b63faa64fdbb", "results_cut_id": "gb2-20260727-b63faa64fdbb", "schema_version": 2, "snapshot_id": "20260727_140229", "tracks": { "full_freedom/balanced": { "GB2-01": [ { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 20, "model": "claude-fable-5", "point_rating_method": "sequential_elo", "public_id": "E-2dbc6efbd7db03b5", "rated_matches": 56, "raw_elo_rating": 1661.6976408495564, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 68.52383229044648, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 36 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 9, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 9, "generated_at": "2026-07-02T16:51:45Z", "losses": 23, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-13ec9509bc80f2bf", "rated_matches": 52, "raw_elo_rating": 1483.905475102522, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 45.19928208402567, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 5, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 5, "generated_at": "2026-07-25T15:48:00Z", "losses": 16, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-0437af9582860271", "rated_matches": 50, "raw_elo_rating": 1554.5202933343148, "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": 54.2236275574193, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 2, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 2, "generated_at": "2026-07-25T15:48:00Z", "losses": 18, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-93a6875407c22137", "rated_matches": 48, "raw_elo_rating": 1684.0720782689243, "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": 70.88708715244077, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 7, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 7, "generated_at": "2026-07-02T16:51:45Z", "losses": 26, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-cd50a27a6bb44b58", "rated_matches": 60, "raw_elo_rating": 1450.988870016457, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 41.41203641046077, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 27 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 20, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 20, "generated_at": "2026-07-02T06:10:40Z", "losses": 18, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-f1d9dfb787d0d902", "rated_matches": 42, "raw_elo_rating": 1354.422251343348, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 27.61217116800776, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 5, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 5, "generated_at": "2026-07-01T00:15:48Z", "losses": 19, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-fd9da5310ad15cac", "rated_matches": 42, "raw_elo_rating": 1603.5204746601908, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 59.934503672797355, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 29, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 29, "generated_at": "2026-07-02T16:51:45Z", "losses": 16, "model": "google/gemini-3.1-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-7669b8a03ef19548", "rated_matches": 58, "raw_elo_rating": 1458.4305805417964, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 42.26595649843005, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 0, "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": 56, "raw_elo_rating": 1819.728353888386, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 89.02948337376621, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 47 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 20, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 20, "generated_at": "2026-07-24T13:40:00Z", "losses": 23, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-77d8df8cd762fd09", "rated_matches": 66, "raw_elo_rating": 1486.4532366607398, "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": 46.31833688879277, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 11, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 11, "generated_at": "2026-07-24T13:40:00Z", "losses": 32, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-fc3c30006929710a", "rated_matches": 60, "raw_elo_rating": 1519.8637003276654, "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": 50.349053852364435, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 31, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 31, "generated_at": "2026-07-24T13:40:00Z", "losses": 18, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-4b36631072d1c39e", "rated_matches": 60, "raw_elo_rating": 1328.006075988608, "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": 25.454111428073276, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 2, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 2, "generated_at": "2026-07-24T13:40:00Z", "losses": 8, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-7484f4e7d8863a3b", "rated_matches": 60, "raw_elo_rating": 1834.1963383041368, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 91.13603300660792, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 50 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 15, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 15, "generated_at": "2026-07-02T16:51:45Z", "losses": 25, "model": "gpt-5", "point_rating_method": "sequential_elo", "public_id": "E-adee794ecd761044", "rated_matches": 54, "raw_elo_rating": 1359.6393456579792, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 29.205660998009655, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 24, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 24, "generated_at": "2026-07-02T16:51:45Z", "losses": 11, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-586de6c9939561c3", "rated_matches": 58, "raw_elo_rating": 1653.411765004077, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 67.56620389662746, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 5, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 5, "generated_at": "2026-07-02T16:51:45Z", "losses": 24, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-62424dfd649cbac9", "rated_matches": 60, "raw_elo_rating": 1586.2698676615937, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 58.96574405735956, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 31 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 16, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 16, "generated_at": "2026-07-01T00:15:48Z", "losses": 34, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-aa899d4eca8a2891", "rated_matches": 58, "raw_elo_rating": 1313.0379027856814, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 23.400183745738065, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 76, "capped_draws": 11, "coverage_status": "rated", "distinct_rated_opponents": 38, "draws": 11, "generated_at": "2026-07-02T06:10:40Z", "losses": 30, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-c675a6c67536654d", "rated_matches": 76, "raw_elo_rating": 1504.1241861334013, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 49.037337444355906, "uncertainty": 13.230288229818967, "unilateral_faults": 0, "wins": 35 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 17, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 17, "generated_at": "2026-07-02T06:10:40Z", "losses": 21, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-22c14c8deb751cb3", "rated_matches": 54, "raw_elo_rating": 1399.6655784138532, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 34.399360040992676, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 15, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 15, "generated_at": "2026-07-02T16:51:45Z", "losses": 26, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-9257cc1e94bf4b17", "rated_matches": 62, "raw_elo_rating": 1423.4427866640558, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 37.94406357252404, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 10, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 10, "generated_at": "2026-07-01T00:15:48Z", "losses": 45, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-98c36ba5e36ecf75", "rated_matches": 56, "raw_elo_rating": 1133.6056513286212, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 0.0, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 9, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 9, "generated_at": "2026-07-09T17:30:50Z", "losses": 46, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-c48c1aed1cdecc72", "rated_matches": 56, "raw_elo_rating": 1166.088389143785, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 4.214874912986324, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 38, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 38, "generated_at": "2026-07-02T16:51:45Z", "losses": 3, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-e4496be687faac9d", "rated_matches": 56, "raw_elo_rating": 1578.7755636434526, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 57.76408091303755, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 8, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 8, "generated_at": "2026-07-10T05:30:29Z", "losses": 23, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-4f775a5b7b265dae", "rated_matches": 62, "raw_elo_rating": 1631.9779985185817, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 65.00304603642252, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 31 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 25, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-bc834303cebba06a", "rated_matches": 54, "raw_elo_rating": 1589.1789388885927, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 58.990116931190066, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 20, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 20, "generated_at": "2026-07-10T05:30:29Z", "losses": 18, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-46de264ad4571b48", "rated_matches": 56, "raw_elo_rating": 1500.156493815032, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 47.5626764936281, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "inclusionai/ling-3.0-flash", "point_rating_method": "sequential_elo", "public_id": "E-47f813dcedb11262", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-5e8d45873865cc93", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 1, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 1, "generated_at": "2026-07-02T16:51:45Z", "losses": 17, "model": "minimax/minimax-m3", "point_rating_method": "sequential_elo", "public_id": "E-e0a841a9daa66219", "rated_matches": 34, "raw_elo_rating": 1460.7073343854129, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 40.54537078329118, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 30, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 15, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 14, "model": "moonshotai/kimi-k2.7-code", "point_rating_method": "sequential_elo", "public_id": "E-4935e918b1e70ea1", "rated_matches": 30, "raw_elo_rating": 1510.1966215730497, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 46.4181257426225, "uncertainty": 46.05265101338746, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 30, "capped_draws": 19, "coverage_status": "under_covered", "distinct_rated_opponents": 15, "draws": 19, "generated_at": "2026-07-24T14:00:00Z", "losses": 6, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-6cc4477cf8936e55", "rated_matches": 30, "raw_elo_rating": 1505.7367507618944, "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": 45.83942459667651, "uncertainty": 46.05265101338746, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 30, "capped_draws": 11, "coverage_status": "under_covered", "distinct_rated_opponents": 15, "draws": 11, "generated_at": "2026-07-21T14:43:57Z", "losses": 6, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-ee608da1db5fc482", "rated_matches": 30, "raw_elo_rating": 1590.2168161325296, "reasoning": "high", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 56.80133643441302, "uncertainty": 46.05265101338746, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 14, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 14, "generated_at": "2026-07-02T16:51:45Z", "losses": 26, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-b851008baae8f441", "rated_matches": 64, "raw_elo_rating": 1508.9996053111847, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 49.14708051635627, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 7, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 7, "generated_at": "2026-07-02T16:51:45Z", "losses": 21, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-428923c2eb87dc7a", "rated_matches": 54, "raw_elo_rating": 1521.3936825716696, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 50.19447975472116, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 18, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 18, "generated_at": "2026-07-02T16:51:45Z", "losses": 22, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-a3e0c8f8ea39b5ec", "rated_matches": 56, "raw_elo_rating": 1406.1009817298916, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 35.358279790014166, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-ffd72d2c5c11728a", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 30, "capped_draws": 7, "coverage_status": "under_covered", "distinct_rated_opponents": 15, "draws": 7, "generated_at": "2026-07-02T16:51:45Z", "losses": 14, "model": "qwen/qwen3.7-max", "point_rating_method": "sequential_elo", "public_id": "E-24581eb49b81bf8f", "rated_matches": 30, "raw_elo_rating": 1452.8629061397091, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 38.978653114934275, "uncertainty": 46.05265101338746, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 3, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 3, "generated_at": "2026-07-02T16:51:45Z", "losses": 18, "model": "qwen/qwen3.7-plus", "point_rating_method": "sequential_elo", "public_id": "E-1e5dceaf2ba3ca9a", "rated_matches": 40, "raw_elo_rating": 1493.5331251706154, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 45.47208022011386, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 13, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 13, "generated_at": "2026-07-24T13:40:00Z", "losses": 22, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-7382cf954e1b755d", "rated_matches": 62, "raw_elo_rating": 1458.1859571349817, "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": 42.45224630172584, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 27 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 20, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 20, "generated_at": "2026-07-24T13:40:00Z", "losses": 27, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-c9890f6abafaf54f", "rated_matches": 60, "raw_elo_rating": 1303.8451033164808, "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": 22.319046946483994, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 76, "capped_draws": 7, "coverage_status": "rated", "distinct_rated_opponents": 38, "draws": 7, "generated_at": "2026-07-17T22:36:00Z", "losses": 37, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-abb31ae26e404d88", "rated_matches": 76, "raw_elo_rating": 1464.725832992289, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 43.92511041434462, "uncertainty": 13.230288229818967, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 6, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 6, "generated_at": "2026-07-24T14:00:00Z", "losses": 10, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-d709aeb6802f9289", "rated_matches": 72, "raw_elo_rating": 1810.7375600339055, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 88.66279441284121, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 56 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 12, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 12, "generated_at": "2026-07-17T22:36:00Z", "losses": 20, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-fcb362c12bec2a34", "rated_matches": 60, "raw_elo_rating": 1620.4063338934643, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 63.39520243483502, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 5, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 5, "generated_at": "2026-07-02T16:51:45Z", "losses": 16, "model": "x-ai/grok-build-0.1", "point_rating_method": "sequential_elo", "public_id": "E-f1ded648f3ab17dc", "rated_matches": 40, "raw_elo_rating": 1516.3694881573388, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 48.43526682108, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 3, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 3, "generated_at": "2026-07-02T16:51:45Z", "losses": 16, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-1208f50b0908ecb4", "rated_matches": 38, "raw_elo_rating": 1508.5308307724358, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 47.21289857419709, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 4, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 4, "generated_at": "2026-07-02T06:10:40Z", "losses": 18, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-2a71bee21bd7c0b9", "rated_matches": 36, "raw_elo_rating": 1489.219330088802, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 44.48542000207563, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 32, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 32, "generated_at": "2026-07-01T00:15:48Z", "losses": 7, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-b2a148bd3f2766ff", "rated_matches": 44, "raw_elo_rating": 1467.924210170858, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 42.51777854057247, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 3, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 3, "generated_at": "2026-07-11T17:22:09Z", "losses": 18, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-f889d782e3cce209", "rated_matches": 44, "raw_elo_rating": 1443.3557138091094, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 39.32983485324606, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 23 } ], "GB2-02": [ { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 28, "generated_at": "2026-07-02T16:51:45Z", "losses": 9, "model": "claude-fable-5", "point_rating_method": "sequential_elo", "public_id": "E-cd3608270e8c00fd", "rated_matches": 58, "raw_elo_rating": 1624.075614202798, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 63.51723403185436, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 39, "generated_at": "2026-07-02T16:51:45Z", "losses": 3, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-ed71c4ecf219b609", "rated_matches": 44, "raw_elo_rating": 1477.1586139699823, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 26.60687800872694, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 21, "generated_at": "2026-07-25T10:50:00Z", "losses": 10, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-50b401cafe71e710", "rated_matches": 50, "raw_elo_rating": 1639.4351675605897, "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": 66.24696134878403, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 24, "generated_at": "2026-07-25T10:50:00Z", "losses": 7, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-8a5bf2e23121edf6", "rated_matches": 48, "raw_elo_rating": 1621.3399904009398, "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": 61.65273875121062, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 50, "generated_at": "2026-07-02T16:51:45Z", "losses": 3, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-a1a16bb5799cfdbe", "rated_matches": 54, "raw_elo_rating": 1489.9472910874329, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 31.022925443196662, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 30, "generated_at": "2026-07-02T06:10:40Z", "losses": 6, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-08e2baea96c43eb4", "rated_matches": 36, "raw_elo_rating": 1449.9398243337023, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 18.637967876169636, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 38, "generated_at": "2026-07-01T00:15:48Z", "losses": 0, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-1e168b9e73c26073", "rated_matches": 38, "raw_elo_rating": 1494.110316710008, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 29.60064491715948, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 45, "generated_at": "2026-07-02T16:51:45Z", "losses": 2, "model": "google/gemini-3.5-flash", "point_rating_method": "sequential_elo", "public_id": "E-ef7a835bdb46a90e", "rated_matches": 54, "raw_elo_rating": 1499.278211372801, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 33.25253493848372, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 57, "generated_at": "2026-07-24T13:40:00Z", "losses": 3, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-60dfb882a81b3944", "rated_matches": 64, "raw_elo_rating": 1490.350042065004, "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": 32.15192038613775, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 63, "generated_at": "2026-07-24T13:40:00Z", "losses": 1, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-f2b9f6de4830b5f8", "rated_matches": 64, "raw_elo_rating": 1482.1921841435394, "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": 30.20261239436096, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 62, "generated_at": "2026-07-24T13:40:00Z", "losses": 4, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-62275b0c39dda32a", "rated_matches": 66, "raw_elo_rating": 1470.9407016695134, "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": 27.69237075496183, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 61, "generated_at": "2026-07-24T13:40:00Z", "losses": 1, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-e49b9c0097a352eb", "rated_matches": 62, "raw_elo_rating": 1481.9137366439209, "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": 29.94937076585172, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 59, "generated_at": "2026-07-02T16:51:45Z", "losses": 6, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-f4948a32cdd115a9", "rated_matches": 68, "raw_elo_rating": 1462.112751652437, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 25.753419845975525, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 44, "generated_at": "2026-07-02T06:10:40Z", "losses": 3, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-3082b8a32a9c1e1f", "rated_matches": 50, "raw_elo_rating": 1498.9538966960165, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 32.67917105045695, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 54, "generated_at": "2026-07-01T00:15:48Z", "losses": 4, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-4f2717a1b63468f4", "rated_matches": 58, "raw_elo_rating": 1481.8972078750385, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 29.54391574402747, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 46, "generated_at": "2026-07-02T16:51:45Z", "losses": 2, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-6724998b59176607", "rated_matches": 48, "raw_elo_rating": 1480.1650165924148, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 27.919189168328465, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 59, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 51, "generated_at": "2026-07-01T00:15:48Z", "losses": 6, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-6a4ccfcf11c5e3f3", "rated_matches": 59, "raw_elo_rating": 1480.7550497920456, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 29.375129293410357, "uncertainty": 20.79972243679028, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 43, "generated_at": "2026-07-02T06:10:40Z", "losses": 2, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-a92f8113f0090156", "rated_matches": 46, "raw_elo_rating": 1477.3205291766571, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 26.95201475987576, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 55, "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": 58, "raw_elo_rating": 1485.0578421415407, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 30.29914459136565, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 30, "generated_at": "2026-07-02T16:51:45Z", "losses": 12, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-8460841e3919c568", "rated_matches": 56, "raw_elo_rating": 1534.4980840240307, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 41.89639389555927, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 50, "generated_at": "2026-07-10T05:30:29Z", "losses": 0, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-e2dda893ae4363f2", "rated_matches": 50, "raw_elo_rating": 1491.9181454193697, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 30.997988769059855, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 25, "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": 58, "raw_elo_rating": 1554.6276258057092, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 46.92274071038185, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 22 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 50, "generated_at": "2026-07-10T05:30:29Z", "losses": 2, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-82ad98d8d570daab", "rated_matches": 52, "raw_elo_rating": 1487.2623907567247, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 30.140455882095676, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "inclusionai/ling-3.0-flash", "point_rating_method": "sequential_elo", "public_id": "E-129026c5e53b35ad", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "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": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 26, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 13, "draws": 24, "generated_at": "2026-07-02T16:51:45Z", "losses": 2, "model": "minimax/minimax-m3", "point_rating_method": "sequential_elo", "public_id": "E-cad87bcb23d33fef", "rated_matches": 26, "raw_elo_rating": 1468.2779761828997, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 20.338734282488755, "uncertainty": 52.475044864937615, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 25, "generated_at": "2026-07-02T16:51:45Z", "losses": 5, "model": "moonshotai/kimi-k2.7-code", "point_rating_method": "sequential_elo", "public_id": "E-85c8a9372a607001", "rated_matches": 32, "raw_elo_rating": 1459.5981620032649, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 20.020731887899807, "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": 28, "generated_at": "2026-07-24T14:00:00Z", "losses": 4, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-8825a1d540d89836", "rated_matches": 32, "raw_elo_rating": 1469.0416443249453, "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": 22.277237914000036, "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": 15, "draws": 24, "generated_at": "2026-07-21T14:43:57Z", "losses": 3, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-be8e56a3b58c5bcc", "rated_matches": 30, "raw_elo_rating": 1513.034788159119, "reasoning": "high", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 32.26100494924303, "uncertainty": 46.05265101338746, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 52, "generated_at": "2026-07-02T16:51:45Z", "losses": 2, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-bd70ebbd81fdbef0", "rated_matches": 54, "raw_elo_rating": 1479.6156043304468, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 28.554184291069387, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 45, "generated_at": "2026-07-02T16:51:45Z", "losses": 2, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-8f0c6569aa132f8e", "rated_matches": 48, "raw_elo_rating": 1484.5879724595852, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 28.976047880768927, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "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": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "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": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 30, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 15, "draws": 26, "generated_at": "2026-07-02T16:51:45Z", "losses": 2, "model": "qwen/qwen3.7-max", "point_rating_method": "sequential_elo", "public_id": "E-95265340f8562bfd", "rated_matches": 30, "raw_elo_rating": 1499.9888156481884, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 29.143689261610728, "uncertainty": 46.05265101338746, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 28, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 14, "draws": 25, "generated_at": "2026-07-02T16:51:45Z", "losses": 2, "model": "qwen/qwen3.7-plus", "point_rating_method": "sequential_elo", "public_id": "E-57293d5b71f14882", "rated_matches": 28, "raw_elo_rating": 1497.4309640195622, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 27.950412402617552, "uncertainty": 49.09766908852594, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 49, "generated_at": "2026-07-02T16:51:45Z", "losses": 4, "model": "stepfun/step-3.7-flash", "point_rating_method": "sequential_elo", "public_id": "E-0ccea44addccfff0", "rated_matches": 54, "raw_elo_rating": 1497.5007403786417, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 32.827810893590744, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 63, "generated_at": "2026-07-24T13:40:00Z", "losses": 5, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-63e0985794df5d5b", "rated_matches": 68, "raw_elo_rating": 1476.5603955656177, "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": 29.205662826109684, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 29, "generated_at": "2026-07-17T22:36:00Z", "losses": 8, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-081ac2f1dd1c34b2", "rated_matches": 54, "raw_elo_rating": 1579.9832825904505, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 52.5368914222546, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugin_count": 1, "attempted_matches": 78, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 39, "draws": 52, "generated_at": "2026-07-24T14:00:00Z", "losses": 13, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-da5ea0258e71b6ab", "rated_matches": 78, "raw_elo_rating": 1504.8822556582252, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 36.72601406890413, "uncertainty": 12.5043950463012, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 26, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 13, "draws": 23, "generated_at": "2026-07-02T16:51:45Z", "losses": 2, "model": "x-ai/grok-build-0.1", "point_rating_method": "sequential_elo", "public_id": "E-99592fa0331c6679", "rated_matches": 26, "raw_elo_rating": 1495.6785070208127, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 26.8860502881689, "uncertainty": 52.475044864937615, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 28, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 14, "draws": 26, "generated_at": "2026-07-02T16:51:45Z", "losses": 1, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-5b213ae773e821cc", "rated_matches": 28, "raw_elo_rating": 1493.0334253932465, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 26.899627101997144, "uncertainty": 49.09766908852594, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 26, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 13, "draws": 23, "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": 26, "raw_elo_rating": 1464.4614016431726, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 19.426769484483785, "uncertainty": 52.475044864937615, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 30, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 15, "draws": 25, "generated_at": "2026-07-02T06:10:40Z", "losses": 3, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-c37f25e181320efb", "rated_matches": 30, "raw_elo_rating": 1484.770314980792, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 25.507251208949754, "uncertainty": 46.05265101338746, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 38, "generated_at": "2026-07-11T17:22:09Z", "losses": 2, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-32435b01ac08ed41", "rated_matches": 40, "raw_elo_rating": 1470.8448216282686, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 24.41934796442663, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 0 } ], "GB2-03": [ { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 5, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 23, "generated_at": "2026-07-02T16:51:45Z", "losses": 10, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-823b961281482cd1", "rated_matches": 40, "raw_elo_rating": 1461.662536911419, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 38.63559627801959, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 0, "generated_at": "2026-07-25T15:48:00Z", "losses": 9, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-bd02f4c2907d0a7c", "rated_matches": 40, "raw_elo_rating": 1762.3109287237023, "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": 89.51905887569116, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 31 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 2, "generated_at": "2026-07-25T15:48:00Z", "losses": 4, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-d8babc5495b1a188", "rated_matches": 40, "raw_elo_rating": 1790.8153742206016, "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": 94.34331513585578, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 22, "capped_draws": 1, "coverage_status": "under_covered", "distinct_rated_opponents": 11, "draws": 11, "generated_at": "2026-07-02T16:51:45Z", "losses": 8, "model": "cohere/north-mini-code", "point_rating_method": "sequential_elo", "public_id": "E-0f669ae82234cf76", "rated_matches": 22, "raw_elo_rating": 1447.2565796679385, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 32.65407606258489, "uncertainty": 60.5072070285374, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 30, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 15, "draws": 9, "generated_at": "2026-07-01T00:15:48Z", "losses": 9, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-32e04fe5ad231857", "rated_matches": 30, "raw_elo_rating": 1546.9358887216838, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 51.48147323629893, "uncertainty": 46.05265101338746, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 14, "generated_at": "2026-07-02T16:51:45Z", "losses": 13, "model": "google/gemini-3.5-flash", "point_rating_method": "sequential_elo", "public_id": "E-8ed795ea8fd1e0aa", "rated_matches": 50, "raw_elo_rating": 1586.8467498305283, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 60.91553236200583, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 3, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 21, "generated_at": "2026-07-24T13:40:00Z", "losses": 16, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-36e89f1dca2cd568", "rated_matches": 52, "raw_elo_rating": 1539.062970554589, "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": 53.008912249425926, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 17, "generated_at": "2026-07-24T13:40:00Z", "losses": 16, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-e51f710b50e975e5", "rated_matches": 50, "raw_elo_rating": 1502.0617027417863, "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": 46.56602346765769, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 2, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 24, "generated_at": "2026-07-24T13:40:00Z", "losses": 12, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-9b5d467ecf278026", "rated_matches": 50, "raw_elo_rating": 1566.0655294136466, "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": 57.39839912393218, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 3, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 13, "generated_at": "2026-07-24T13:40:00Z", "losses": 18, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-f44c7c8e627e08cd", "rated_matches": 54, "raw_elo_rating": 1552.608731840876, "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": 55.47211453610619, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 26, "generated_at": "2026-07-02T16:51:45Z", "losses": 11, "model": "gpt-5", "point_rating_method": "sequential_elo", "public_id": "E-e724ba162431d43a", "rated_matches": 42, "raw_elo_rating": 1435.8623185574695, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 34.51782318989246, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 2, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 24, "generated_at": "2026-07-02T16:51:45Z", "losses": 19, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-496f83ad0bd69447", "rated_matches": 54, "raw_elo_rating": 1403.617820599916, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 30.256036000566052, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 7, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 18, "generated_at": "2026-07-01T00:15:48Z", "losses": 12, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-3e164d6fc6c16cbb", "rated_matches": 44, "raw_elo_rating": 1548.059725737291, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 53.73878477740568, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 13, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 25, "generated_at": "2026-07-02T06:10:40Z", "losses": 9, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-7cbcc752e71e2d3b", "rated_matches": 40, "raw_elo_rating": 1468.4407340067614, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 39.782777329950335, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 9, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 34, "generated_at": "2026-07-02T16:51:45Z", "losses": 7, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-9e39bdd48b7328c7", "rated_matches": 52, "raw_elo_rating": 1527.160673130626, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 50.99449899363607, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 4, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 24, "generated_at": "2026-07-01T00:15:48Z", "losses": 15, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-0ad5302188ed9e2f", "rated_matches": 48, "raw_elo_rating": 1411.064865920198, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 30.973667967146064, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 2, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 19, "generated_at": "2026-07-02T16:51:45Z", "losses": 13, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-c002b0ea38b845f8", "rated_matches": 40, "raw_elo_rating": 1471.7215759387857, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 40.338045883793995, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 15, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 32, "generated_at": "2026-07-10T05:30:29Z", "losses": 4, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-0300c20cb034e3a4", "rated_matches": 40, "raw_elo_rating": 1487.0489962766576, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 42.932146636436144, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 2, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 12, "generated_at": "2026-07-10T05:30:29Z", "losses": 9, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-b741de451c385e8e", "rated_matches": 44, "raw_elo_rating": 1594.5085265402074, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 61.60004691193783, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 24, "generated_at": "2026-07-10T05:30:29Z", "losses": 8, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-e44c62bb88a3042a", "rated_matches": 38, "raw_elo_rating": 1504.641480334261, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 45.64189418693135, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-3dc5f5cc9bb215b7", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 18, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 9, "draws": 7, "generated_at": "2026-07-21T14:43:57Z", "losses": 1, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-0d3d2270a391a708", "rated_matches": 18, "raw_elo_rating": 1615.5137739533775, "reasoning": "high", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 59.715907303989454, "uncertainty": 70.95786693528086, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugin_count": 1, "attempted_matches": 20, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 10, "draws": 4, "generated_at": "2026-07-24T14:00:00Z", "losses": 8, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-b97350a867368460", "rated_matches": 20, "raw_elo_rating": 1515.952994031412, "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": 43.623743400869515, "uncertainty": 65.3589451179962, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 26, "capped_draws": 2, "coverage_status": "under_covered", "distinct_rated_opponents": 13, "draws": 16, "generated_at": "2026-07-02T16:51:45Z", "losses": 7, "model": "nex-agi/nex-n2-pro", "point_rating_method": "sequential_elo", "public_id": "E-57ad2863cbf32d58", "rated_matches": 26, "raw_elo_rating": 1476.5001108946622, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 38.690946889939994, "uncertainty": 52.475044864937615, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 4, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 28, "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": 46, "raw_elo_rating": 1431.961147134627, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 34.30664851641847, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-08762a3df1a52f6b", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-936fb7956df3d03b", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 5, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 29, "generated_at": "2026-07-17T22:36:00Z", "losses": 14, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-09ef87ab56d05a09", "rated_matches": 54, "raw_elo_rating": 1491.5322019169912, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 45.135171413796165, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 4, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 22, "generated_at": "2026-07-24T14:00:00Z", "losses": 15, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-cbed46472ce4dd05", "rated_matches": 60, "raw_elo_rating": 1541.5973937371334, "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": 54.06905016019426, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 7, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 19, "generated_at": "2026-07-17T22:36:00Z", "losses": 9, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-d5ed477108214e1c", "rated_matches": 42, "raw_elo_rating": 1542.807683594637, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 52.6178717185429, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 20, "capped_draws": 1, "coverage_status": "under_covered", "distinct_rated_opponents": 10, "draws": 10, "generated_at": "2026-07-02T16:51:45Z", "losses": 5, "model": "x-ai/grok-build-0.1", "point_rating_method": "sequential_elo", "public_id": "E-2a93343a8a88fd59", "rated_matches": 20, "raw_elo_rating": 1527.633626050185, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 45.60064072888019, "uncertainty": 65.3589451179962, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 30, "capped_draws": 6, "coverage_status": "under_covered", "distinct_rated_opponents": 15, "draws": 19, "generated_at": "2026-07-11T17:22:09Z", "losses": 6, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-40aa28533b1afda1", "rated_matches": 30, "raw_elo_rating": 1483.8175424040835, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 40.79896136680666, "uncertainty": 46.05265101338746, "unilateral_faults": 0, "wins": 5 } ], "GB2-04": [ { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 24, "generated_at": "2026-07-02T16:51:45Z", "losses": 15, "model": "claude-fable-5", "point_rating_method": "sequential_elo", "public_id": "E-eb1f17ce19beffd0", "rated_matches": 56, "raw_elo_rating": 1566.7841216373108, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 49.32044382130511, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 40, "generated_at": "2026-07-02T16:51:45Z", "losses": 6, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-caf91ab5b69b1e64", "rated_matches": 50, "raw_elo_rating": 1471.7037725606615, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 29.776397542600765, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 28, "generated_at": "2026-07-25T15:48:00Z", "losses": 10, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-048d3dcf802043b4", "rated_matches": 52, "raw_elo_rating": 1542.4583062266756, "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": 44.083596095880694, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 17, "generated_at": "2026-07-25T15:48:00Z", "losses": 14, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-d0f0a2b1c4bbddae", "rated_matches": 48, "raw_elo_rating": 1533.973142353106, "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": 41.95533146404428, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 32, "generated_at": "2026-07-02T16:51:45Z", "losses": 7, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-b1fc5b99a5deb881", "rated_matches": 46, "raw_elo_rating": 1487.5701896988592, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 32.47196362002854, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 18, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 9, "draws": 12, "generated_at": "2026-07-02T16:51:45Z", "losses": 4, "model": "cohere/north-mini-code", "point_rating_method": "sequential_elo", "public_id": "E-1460cf3cd86be35c", "rated_matches": 18, "raw_elo_rating": 1479.047030105418, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 24.11662065009035, "uncertainty": 70.95786693528086, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 33, "generated_at": "2026-07-01T00:15:48Z", "losses": 4, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-5d143d6301429619", "rated_matches": 38, "raw_elo_rating": 1471.716990074414, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 28.177411381216853, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 36, "generated_at": "2026-07-02T16:51:45Z", "losses": 2, "model": "google/gemini-3.1-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-860c31323fa5eda7", "rated_matches": 42, "raw_elo_rating": 1497.0294371743323, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 33.82771565073253, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 32, "generated_at": "2026-07-02T16:51:45Z", "losses": 8, "model": "google/gemini-3.5-flash", "point_rating_method": "sequential_elo", "public_id": "E-32cfa6c9dfb1d16f", "rated_matches": 52, "raw_elo_rating": 1535.795958549268, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 42.75642364948741, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 50, "generated_at": "2026-07-24T13:40:00Z", "losses": 4, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-2fe680857b884561", "rated_matches": 61, "raw_elo_rating": 1505.7253482509934, "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": 37.5917500959702, "uncertainty": 19.750063500095248, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 48, "generated_at": "2026-07-24T13:40:00Z", "losses": 11, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-5c270e2afa7b70f5", "rated_matches": 63, "raw_elo_rating": 1472.9002203129974, "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": 31.212197117191156, "uncertainty": 18.75, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 63, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 37, "generated_at": "2026-07-24T13:40:00Z", "losses": 10, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-1ff96286ae16ecd4", "rated_matches": 62, "raw_elo_rating": 1499.79460936863, "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": 36.49095343062815, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 46, "generated_at": "2026-07-24T13:40:00Z", "losses": 8, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-d109ab12db58a65f", "rated_matches": 62, "raw_elo_rating": 1478.0034412795826, "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": 32.15004550104347, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 24, "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": 32, "raw_elo_rating": 1517.6711255592445, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 36.22017754259853, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 39, "generated_at": "2026-07-02T16:51:45Z", "losses": 7, "model": "gpt-5", "point_rating_method": "sequential_elo", "public_id": "E-6f1aae863396df76", "rated_matches": 60, "raw_elo_rating": 1548.729486332967, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 46.07577553411435, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 40, "generated_at": "2026-07-02T16:51:45Z", "losses": 7, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-0b4132559ee98caf", "rated_matches": 58, "raw_elo_rating": 1513.1147492207922, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 38.809666551358085, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 37, "generated_at": "2026-07-01T00:15:48Z", "losses": 5, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-6d633c9c2680eb32", "rated_matches": 54, "raw_elo_rating": 1554.4248661845468, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 46.66823942277007, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 31, "generated_at": "2026-07-02T16:51:45Z", "losses": 7, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-74f5bcc8ad3796a5", "rated_matches": 56, "raw_elo_rating": 1565.0718297202598, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 48.979346844304295, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 48, "generated_at": "2026-07-02T06:10:40Z", "losses": 6, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-f9e13a78abccfd1f", "rated_matches": 64, "raw_elo_rating": 1528.4438868136224, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 42.35368309302285, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 34, "generated_at": "2026-07-09T17:30:50Z", "losses": 8, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-a32cb67d48c62b3b", "rated_matches": 58, "raw_elo_rating": 1559.1494715097724, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 47.98000979334802, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 43, "generated_at": "2026-07-01T00:15:48Z", "losses": 13, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-fd2be90162c92ecf", "rated_matches": 70, "raw_elo_rating": 1532.7044940450228, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 43.62923896691468, "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": 40, "generated_at": "2026-07-02T16:51:45Z", "losses": 13, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-9e7bdad81107b7e4", "rated_matches": 62, "raw_elo_rating": 1454.5510147312568, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 27.47820671040979, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 59, "generated_at": "2026-07-10T05:30:29Z", "losses": 1, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-5389e160269f5ceb", "rated_matches": 62, "raw_elo_rating": 1512.834046928935, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 39.08847356683884, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 50, "generated_at": "2026-07-10T05:30:29Z", "losses": 4, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-c81bf4d15f3d48f1", "rated_matches": 58, "raw_elo_rating": 1489.7668442731074, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 34.15864897798004, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 49, "generated_at": "2026-07-10T05:30:29Z", "losses": 5, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-89c18d144e85d89f", "rated_matches": 62, "raw_elo_rating": 1510.4667796354577, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 38.61690227136209, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "inclusionai/ling-3.0-flash", "point_rating_method": "sequential_elo", "public_id": "E-20e94e7276184071", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-46a1c9f4e3ff6058", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-4ccf296e55b59be3", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 20, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 10, "draws": 19, "generated_at": "2026-07-02T16:51:45Z", "losses": 1, "model": "minimax/minimax-m3", "point_rating_method": "sequential_elo", "public_id": "E-c60620c3c72a6064", "rated_matches": 20, "raw_elo_rating": 1485.2635116292065, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 26.247240589417363, "uncertainty": 65.3589451179962, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 22, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 11, "draws": 17, "generated_at": "2026-07-02T16:51:45Z", "losses": 3, "model": "moonshotai/kimi-k2.7-code", "point_rating_method": "sequential_elo", "public_id": "E-eb97811a38950c20", "rated_matches": 22, "raw_elo_rating": 1477.805603453178, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 25.53478066069057, "uncertainty": 60.5072070285374, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 20, "generated_at": "2026-07-21T14:43:57Z", "losses": 8, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-0f7ca9245c7db7c7", "rated_matches": 40, "raw_elo_rating": 1503.1676826710195, "reasoning": "high", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 34.7576378651005, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 27, "generated_at": "2026-07-24T14:00:00Z", "losses": 6, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-35e5c9532c697b2c", "rated_matches": 36, "raw_elo_rating": 1479.9223016926098, "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": 29.47164141744014, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 44, "generated_at": "2026-07-02T16:51:45Z", "losses": 7, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-7e92e17a121661f4", "rated_matches": 54, "raw_elo_rating": 1460.2028298284708, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 27.89874606250913, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 36, "generated_at": "2026-07-02T16:51:45Z", "losses": 4, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-f1288f2abfdbbfe4", "rated_matches": 44, "raw_elo_rating": 1480.001540532111, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 30.70877457082836, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-e996fd38983e3b7f", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 24, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 12, "draws": 14, "generated_at": "2026-07-02T16:51:45Z", "losses": 6, "model": "qwen/qwen3.7-max", "point_rating_method": "sequential_elo", "public_id": "E-ea08328e287de1ad", "rated_matches": 24, "raw_elo_rating": 1494.484627206166, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "first_pass", "score": 29.53576955257776, "uncertainty": 56.25, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 42, "generated_at": "2026-07-02T16:51:45Z", "losses": 3, "model": "stepfun/step-3.7-flash", "point_rating_method": "sequential_elo", "public_id": "E-25e56c6bfae33c62", "rated_matches": 50, "raw_elo_rating": 1526.1505400202454, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 40.6224615828462, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 47, "generated_at": "2026-07-24T13:40:00Z", "losses": 5, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-7ca32267720b2e1a", "rated_matches": 56, "raw_elo_rating": 1499.9771522139858, "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": 36.0121667185741, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 40, "generated_at": "2026-07-24T13:40:00Z", "losses": 12, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-d9e91f86e4e39739", "rated_matches": 58, "raw_elo_rating": 1445.7739527166314, "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": 25.39504846686978, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 47, "generated_at": "2026-07-17T22:36:00Z", "losses": 6, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-1a7064508fe2a12f", "rated_matches": 62, "raw_elo_rating": 1503.5559184005565, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 37.2402247012451, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 40, "generated_at": "2026-07-17T22:36:00Z", "losses": 9, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-83f4cc0ffc20bde5", "rated_matches": 56, "raw_elo_rating": 1504.184417188392, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 36.8502746077259, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 82, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 41, "draws": 58, "generated_at": "2026-07-24T14:00:00Z", "losses": 12, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-ba6a8e6d7fc9a48d", "rated_matches": 82, "raw_elo_rating": 1504.4453110108711, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 38.71014819221992, "uncertainty": 11.132129994845172, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugin_count": 1, "attempted_matches": 22, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 11, "draws": 18, "generated_at": "2026-07-02T16:51:45Z", "losses": 3, "model": "x-ai/grok-build-0.1", "point_rating_method": "sequential_elo", "public_id": "E-85934b32572399da", "rated_matches": 22, "raw_elo_rating": 1479.2974345534708, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 25.831960757984973, "uncertainty": 60.5072070285374, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 30, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 15, "draws": 23, "generated_at": "2026-07-02T06:10:40Z", "losses": 5, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-00e6914e513b1656", "rated_matches": 30, "raw_elo_rating": 1468.7641962381597, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 26.03722280334275, "uncertainty": 46.05265101338746, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 30, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 15, "draws": 19, "generated_at": "2026-07-01T00:15:48Z", "losses": 10, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-23e877112cb95491", "rated_matches": 30, "raw_elo_rating": 1420.0369437120878, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 16.33051428671147, "uncertainty": 46.05265101338746, "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, "generated_at": "2026-07-02T16:51:45Z", "losses": 4, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-2f7e15b8aa123825", "rated_matches": 26, "raw_elo_rating": 1460.9897364084577, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 23.46501417222989, "uncertainty": 52.475044864937615, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 30, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 15, "draws": 13, "generated_at": "2026-07-02T16:51:45Z", "losses": 8, "model": "xiaomi/mimo-v2.5-pro", "point_rating_method": "sequential_elo", "public_id": "E-ffdebde8a72ed049", "rated_matches": 30, "raw_elo_rating": 1489.28005979839, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 30.12408379431653, "uncertainty": 46.05265101338746, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 24, "generated_at": "2026-07-11T17:22:09Z", "losses": 8, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-912f31ad14c4bf0a", "rated_matches": 38, "raw_elo_rating": 1467.1029555456405, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 27.2582729948998, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 11, "generated_at": "2026-07-01T00:15:48Z", "losses": 12, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-947248ef34168cde", "rated_matches": 34, "raw_elo_rating": 1520.0418361385473, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 37.09457411598848, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 11 } ], "GB2-05": [ { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 24, "model": "claude-fable-5", "point_rating_method": "sequential_elo", "public_id": "E-ad7cf41c05ec3f64", "rated_matches": 54, "raw_elo_rating": 1564.6835482433685, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 52.452932914118634, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 30 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 28, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-924d7e6ee41b562e", "rated_matches": 60, "raw_elo_rating": 1525.7692733725237, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 48.12979094866205, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 0, "generated_at": "2026-07-25T10:50:00Z", "losses": 17, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-32c377b229530444", "rated_matches": 56, "raw_elo_rating": 1760.302528451473, "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": 75.93302615623676, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 39 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 0, "generated_at": "2026-07-25T10:50:00Z", "losses": 11, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-d7111b534ebcaba2", "rated_matches": 56, "raw_elo_rating": 1820.5237005744175, "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": 83.1262514808048, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 45 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 27, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-e0a09b1ea3f11175", "rated_matches": 62, "raw_elo_rating": 1520.9036581003338, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 47.646494167430816, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 35 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 16, "model": "cohere/north-mini-code", "point_rating_method": "sequential_elo", "public_id": "E-a0518a43c688d1e2", "rated_matches": 38, "raw_elo_rating": 1495.2464344570433, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "first_pass", "score": 42.950656228503576, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 22 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 0, "generated_at": "2026-07-01T00:15:48Z", "losses": 27, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-06a41d0e11b18b77", "rated_matches": 46, "raw_elo_rating": 1416.3172699890229, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 34.20429693319734, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 28, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-2c1cbd253f3a9d69", "rated_matches": 48, "raw_elo_rating": 1370.0003984534594, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 28.81560673275056, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 37, "model": "google/gemini-3.1-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-7603462aff103041", "rated_matches": 64, "raw_elo_rating": 1321.2599404656255, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 23.893026239049423, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 27 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 37, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 40, "model": "google/gemini-3.5-flash", "point_rating_method": "sequential_elo", "public_id": "E-a7ce764239377b3f", "rated_matches": 74, "raw_elo_rating": 1469.3980693923404, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 41.99685872000467, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 34, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-c311887ca24f8a76", "rated_matches": 68, "raw_elo_rating": 1371.5676509074417, "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": 30.076459313809973, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 33, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-e3c1bc55ae62b8db", "rated_matches": 64, "raw_elo_rating": 1367.3874948935063, "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": 29.40281425834644, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 31 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 15, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-9e479871cca0aeaa", "rated_matches": 72, "raw_elo_rating": 1811.4294073860576, "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": 82.77633717030919, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 57 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 37, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 39, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-c7d3f2597dfefeb3", "rated_matches": 74, "raw_elo_rating": 1599.0133940880332, "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": 57.47899238139743, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 35 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 18, "model": "google/gemma-4-31b-it", "point_rating_method": "sequential_elo", "public_id": "E-fd1bc1e2e6ac48fb", "rated_matches": 32, "raw_elo_rating": 1490.3861000662391, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 41.70361565070743, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 31, "model": "gpt-5", "point_rating_method": "sequential_elo", "public_id": "E-9e5b308c41a36374", "rated_matches": 58, "raw_elo_rating": 1567.8741951513823, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 53.05626716087649, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 27 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 32, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-cafab3c275850d3b", "rated_matches": 64, "raw_elo_rating": 1525.8350202224913, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 48.32886155421666, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 30, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-0791f6b66243ec1a", "rated_matches": 58, "raw_elo_rating": 1473.506918125209, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 41.784399427558654, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 33, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-539afc540807da47", "rated_matches": 58, "raw_elo_rating": 1388.3021280033795, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 31.606961286242058, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 0, "generated_at": "2026-07-01T00:15:48Z", "losses": 32, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-ce84b7a3c6105fb2", "rated_matches": 56, "raw_elo_rating": 1420.6809546650486, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 35.3663214706702, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 45, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-83cfa14483bf0d43", "rated_matches": 58, "raw_elo_rating": 1265.5935646074108, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 16.94981804832515, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 16, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-8e40431df091d53f", "rated_matches": 68, "raw_elo_rating": 1741.0650102044026, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 74.21173049102529, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 52 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 0, "generated_at": "2026-07-09T17:30:50Z", "losses": 40, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-a0d8c8fd6b01598c", "rated_matches": 66, "raw_elo_rating": 1407.2421202586966, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 34.25244224396947, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 0, "generated_at": "2026-07-01T00:15:48Z", "losses": 40, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-ff2b4db95370e3d6", "rated_matches": 62, "raw_elo_rating": 1328.4399839095454, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 24.6573272939897, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 22 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 21, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-ffa82d1e96e897ab", "rated_matches": 58, "raw_elo_rating": 1652.109166288075, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 63.117863543585464, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 37 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 29, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-e917387a1c57aa23", "rated_matches": 54, "raw_elo_rating": 1566.3786416398286, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 52.65540636850494, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 20, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-d61f8454991c5422", "rated_matches": 60, "raw_elo_rating": 1639.493660691125, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 61.71380324937027, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 40 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 28, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-9664e98d37ece097", "rated_matches": 60, "raw_elo_rating": 1554.884848939414, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 51.6075528075571, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-52b991e608dc1672", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-9061c6162106c911", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 28, "model": "minimax/minimax-m3", "point_rating_method": "sequential_elo", "public_id": "E-fb8ac45946e32e22", "rated_matches": 32, "raw_elo_rating": 1259.1865795370063, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 14.08757651577286, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 17, "model": "moonshotai/kimi-k2.7-code", "point_rating_method": "sequential_elo", "public_id": "E-952fba19b28982d5", "rated_matches": 32, "raw_elo_rating": 1544.771611656525, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 48.199790093512426, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 0, "generated_at": "2026-07-21T14:43:57Z", "losses": 18, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-4a1443311507f194", "rated_matches": 36, "raw_elo_rating": 1546.1994437538688, "reasoning": "high", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 48.832774381854, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 24, "model": "nex-agi/nex-n2-pro", "point_rating_method": "sequential_elo", "public_id": "E-5f76f577111bee8d", "rated_matches": 32, "raw_elo_rating": 1336.8196578257846, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 23.360598031045697, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 32, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-343b92f3dda3dcb5", "rated_matches": 68, "raw_elo_rating": 1497.821508842899, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 45.157076581963906, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 36 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 29, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-5ef540286ecbb63d", "rated_matches": 62, "raw_elo_rating": 1447.33708487285, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 38.85920360288856, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 33 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-53ce0020411c86d4", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-62e15a037ee860c1", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 19, "model": "qwen/qwen3.7-max", "point_rating_method": "sequential_elo", "public_id": "E-435ec29661cdc285", "rated_matches": 34, "raw_elo_rating": 1512.8093379384543, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 44.62312914680338, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 20, "model": "qwen/qwen3.7-plus", "point_rating_method": "sequential_elo", "public_id": "E-6cc7454f585005c4", "rated_matches": 44, "raw_elo_rating": 1491.7047630621466, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 43.055902071000624, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 24, "model": "stepfun/step-3.7-flash", "point_rating_method": "sequential_elo", "public_id": "E-7b9b33921ba865f5", "rated_matches": 56, "raw_elo_rating": 1572.8040677708518, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 53.536938067285334, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 36, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-01a1df4eac0e6aef", "rated_matches": 64, "raw_elo_rating": 1346.8039660609616, "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": 26.944177940790823, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 42, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-ae60ed096a69eeff", "rated_matches": 68, "raw_elo_rating": 1386.8091340232932, "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": 31.897005451787702, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 84, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 42, "draws": 0, "generated_at": "2026-07-24T14:00:00Z", "losses": 31, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-824ec3caceabd338", "rated_matches": 84, "raw_elo_rating": 1646.441087627935, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 63.47875935949037, "uncertainty": 10.482614454664043, "unilateral_faults": 0, "wins": 53 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 0, "generated_at": "2026-07-18T00:06:00Z", "losses": 18, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-9f28818a3063ee74", "rated_matches": 64, "raw_elo_rating": 1747.574278013794, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 74.81490273154559, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 46 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 0, "generated_at": "2026-07-18T00:06:00Z", "losses": 26, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-c0bc4ff29a3cbf96", "rated_matches": 66, "raw_elo_rating": 1704.3892195628102, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 69.74570756056913, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 40 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 17, "model": "x-ai/grok-build-0.1", "point_rating_method": "sequential_elo", "public_id": "E-4aac1b6621aeae38", "rated_matches": 38, "raw_elo_rating": 1585.890955890403, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 53.777852779521325, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 18, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-ad48cf51fe7da3cc", "rated_matches": 38, "raw_elo_rating": 1473.798526608742, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 40.38877261756302, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 20, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-faaa866ee28d6401", "rated_matches": 34, "raw_elo_rating": 1432.3565317225514, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 35.01330019954669, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 22, "model": "xiaomi/mimo-v2.5-pro", "point_rating_method": "sequential_elo", "public_id": "E-9c228ad72a159b33", "rated_matches": 36, "raw_elo_rating": 1436.0176886705406, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 35.67191810770685, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 0, "generated_at": "2026-07-01T00:15:48Z", "losses": 19, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-1a8c2012f200fd88", "rated_matches": 48, "raw_elo_rating": 1640.6299431856698, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 61.141435442457045, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 0, "generated_at": "2026-07-11T17:22:09Z", "losses": 25, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-3916ba303b2ff700", "rated_matches": 46, "raw_elo_rating": 1532.8948638592171, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 48.129115579907, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 21 } ], "GB2-06": [ { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 7, "generated_at": "2026-07-02T16:51:45Z", "losses": 13, "model": "claude-fable-5", "point_rating_method": "sequential_elo", "public_id": "E-e1ca3ac536f3eb1e", "rated_matches": 48, "raw_elo_rating": 1646.4648905020276, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 71.02490499954271, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 1, "generated_at": "2026-07-02T16:51:45Z", "losses": 21, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-39e283268f14261d", "rated_matches": 58, "raw_elo_rating": 1681.0254506469776, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 76.32595670280091, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 36 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 3, "generated_at": "2026-07-02T16:51:45Z", "losses": 32, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-01597b81edc004dd", "rated_matches": 68, "raw_elo_rating": 1480.3349355924784, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 50.00396058789727, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 33 }, { "admitted_plugin_count": 1, "attempted_matches": 30, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 15, "draws": 1, "generated_at": "2026-07-02T16:51:45Z", "losses": 23, "model": "cohere/north-mini-code", "point_rating_method": "sequential_elo", "public_id": "E-78dfcb6ce8b3efaa", "rated_matches": 30, "raw_elo_rating": 1317.998444155539, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "first_pass", "score": 25.119335087150468, "uncertainty": 46.05265101338746, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 2, "generated_at": "2026-07-02T06:10:40Z", "losses": 23, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-6f20412107151172", "rated_matches": 40, "raw_elo_rating": 1383.6389637210625, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 35.153906261071285, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 0, "generated_at": "2026-07-01T00:15:48Z", "losses": 29, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-d8ca2fcf88af96c7", "rated_matches": 42, "raw_elo_rating": 1278.5777811236649, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 21.296435602250163, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 29, "model": "google/gemini-3.1-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-a10101fbca309818", "rated_matches": 52, "raw_elo_rating": 1429.7879988349669, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 42.33396509337835, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 11, "generated_at": "2026-07-02T16:51:45Z", "losses": 9, "model": "google/gemini-3.5-flash", "point_rating_method": "sequential_elo", "public_id": "E-35d6e87056063577", "rated_matches": 50, "raw_elo_rating": 1732.4144195081535, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 82.67382914279403, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 30 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 1, "generated_at": "2026-07-24T13:40:00Z", "losses": 36, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-100ff33157ca87e5", "rated_matches": 60, "raw_elo_rating": 1333.6124881844505, "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": 29.96737981748139, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 1, "generated_at": "2026-07-24T13:40:00Z", "losses": 33, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-92d447632fa55355", "rated_matches": 62, "raw_elo_rating": 1485.9208961239233, "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": 50.45142926942041, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 10, "generated_at": "2026-07-24T13:40:00Z", "losses": 24, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-aa5fab059f4d0186", "rated_matches": 64, "raw_elo_rating": 1553.219249586199, "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": 59.558511878686765, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 30 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 4, "generated_at": "2026-07-24T13:40:00Z", "losses": 12, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-dd9886be3d9e45b5", "rated_matches": 64, "raw_elo_rating": 1855.5383801769424, "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": 100.0, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 48 }, { "admitted_plugin_count": 1, "attempted_matches": 30, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 15, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 21, "model": "google/gemma-4-31b-it", "point_rating_method": "sequential_elo", "public_id": "E-41987f96551bf9d3", "rated_matches": 30, "raw_elo_rating": 1361.5388402568406, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 30.94377103431437, "uncertainty": 46.05265101338746, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 7, "generated_at": "2026-07-02T16:51:45Z", "losses": 25, "model": "gpt-5", "point_rating_method": "sequential_elo", "public_id": "E-816d262cd933cdb9", "rated_matches": 54, "raw_elo_rating": 1498.859087874097, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 51.70853629281069, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 22 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 11, "generated_at": "2026-07-02T16:51:45Z", "losses": 4, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-61f3ed920d3c145d", "rated_matches": 52, "raw_elo_rating": 1788.705954908835, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 90.34672640532096, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 37 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 5, "generated_at": "2026-07-02T16:51:45Z", "losses": 19, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-3ccfe46cbdc271eb", "rated_matches": 54, "raw_elo_rating": 1503.7452804395457, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 52.36216644253991, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 30 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 0, "generated_at": "2026-07-01T00:15:48Z", "losses": 31, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-ac7c887de3c2e7af", "rated_matches": 66, "raw_elo_rating": 1575.0507387574512, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 62.5787374043566, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 35 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 2, "generated_at": "2026-07-02T16:51:45Z", "losses": 28, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-5ccde5c853d97bd9", "rated_matches": 56, "raw_elo_rating": 1576.3180575619283, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 62.19799910410298, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 5, "generated_at": "2026-07-02T06:10:40Z", "losses": 34, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-962a93f9cc008820", "rated_matches": 68, "raw_elo_rating": 1495.4760962529135, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 52.02940657206428, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 8, "generated_at": "2026-07-01T00:15:48Z", "losses": 29, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-9b6b064b63e4164b", "rated_matches": 56, "raw_elo_rating": 1506.4464307827188, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 52.85121195607604, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 2, "generated_at": "2026-07-09T17:30:50Z", "losses": 29, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-9c5263dcfd4c2ec7", "rated_matches": 62, "raw_elo_rating": 1488.9814231842397, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 50.860838586366015, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 31 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 32, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-1ea2c2c23d752166", "rated_matches": 58, "raw_elo_rating": 1448.0809451241314, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 45.16477138641322, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 6, "generated_at": "2026-07-10T10:07:13Z", "losses": 24, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-f4c50b1a9cf2c2e6", "rated_matches": 58, "raw_elo_rating": 1591.7478127385095, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 64.38321088344401, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 9, "generated_at": "2026-07-10T10:07:13Z", "losses": 13, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-acdece52463a2698", "rated_matches": 52, "raw_elo_rating": 1667.5084391584408, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 74.1340312841928, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 30 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 9, "generated_at": "2026-07-10T05:30:29Z", "losses": 19, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-a3722334e358f0fe", "rated_matches": 56, "raw_elo_rating": 1496.011348653353, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 51.455302113536305, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "inclusionai/ling-3.0-flash", "point_rating_method": "sequential_elo", "public_id": "E-6c37c8c2b8e19c4c", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "inclusionai/ling-3.0-flash", "point_rating_method": "sequential_elo", "public_id": "E-7f02a37922fd94e7", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-9b849343b9780ba9", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-a9bdeb6a9326ac2d", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 30, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 15, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 21, "model": "minimax/minimax-m3", "point_rating_method": "sequential_elo", "public_id": "E-ef8c1a9fa3580f83", "rated_matches": 30, "raw_elo_rating": 1336.3094441421288, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 27.56881318335969, "uncertainty": 46.05265101338746, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 30, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 15, "draws": 6, "generated_at": "2026-07-21T14:43:57Z", "losses": 2, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-13c9d1fee169a6f5", "rated_matches": 30, "raw_elo_rating": 1714.2525453020537, "reasoning": "high", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 78.12658439097301, "uncertainty": 46.05265101338746, "unilateral_faults": 0, "wins": 22 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 2, "generated_at": "2026-07-24T14:00:00Z", "losses": 13, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-1640f1438f9390d7", "rated_matches": 32, "raw_elo_rating": 1500.187292766553, "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": 49.786668032753, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugin_count": 1, "attempted_matches": 30, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 15, "draws": 3, "generated_at": "2026-07-02T16:51:45Z", "losses": 19, "model": "nex-agi/nex-n2-pro", "point_rating_method": "sequential_elo", "public_id": "E-209380b737b62580", "rated_matches": 30, "raw_elo_rating": 1350.0536939072658, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 29.40739320483244, "uncertainty": 46.05265101338746, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 4, "generated_at": "2026-07-02T16:51:45Z", "losses": 26, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-1ea0c8193f35ca72", "rated_matches": 62, "raw_elo_rating": 1555.945264596268, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 59.81864880409941, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 10, "generated_at": "2026-07-02T16:51:45Z", "losses": 24, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-69e964db7b91b1bb", "rated_matches": 60, "raw_elo_rating": 1533.5565018760735, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 56.714061176471255, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 1, "generated_at": "2026-07-02T16:51:45Z", "losses": 34, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-f225b6990e542d31", "rated_matches": 54, "raw_elo_rating": 1369.2947045902554, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 34.37659816081083, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-b582570ce841ee30", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 2, "generated_at": "2026-07-02T16:51:45Z", "losses": 17, "model": "qwen/qwen3.7-max", "point_rating_method": "sequential_elo", "public_id": "E-8283efe6f68a787e", "rated_matches": 34, "raw_elo_rating": 1497.314614258339, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 49.67243354235248, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 5, "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": 32, "raw_elo_rating": 1547.6483336535148, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 56.1355719790718, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 1, "generated_at": "2026-07-02T16:51:45Z", "losses": 33, "model": "stepfun/step-3.7-flash", "point_rating_method": "sequential_elo", "public_id": "E-6526762dce98da7c", "rated_matches": 54, "raw_elo_rating": 1388.4103550666105, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 36.933715039786, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 35, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-0825a2443d50c563", "rated_matches": 62, "raw_elo_rating": 1356.7474097662753, "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": 33.17178175285869, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 27 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 12, "generated_at": "2026-07-17T22:36:00Z", "losses": 7, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-03c854e808265e3b", "rated_matches": 56, "raw_elo_rating": 1705.4947693431316, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 79.47807808832648, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 37 }, { "admitted_plugin_count": 1, "attempted_matches": 80, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 40, "draws": 7, "generated_at": "2026-07-24T14:00:00Z", "losses": 41, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-3baaff3521870bef", "rated_matches": 80, "raw_elo_rating": 1483.7927030714934, "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": 50.96278515457614, "uncertainty": 11.805555555555554, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 3, "generated_at": "2026-07-17T22:36:00Z", "losses": 32, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-8cb8510a257ade6a", "rated_matches": 64, "raw_elo_rating": 1508.140720329728, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 53.52831854659575, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 21, "model": "x-ai/grok-build-0.1", "point_rating_method": "sequential_elo", "public_id": "E-133675db0ee21fd5", "rated_matches": 36, "raw_elo_rating": 1406.828541437424, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 37.815877694328925, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 30, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 15, "draws": 3, "generated_at": "2026-07-02T16:51:45Z", "losses": 20, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-7b4c450b6850f156", "rated_matches": 30, "raw_elo_rating": 1351.5255739443542, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 29.60428785360836, "uncertainty": 46.05265101338746, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 0, "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": 34, "raw_elo_rating": 1534.1970432183366, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 54.6062275426075, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 3, "generated_at": "2026-07-02T06:10:40Z", "losses": 14, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-72584b5bdb2d01e3", "rated_matches": 40, "raw_elo_rating": 1673.3960713457311, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 73.91496184882483, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 7, "generated_at": "2026-07-11T17:22:09Z", "losses": 12, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-bc40affcf893e495", "rated_matches": 40, "raw_elo_rating": 1595.4337214549123, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 63.485871764918144, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 21 } ], "GB2-07": [ { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 15, "model": "claude-fable-5", "point_rating_method": "sequential_elo", "public_id": "E-bc12a8303ec2def7", "rated_matches": 56, "raw_elo_rating": 1721.3733595723618, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 76.52631679447857, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 41 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 19, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-0bf7b9ed307db853", "rated_matches": 56, "raw_elo_rating": 1655.5878327465305, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 67.93204374088673, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 37 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 0, "generated_at": "2026-07-25T10:50:00Z", "losses": 4, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-54bca3ce32fa85ae", "rated_matches": 52, "raw_elo_rating": 1903.0174118422897, "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": 100.0, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 48 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 0, "generated_at": "2026-07-25T10:50:00Z", "losses": 20, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-de5e72176c4f0dc9", "rated_matches": 54, "raw_elo_rating": 1759.1370608743762, "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": 81.3350744150181, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 30, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-9e40526fba9fa8b9", "rated_matches": 66, "raw_elo_rating": 1486.9450008445583, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 46.43780435774322, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 36 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 18, "model": "cohere/north-mini-code", "point_rating_method": "sequential_elo", "public_id": "E-1c961fde1b53f0eb", "rated_matches": 36, "raw_elo_rating": 1490.616193888619, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 44.71065160481735, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 0, "generated_at": "2026-07-01T00:15:48Z", "losses": 31, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-8f2f6c973751f183", "rated_matches": 42, "raw_elo_rating": 1396.5049366327746, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 33.03775475106972, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 26, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-edc2d085c4253ed3", "rated_matches": 44, "raw_elo_rating": 1483.83321482663, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 44.62549163840255, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 46, "model": "google/gemini-3.1-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-1b3c52da51dfbdd4", "rated_matches": 56, "raw_elo_rating": 1176.6504298057089, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 5.363284090316728, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 26, "model": "google/gemini-3.5-flash", "point_rating_method": "sequential_elo", "public_id": "E-5447c508e2b0ab6c", "rated_matches": 54, "raw_elo_rating": 1476.3023229705768, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 44.38532142418434, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 35, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-2950a4947ff48aa6", "rated_matches": 62, "raw_elo_rating": 1304.2873775939768, "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": 22.37571666331624, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 27 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 42, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-42943e41c64d22d2", "rated_matches": 64, "raw_elo_rating": 1225.4888233208255, "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": 12.18349014380252, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 22 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 30, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-5f208f03ea700603", "rated_matches": 66, "raw_elo_rating": 1496.1274992814167, "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": 47.63741318795713, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 36 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 26, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-65c6c8e09fe2c210", "rated_matches": 70, "raw_elo_rating": 1444.7694103173546, "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": 41.11039333473561, "uncertainty": 15.58908290969266, "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, "generated_at": "2026-07-02T16:51:45Z", "losses": 17, "model": "google/gemma-4-31b-it", "point_rating_method": "sequential_elo", "public_id": "E-f417d302c870dfa6", "rated_matches": 36, "raw_elo_rating": 1459.431391791758, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 40.63664448996656, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 25, "model": "gpt-5", "point_rating_method": "sequential_elo", "public_id": "E-4d8b4cfcff519db6", "rated_matches": 66, "raw_elo_rating": 1571.1643984055847, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 57.44029280728862, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 41 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 24, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-22466ae84d7027e5", "rated_matches": 58, "raw_elo_rating": 1563.3796006203124, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 56.004212916192515, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 69, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 0, "generated_at": "2026-07-01T00:15:48Z", "losses": 40, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-946bc9bcbefb4ad1", "rated_matches": 69, "raw_elo_rating": 1450.0764750092626, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 41.75957179317546, "uncertainty": 16.01143046671968, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 37, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-b96fbceba82aa188", "rated_matches": 64, "raw_elo_rating": 1489.954941342898, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 46.73355216158762, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 27 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 27, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-f4d7ac8a0f5d2974", "rated_matches": 56, "raw_elo_rating": 1506.1518610341518, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 48.40961066339226, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 47, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-acb1779a65c941b4", "rated_matches": 54, "raw_elo_rating": 1182.0036362477724, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 5.937909127774502, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 49, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-bea6d7d9558897f9", "rated_matches": 58, "raw_elo_rating": 1180.2311075914536, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 5.94939192372365, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 0, "generated_at": "2026-07-01T00:15:48Z", "losses": 51, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-c4ad375a0a870e69", "rated_matches": 66, "raw_elo_rating": 1287.0525736672737, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 20.323700186242597, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 55, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 0, "generated_at": "2026-07-09T17:30:50Z", "losses": 28, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-ce04fd14b6f43868", "rated_matches": 55, "raw_elo_rating": 1567.6900578052491, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 56.38748335772921, "uncertainty": 23.065310478106092, "unilateral_faults": 0, "wins": 27 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 26, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-640b3078b8bce40e", "rated_matches": 58, "raw_elo_rating": 1637.762905975935, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 65.72170653066799, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 38, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-45c76cf9faaba10a", "rated_matches": 70, "raw_elo_rating": 1502.494574211802, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 48.65165422462213, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 25, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-cc78d54d18d4c3f1", "rated_matches": 58, "raw_elo_rating": 1613.924246727442, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 62.60740530517968, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 33 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 27, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-aca193dd2a8774fb", "rated_matches": 54, "raw_elo_rating": 1416.8015449056545, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 36.612092900151, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 27 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "inclusionai/ling-3.0-flash", "point_rating_method": "sequential_elo", "public_id": "E-57b2b1d3b488c246", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "inclusionai/ling-3.0-flash", "point_rating_method": "sequential_elo", "public_id": "E-5e20a850f6c14680", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-0ad780cd41873f27", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 18, "model": "minimax/minimax-m3", "point_rating_method": "sequential_elo", "public_id": "E-4547f4cedca403f9", "rated_matches": 34, "raw_elo_rating": 1528.3941973331473, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 49.40395561210127, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 18, "model": "moonshotai/kimi-k2.7-code", "point_rating_method": "sequential_elo", "public_id": "E-d35e87ebfc251f60", "rated_matches": 34, "raw_elo_rating": 1499.4128100931498, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 45.6178043501094, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 0, "generated_at": "2026-07-21T14:43:57Z", "losses": 12, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-3d2d4c8b0819b60b", "rated_matches": 32, "raw_elo_rating": 1611.7277808628844, "reasoning": "high", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 60.02699318566077, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 0, "generated_at": "2026-07-24T14:00:00Z", "losses": 17, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-4cc8f48bf8bccc77", "rated_matches": 36, "raw_elo_rating": 1497.3704310336243, "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": 45.59303046676025, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 15, "model": "nex-agi/nex-n2-pro", "point_rating_method": "sequential_elo", "public_id": "E-d1f432cda667f27f", "rated_matches": 34, "raw_elo_rating": 1480.9244522915517, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 43.20247072087337, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 45, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-459f395cc0af6d2e", "rated_matches": 62, "raw_elo_rating": 1172.4066172061932, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 5.146710224123554, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 30, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-f1e3e54a3d40556f", "rated_matches": 64, "raw_elo_rating": 1537.8619196179889, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 52.99215754691314, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 7, "model": "qwen/qwen3.7-max", "point_rating_method": "sequential_elo", "public_id": "E-59c7745eb1e91d63", "rated_matches": 32, "raw_elo_rating": 1700.82192229776, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 71.66632201544819, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 19, "model": "qwen/qwen3.7-plus", "point_rating_method": "sequential_elo", "public_id": "E-9d091700cb41ece2", "rated_matches": 44, "raw_elo_rating": 1491.841528725517, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 45.67170407549571, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 31, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-6df2b00898e4ba3c", "rated_matches": 68, "raw_elo_rating": 1640.3004589168615, "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": 66.56548612877529, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 37 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 32, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-8ad2285ad59d87bf", "rated_matches": 62, "raw_elo_rating": 1440.3656332366938, "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": 40.15308718960612, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 30 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 0, "generated_at": "2026-07-17T22:36:00Z", "losses": 24, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-3cfeaacb3dbbab07", "rated_matches": 58, "raw_elo_rating": 1573.6891886176236, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 57.35106561456042, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 0, "generated_at": "2026-07-17T22:36:00Z", "losses": 18, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-a1728c5ac67e11f3", "rated_matches": 66, "raw_elo_rating": 1688.6107752565024, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 72.7835800091097, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 48 }, { "admitted_plugin_count": 1, "attempted_matches": 82, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 41, "draws": 0, "generated_at": "2026-07-24T14:00:00Z", "losses": 34, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-e58f3df122cf1d29", "rated_matches": 82, "raw_elo_rating": 1654.3079800618857, "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": 68.95048504308706, "uncertainty": 11.132129994845172, "unilateral_faults": 0, "wins": 48 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 21, "model": "x-ai/grok-build-0.1", "point_rating_method": "sequential_elo", "public_id": "E-37ae0129627ee16f", "rated_matches": 32, "raw_elo_rating": 1338.4379390913737, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 24.324192945486605, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 0, "generated_at": "2026-07-01T00:15:48Z", "losses": 14, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-345a5b25cbac7f3b", "rated_matches": 32, "raw_elo_rating": 1497.9774514768028, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "first_pass", "score": 45.16656053657338, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 19, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-fa1a93f7e4d57000", "rated_matches": 32, "raw_elo_rating": 1398.4187741474352, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 32.16013649305479, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 21, "model": "xiaomi/mimo-v2.5-pro", "point_rating_method": "sequential_elo", "public_id": "E-3b160130ae038271", "rated_matches": 36, "raw_elo_rating": 1493.5745054280833, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 45.09712775503596, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 16, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-1d66fd51bbcbb370", "rated_matches": 42, "raw_elo_rating": 1664.0248249736765, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 67.98676372921676, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 0, "generated_at": "2026-07-01T00:15:48Z", "losses": 17, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-e10fd023695e8b0a", "rated_matches": 42, "raw_elo_rating": 1663.8404021886329, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 67.96267059128135, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 0, "generated_at": "2026-07-11T17:22:09Z", "losses": 18, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-ecd98326faa92bf4", "rated_matches": 44, "raw_elo_rating": 1517.4039789444332, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 49.01120271144721, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 26 } ], "GB2-08": [ { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 12, "model": "claude-fable-5", "point_rating_method": "sequential_elo", "public_id": "E-9ccf296d44d35675", "rated_matches": 60, "raw_elo_rating": 1742.3401615411974, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 73.64139541154456, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 48 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 49, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 49, "generated_at": "2026-07-02T16:51:45Z", "losses": 7, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-c2dade0b97891d8a", "rated_matches": 60, "raw_elo_rating": 1451.714886192373, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 28.618761053818325, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 0, "generated_at": "2026-07-25T10:50:00Z", "losses": 24, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-35a5bf9b35d5e1e8", "rated_matches": 58, "raw_elo_rating": 1686.7468791495075, "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": 64.89572776231789, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 0, "generated_at": "2026-07-25T10:50:00Z", "losses": 16, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-e73b6fb78880341d", "rated_matches": 58, "raw_elo_rating": 1773.600323016276, "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": 78.35075448437216, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 42 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 45, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 45, "generated_at": "2026-07-02T16:51:45Z", "losses": 9, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-130fb40b1c7a4d39", "rated_matches": 60, "raw_elo_rating": 1443.826362619811, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 27.396699029090957, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 24, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 24, "generated_at": "2026-07-02T16:51:45Z", "losses": 8, "model": "cohere/north-mini-code", "point_rating_method": "sequential_elo", "public_id": "E-efd7b75d5cd3b538", "rated_matches": 32, "raw_elo_rating": 1430.5543856985234, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "first_pass", "score": 22.487662221514032, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 40, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 40, "generated_at": "2026-07-02T06:10:40Z", "losses": 4, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-43aba68125a9abc5", "rated_matches": 44, "raw_elo_rating": 1444.850116717791, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 26.251870635555328, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 39, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 39, "generated_at": "2026-07-01T00:15:48Z", "losses": 4, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-d28ef17ff6995c62", "rated_matches": 44, "raw_elo_rating": 1443.8493725610651, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 26.096838908876283, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 25, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 25, "generated_at": "2026-07-02T16:51:45Z", "losses": 24, "model": "google/gemini-3.1-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-cc6fb78c96472032", "rated_matches": 72, "raw_elo_rating": 1457.7343014406704, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 30.232635390830257, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 57, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 57, "generated_at": "2026-07-02T16:51:45Z", "losses": 5, "model": "google/gemini-3.5-flash", "point_rating_method": "sequential_elo", "public_id": "E-bd0bbefbbd252fc5", "rated_matches": 62, "raw_elo_rating": 1402.0511352404135, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 21.05198164014908, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 2, "attempted_matches": 70, "capped_draws": 55, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 55, "generated_at": "2026-07-24T13:40:00Z", "losses": 12, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-94d4c9bacc61b6b0", "rated_matches": 70, "raw_elo_rating": 1429.1142665897733, "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": 25.697480906486177, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 50, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 50, "generated_at": "2026-07-24T13:40:00Z", "losses": 20, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-10fc8582228643cf", "rated_matches": 70, "raw_elo_rating": 1377.8172524718702, "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": 17.750729862546706, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 39, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 39, "generated_at": "2026-07-24T13:40:00Z", "losses": 16, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-679bf377de51ec1e", "rated_matches": 68, "raw_elo_rating": 1435.6060844881897, "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": 26.5973507181767, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 49, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 49, "generated_at": "2026-07-02T16:51:45Z", "losses": 11, "model": "gpt-5", "point_rating_method": "sequential_elo", "public_id": "E-04ae9f2b42e0e036", "rated_matches": 68, "raw_elo_rating": 1439.8208523917242, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 27.25028757645839, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 21, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 21, "generated_at": "2026-07-02T16:51:45Z", "losses": 26, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-b13a2be40d59c1ea", "rated_matches": 66, "raw_elo_rating": 1456.5400400197243, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 29.72984163252576, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 47, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 47, "generated_at": "2026-07-02T06:10:40Z", "losses": 7, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-8cc872d6760c46c1", "rated_matches": 56, "raw_elo_rating": 1433.1644338510025, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 25.471324478270816, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 39, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 39, "generated_at": "2026-07-01T00:15:48Z", "losses": 13, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-acdb5996d6e8fdfc", "rated_matches": 58, "raw_elo_rating": 1449.3936251532014, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 28.12580554730766, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 25, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 25, "generated_at": "2026-07-02T16:51:45Z", "losses": 21, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-b5171a15f0048555", "rated_matches": 60, "raw_elo_rating": 1453.6580457764076, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 28.91978842779916, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 45, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 45, "generated_at": "2026-07-02T16:51:45Z", "losses": 18, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-26fa12e871bd8f3a", "rated_matches": 68, "raw_elo_rating": 1394.8874477441384, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 20.2893642862598, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 0, "generated_at": "2026-07-09T17:30:50Z", "losses": 23, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-e361d8cbba2abd67", "rated_matches": 60, "raw_elo_rating": 1675.169994435442, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 63.23563194269277, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 37 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 48, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 48, "generated_at": "2026-07-02T06:10:40Z", "losses": 7, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-f26c38927e48d019", "rated_matches": 60, "raw_elo_rating": 1463.8982068741182, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 30.506157776827983, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 25, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 25, "generated_at": "2026-07-02T16:51:45Z", "losses": 22, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-0d83a3c5c5e66085", "rated_matches": 62, "raw_elo_rating": 1541.4688058948389, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 42.65007148744865, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 49, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 49, "generated_at": "2026-07-10T05:30:29Z", "losses": 6, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-e6198d88365e0492", "rated_matches": 62, "raw_elo_rating": 1466.5807611762505, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 31.048681859229955, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 5, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 5, "generated_at": "2026-07-10T05:30:29Z", "losses": 15, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-0385f0602a8e29e2", "rated_matches": 58, "raw_elo_rating": 1672.1128256209613, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 62.628672220103525, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 38 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 33, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 33, "generated_at": "2026-07-10T05:30:29Z", "losses": 14, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-d004e78844cdd202", "rated_matches": 60, "raw_elo_rating": 1488.7884995268803, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 34.36207341877303, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-4289b162cf8180f0", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-fffc7436e4cd7fbe", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 29, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 29, "generated_at": "2026-07-02T16:51:45Z", "losses": 6, "model": "minimax/minimax-m3", "point_rating_method": "sequential_elo", "public_id": "E-d169e7b29be70652", "rated_matches": 38, "raw_elo_rating": 1461.5536447992083, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 28.154360136186384, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 30, "capped_draws": 2, "coverage_status": "under_covered", "distinct_rated_opponents": 15, "draws": 2, "generated_at": "2026-07-02T16:51:45Z", "losses": 14, "model": "moonshotai/kimi-k2.7-code", "point_rating_method": "sequential_elo", "public_id": "E-251b5d53a5f89562", "rated_matches": 30, "raw_elo_rating": 1564.582882005904, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 42.90835102937155, "uncertainty": 46.05265101338746, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 37, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 37, "generated_at": "2026-07-24T14:00:00Z", "losses": 3, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-151c4ee6a2d1838e", "rated_matches": 42, "raw_elo_rating": 1466.675965925635, "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": 29.420671091039058, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 13, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 13, "generated_at": "2026-07-21T14:43:57Z", "losses": 17, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-66c86eb2913b72e2", "rated_matches": 46, "raw_elo_rating": 1507.2816043430432, "reasoning": "high", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 36.12221240307626, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 30, "capped_draws": 8, "coverage_status": "under_covered", "distinct_rated_opponents": 15, "draws": 8, "generated_at": "2026-07-02T16:51:45Z", "losses": 19, "model": "nex-agi/nex-n2-pro", "point_rating_method": "sequential_elo", "public_id": "E-92332f4d765b2297", "rated_matches": 30, "raw_elo_rating": 1332.1817748180883, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 6.905597790895916, "uncertainty": 46.05265101338746, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 42, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 42, "generated_at": "2026-07-02T16:51:45Z", "losses": 11, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-15cf0dede27b7e1b", "rated_matches": 56, "raw_elo_rating": 1436.2781128307956, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 25.953684555336736, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 38, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 38, "generated_at": "2026-07-02T16:51:45Z", "losses": 18, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-35de956c8305ff90", "rated_matches": 66, "raw_elo_rating": 1462.0021926743475, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 30.576018901450553, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 45, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 45, "generated_at": "2026-07-02T16:51:45Z", "losses": 10, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-6e65dec497ff2de3", "rated_matches": 58, "raw_elo_rating": 1464.2474413129037, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 30.42690593498895, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-0fab95afbec0dd98", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-f72c72b8f264c57a", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 20, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 20, "generated_at": "2026-07-02T16:51:45Z", "losses": 9, "model": "qwen/qwen3.7-max", "point_rating_method": "sequential_elo", "public_id": "E-64624689e7cbd439", "rated_matches": 32, "raw_elo_rating": 1476.2232335533376, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 29.56251775855583, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 29, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 29, "generated_at": "2026-07-02T16:51:45Z", "losses": 3, "model": "qwen/qwen3.7-plus", "point_rating_method": "sequential_elo", "public_id": "E-6c2a9942e92223c8", "rated_matches": 32, "raw_elo_rating": 1459.9075340300603, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "first_pass", "score": 27.03494759782097, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 38, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-9c877cdf80f00ddf", "rated_matches": 70, "raw_elo_rating": 1602.2012432700476, "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": 52.51149993427681, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 0, "generated_at": "2026-07-17T22:36:00Z", "losses": 13, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-34ecad20175c262b", "rated_matches": 56, "raw_elo_rating": 1786.330960585913, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 80.18262713936724, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 43 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 0, "generated_at": "2026-07-17T22:36:00Z", "losses": 7, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-72b02fc86c46f3d7", "rated_matches": 58, "raw_elo_rating": 1840.5719390163315, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 88.72575912186454, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 51 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 1, "generated_at": "2026-07-24T14:00:00Z", "losses": 12, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-73422318071a105c", "rated_matches": 72, "raw_elo_rating": 1815.553575169084, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 85.66472507362005, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 59 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 24, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 24, "generated_at": "2026-07-02T16:51:45Z", "losses": 5, "model": "x-ai/grok-build-0.1", "point_rating_method": "sequential_elo", "public_id": "E-3e2fe948d2bcebb0", "rated_matches": 32, "raw_elo_rating": 1459.4782493754258, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 26.968444345418725, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 17, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 17, "generated_at": "2026-07-03T19:35:00Z", "losses": 10, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-650d06103e7fa176", "rated_matches": 34, "raw_elo_rating": 1470.498222600706, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 28.988352652103423, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 21, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 21, "generated_at": "2026-07-02T06:10:40Z", "losses": 10, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-b5eb7da0f5021b69", "rated_matches": 32, "raw_elo_rating": 1394.7295192115866, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 16.937801278346626, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 27, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 27, "generated_at": "2026-07-02T16:51:45Z", "losses": 3, "model": "xiaomi/mimo-v2.5-pro", "point_rating_method": "sequential_elo", "public_id": "E-bd1bb7ac29877b8f", "rated_matches": 32, "raw_elo_rating": 1453.6706238024155, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 26.068747640283966, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 30, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 30, "generated_at": "2026-07-02T06:10:40Z", "losses": 10, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-1549af3bdbe8e3c4", "rated_matches": 44, "raw_elo_rating": 1457.469347598416, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 28.20679701672494, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 40, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 40, "generated_at": "2026-07-01T00:15:48Z", "losses": 3, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-18e15798a90b1d2f", "rated_matches": 44, "raw_elo_rating": 1460.632560055503, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 28.696830643980192, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 38, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 38, "generated_at": "2026-07-11T17:22:09Z", "losses": 5, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-da1e9a6be31e371f", "rated_matches": 44, "raw_elo_rating": 1452.9805821593848, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 27.511413434424572, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 1 } ] }, "full_freedom/baseline": { "GB2-01": [ { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 38, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 38, "generated_at": "2026-07-02T16:51:45Z", "losses": 8, "model": "claude-opus-4-5", "point_rating_method": "sequential_elo", "public_id": "E-2e3eca63f7980fac", "rated_matches": 56, "raw_elo_rating": 1445.0343615965558, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 40.41017310675189, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 14, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 14, "generated_at": "2026-07-02T16:51:45Z", "losses": 17, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-757a6149e87d8b53", "rated_matches": 54, "raw_elo_rating": 1577.025901566621, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 57.41317066463946, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 34, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 34, "generated_at": "2026-07-25T15:48:00Z", "losses": 5, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-6c30dc38efb07e9e", "rated_matches": 50, "raw_elo_rating": 1537.6053460906055, "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": 52.028788341658505, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 10, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 10, "generated_at": "2026-07-25T15:48:00Z", "losses": 9, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-865d68ab219fd7ee", "rated_matches": 50, "raw_elo_rating": 1788.9102877159794, "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": 84.63745882976652, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 31 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 12, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 12, "generated_at": "2026-07-02T16:51:45Z", "losses": 9, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-73ff84eba4ec19cb", "rated_matches": 44, "raw_elo_rating": 1562.54730392307, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 54.79582315352283, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 44, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 44, "generated_at": "2026-07-02T16:51:45Z", "losses": 11, "model": "cohere/north-mini-code", "point_rating_method": "sequential_elo", "public_id": "E-194759b182ce3244", "rated_matches": 68, "raw_elo_rating": 1469.458273446667, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 44.20568866165951, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 17, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 17, "generated_at": "2026-07-11T17:22:09Z", "losses": 44, "model": "cohere/north-mini-code", "point_rating_method": "sequential_elo", "public_id": "E-c309b463b29efb71", "rated_matches": 64, "raw_elo_rating": 1214.6977166091126, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 10.959238882028716, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 23, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 23, "generated_at": "2026-07-02T06:10:40Z", "losses": 21, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-c4c43ee3f29394f8", "rated_matches": 66, "raw_elo_rating": 1480.1694379737794, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 45.502967642683174, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 22 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 27, "coverage_status": "rated", "distinct_rated_opponents": 37, "draws": 27, "generated_at": "2026-07-02T16:51:45Z", "losses": 24, "model": "deepseek/deepseek-v4-pro", "point_rating_method": "sequential_elo", "public_id": "E-e121525dd1846069", "rated_matches": 74, "raw_elo_rating": 1494.5716412258355, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 47.71947792576954, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 23, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 23, "generated_at": "2026-07-02T16:51:45Z", "losses": 17, "model": "google/gemini-3.1-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-cc0af0bfa6a9a29f", "rated_matches": 46, "raw_elo_rating": 1340.1564195017108, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 26.105376543268523, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-21c0edac8ac36f2e", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-cf51875df5447bc2", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-e0c4f14c94c0a42a", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-e9733de94d982ade", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 16, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 16, "generated_at": "2026-07-02T16:51:45Z", "losses": 17, "model": "google/gemma-4-31b-it", "point_rating_method": "sequential_elo", "public_id": "E-caaa54d3c88e6570", "rated_matches": 58, "raw_elo_rating": 1477.0492603937407, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 44.68186759149837, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 1, "generated_at": "2026-07-02T16:51:45Z", "losses": 22, "model": "gpt-4.1", "point_rating_method": "sequential_elo", "public_id": "E-f50ec6b60d5b85da", "rated_matches": 44, "raw_elo_rating": 1576.9979684590764, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 56.67090350467359, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 2, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 2, "generated_at": "2026-07-02T16:51:45Z", "losses": 6, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-60fa13e461853992", "rated_matches": 62, "raw_elo_rating": 1828.996677787992, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 90.56767341997636, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 54 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 19, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 19, "generated_at": "2026-07-01T00:15:48Z", "losses": 34, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-3834aa9e894c458b", "rated_matches": 62, "raw_elo_rating": 1301.9549941620744, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 22.18012606933584, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 18, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 18, "generated_at": "2026-07-02T06:10:40Z", "losses": 32, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-b6ed01547d27188c", "rated_matches": 70, "raw_elo_rating": 1474.6255530349806, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 44.96481532557581, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 28, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 28, "generated_at": "2026-07-02T16:51:45Z", "losses": 20, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-ea1cb793f92b3cff", "rated_matches": 64, "raw_elo_rating": 1438.6852463591326, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 40.02327361140479, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 18, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 18, "generated_at": "2026-07-02T06:10:40Z", "losses": 35, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-5c28f8f5135ce060", "rated_matches": 72, "raw_elo_rating": 1403.576939064904, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 35.830699512360106, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 20, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 20, "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": 70, "raw_elo_rating": 1490.1659645875384, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 46.98129839307701, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 21, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 21, "generated_at": "2026-07-02T16:51:45Z", "losses": 25, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-a8887794a1195b75", "rated_matches": 60, "raw_elo_rating": 1522.347373894308, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 50.671328824001904, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 17, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 17, "generated_at": "2026-07-01T00:15:48Z", "losses": 35, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-f491ad1b583dbcac", "rated_matches": 58, "raw_elo_rating": 1228.8312506207556, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 12.47374928888556, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 50, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 50, "generated_at": "2026-07-02T16:51:45Z", "losses": 9, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-58178b9b32a94ca0", "rated_matches": 66, "raw_elo_rating": 1489.9225771870858, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 46.76850942142567, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 16, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 16, "generated_at": "2026-07-10T05:30:29Z", "losses": 31, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-959ed218b1c5605b", "rated_matches": 59, "raw_elo_rating": 1357.846690093915, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 29.271001037603703, "uncertainty": 20.79972243679028, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 15, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 15, "generated_at": "2026-07-10T05:30:29Z", "losses": 19, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-890c38b8e811c121", "rated_matches": 62, "raw_elo_rating": 1563.2313436316006, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 56.082660301584646, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 18, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 18, "generated_at": "2026-07-10T05:30:29Z", "losses": 24, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-40742129939a44b5", "rated_matches": 60, "raw_elo_rating": 1564.6500398829733, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 56.16041187613398, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 22, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 22, "generated_at": "2026-07-24T13:40:00Z", "losses": 20, "model": "inclusionai/ling-3.0-flash", "point_rating_method": "sequential_elo", "public_id": "E-3c618b88b6bdb039", "rated_matches": 60, "raw_elo_rating": 1410.9705067906923, "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": 36.21935849707662, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 13, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 13, "generated_at": "2026-07-24T13:40:00Z", "losses": 33, "model": "inclusionai/ling-3.0-flash", "point_rating_method": "sequential_elo", "public_id": "E-f9af396559c3a1cd", "rated_matches": 64, "raw_elo_rating": 1531.3285214806754, "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": 52.04442214847159, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 18, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 18, "generated_at": "2026-07-24T13:40:00Z", "losses": 23, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-9f5585b5fd96f2c3", "rated_matches": 62, "raw_elo_rating": 1501.8751700705743, "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": 48.12124405118231, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 23, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 23, "generated_at": "2026-07-24T13:40:00Z", "losses": 25, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-ed0f8e084958eebc", "rated_matches": 70, "raw_elo_rating": 1459.1960248159478, "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": 42.96272018877806, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 22 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 15, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 15, "generated_at": "2026-07-02T16:51:45Z", "losses": 23, "model": "minimax/minimax-m3", "point_rating_method": "sequential_elo", "public_id": "E-444510032bc433fc", "rated_matches": 70, "raw_elo_rating": 1497.3874694861893, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 47.91834193923778, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 6, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 6, "generated_at": "2026-07-02T16:51:45Z", "losses": 37, "model": "mistralai/mistral-medium-3-5", "point_rating_method": "sequential_elo", "public_id": "E-a0a38f5e77e983bc", "rated_matches": 61, "raw_elo_rating": 1393.6204375879504, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 34.02186953365919, "uncertainty": 19.750063500095248, "unilateral_faults": 3, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 5, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 5, "generated_at": "2026-07-21T14:20:15Z", "losses": 13, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-2292c77f8fb54ff1", "rated_matches": 38, "raw_elo_rating": 1583.3568125453553, "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": 56.92212183021899, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 24, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 24, "generated_at": "2026-07-24T14:00:00Z", "losses": 5, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-fb8801908d28001f", "rated_matches": 38, "raw_elo_rating": 1564.779507444791, "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": 54.5115794164355, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 11, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 11, "generated_at": "2026-07-02T16:51:45Z", "losses": 17, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-0ce5e196701b51f3", "rated_matches": 44, "raw_elo_rating": 1551.1970854508706, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 53.32304855651662, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 7, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 7, "generated_at": "2026-07-21T14:20:15Z", "losses": 15, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-fbf1a1af436a64a7", "rated_matches": 38, "raw_elo_rating": 1483.123014784552, "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": 43.91604697226371, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 11, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 11, "generated_at": "2026-07-21T14:20:15Z", "losses": 15, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-55f6c0e3dc8a8065", "rated_matches": 38, "raw_elo_rating": 1413.0817228894214, "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": 34.827672532836864, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 7, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 7, "generated_at": "2026-07-24T13:40:00Z", "losses": 29, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-8461eb1b16e40129", "rated_matches": 66, "raw_elo_rating": 1645.1563970303832, "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": 66.9112429750953, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 30 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 22, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 22, "generated_at": "2026-07-24T13:40:00Z", "losses": 24, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-c58ec61528547516", "rated_matches": 68, "raw_elo_rating": 1512.7646082145152, "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": 49.825005143695144, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 22 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 17, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 17, "generated_at": "2026-07-02T16:51:45Z", "losses": 18, "model": "qwen/qwen3.7-max", "point_rating_method": "sequential_elo", "public_id": "E-8a70cd704fcbcf6f", "rated_matches": 64, "raw_elo_rating": 1582.8274794165334, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 58.72679193774028, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 18, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 18, "generated_at": "2026-07-03T18:55:00Z", "losses": 32, "model": "qwen/qwen3.7-plus", "point_rating_method": "sequential_elo", "public_id": "E-5e09f0c994a59f3c", "rated_matches": 66, "raw_elo_rating": 1378.486150271109, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 32.3088107693705, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 13, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 13, "generated_at": "2026-07-21T14:20:15Z", "losses": 25, "model": "stepfun/step-3.7-flash", "point_rating_method": "sequential_elo", "public_id": "E-09ecaa63c419b917", "rated_matches": 56, "raw_elo_rating": 1479.5735802409645, "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": 44.89189158155693, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 15, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 15, "generated_at": "2026-07-02T16:51:45Z", "losses": 15, "model": "tencent/hy3-preview", "point_rating_method": "sequential_elo", "public_id": "E-3407ff2dd1928eb5", "rated_matches": 72, "raw_elo_rating": 1676.59501851212, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 71.25680984831166, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 42 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 33, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 33, "generated_at": "2026-07-24T13:40:00Z", "losses": 24, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-9e638fc0ac98df4f", "rated_matches": 62, "raw_elo_rating": 1356.7506640572788, "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": 29.29026856088901, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 24, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 24, "generated_at": "2026-07-24T13:40:00Z", "losses": 26, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-bc7c657b08ebac66", "rated_matches": 60, "raw_elo_rating": 1308.7036654237002, "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": 22.949481229931152, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 23, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 23, "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": 38, "raw_elo_rating": 1547.678016157504, "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": 52.29253473456167, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 12, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 12, "generated_at": "2026-07-21T14:20:15Z", "losses": 7, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-dc626769adfba01d", "rated_matches": 38, "raw_elo_rating": 1630.6217680312, "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": 63.05509856002232, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 3, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 3, "generated_at": "2026-07-02T06:10:40Z", "losses": 26, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-2cdd8ae895784956", "rated_matches": 62, "raw_elo_rating": 1601.4159101664063, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 61.03738956321968, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 33 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 23, "coverage_status": "rated", "distinct_rated_opponents": 37, "draws": 23, "generated_at": "2026-07-02T16:51:45Z", "losses": 27, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-912a4a40bbdcbd45", "rated_matches": 74, "raw_elo_rating": 1469.798556983822, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 44.5049874513793, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 25, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 25, "generated_at": "2026-07-01T00:15:48Z", "losses": 29, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-a168350bd057f924", "rated_matches": 68, "raw_elo_rating": 1414.8676050846543, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 37.12214663168973, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 76, "capped_draws": 24, "coverage_status": "rated", "distinct_rated_opponents": 38, "draws": 24, "generated_at": "2026-07-02T16:51:45Z", "losses": 29, "model": "xiaomi/mimo-v2.5-pro", "point_rating_method": "sequential_elo", "public_id": "E-9ce4191c7f1f3b3e", "rated_matches": 76, "raw_elo_rating": 1431.6560101881555, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 39.63405689209577, "uncertainty": 13.230288229818967, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 2, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 2, "generated_at": "2026-07-01T00:15:48Z", "losses": 22, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-5bc0612062635fa8", "rated_matches": 46, "raw_elo_rating": 1519.9526508967542, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 49.43526423526853, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 22 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 12, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 12, "generated_at": "2026-07-11T14:00:45Z", "losses": 22, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-5c3b7f5666a38043", "rated_matches": 46, "raw_elo_rating": 1453.34418739154, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 40.79232460935949, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 8, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 8, "generated_at": "2026-07-02T06:10:40Z", "losses": 13, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-6a7eb114b16dc845", "rated_matches": 42, "raw_elo_rating": 1559.2129908058334, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 54.1852807095748, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 1, "generated_at": "2026-07-02T16:51:45Z", "losses": 23, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-c8076ea61de8da45", "rated_matches": 42, "raw_elo_rating": 1384.7748989366414, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 31.55065115733814, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 18 } ], "GB2-02": [ { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 50, "generated_at": "2026-07-02T16:51:45Z", "losses": 5, "model": "claude-opus-4-5", "point_rating_method": "sequential_elo", "public_id": "E-16462f3d1f3a7b19", "rated_matches": 58, "raw_elo_rating": 1507.016974397993, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 35.54624651592337, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 44, "generated_at": "2026-07-02T16:51:45Z", "losses": 7, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-c142942f4138c871", "rated_matches": 54, "raw_elo_rating": 1477.334204135014, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 28.009047114593564, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 17, "generated_at": "2026-07-25T10:50:00Z", "losses": 11, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-51ddad48e10b006f", "rated_matches": 50, "raw_elo_rating": 1644.470715376277, "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": 67.45019799430912, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 22 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 32, "generated_at": "2026-07-25T10:50:00Z", "losses": 3, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-772d1a710082ddb3", "rated_matches": 50, "raw_elo_rating": 1583.7397660803254, "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": 52.938628174086666, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 35, "generated_at": "2026-07-02T16:51:45Z", "losses": 3, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-e501d6808bd19ccc", "rated_matches": 38, "raw_elo_rating": 1479.446255038946, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 26.09668923633087, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 58, "generated_at": "2026-07-02T16:51:45Z", "losses": 2, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-3358fbcda6ab6f4d", "rated_matches": 60, "raw_elo_rating": 1490.412478398123, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 31.784316788866928, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 48, "generated_at": "2026-07-02T06:10:40Z", "losses": 0, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-bc9a8c3886a48505", "rated_matches": 48, "raw_elo_rating": 1494.553696664807, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 31.357342826586542, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 48, "generated_at": "2026-07-02T16:51:45Z", "losses": 1, "model": "deepseek/deepseek-v4-pro", "point_rating_method": "sequential_elo", "public_id": "E-6c3b019c1b20a09b", "rated_matches": 50, "raw_elo_rating": 1502.3246516528714, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 33.484607923588854, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 34, "generated_at": "2026-07-02T16:51:45Z", "losses": 3, "model": "google/gemini-3.1-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-20b3484be872df52", "rated_matches": 38, "raw_elo_rating": 1495.250360698582, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 29.873056729095698, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-1010911d64a09b68", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-e65fdcb71f09a611", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-4492f6d65cd6280b", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-9c8b43dc41bad760", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 31, "generated_at": "2026-07-02T16:51:45Z", "losses": 10, "model": "gpt-4.1", "point_rating_method": "sequential_elo", "public_id": "E-e4707b8e4c581ede", "rated_matches": 44, "raw_elo_rating": 1461.1826663180202, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 22.789449128010855, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 60, "generated_at": "2026-07-02T16:51:45Z", "losses": 1, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-98ddce22d3eb5886", "rated_matches": 62, "raw_elo_rating": 1488.5809352786268, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 31.542487942751787, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 59, "generated_at": "2026-07-02T16:51:45Z", "losses": 1, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-322cbb8be1559087", "rated_matches": 60, "raw_elo_rating": 1485.7642934893795, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 30.67363993262635, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 55, "generated_at": "2026-07-02T06:10:40Z", "losses": 1, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-b45c06f99639b8db", "rated_matches": 58, "raw_elo_rating": 1501.6284527576236, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 34.2586673010664, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 48, "generated_at": "2026-07-01T00:15:48Z", "losses": 2, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-dd45dfa7984ab9fa", "rated_matches": 52, "raw_elo_rating": 1509.4348665175428, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 35.43853591905222, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 45, "generated_at": "2026-07-09T17:30:50Z", "losses": 2, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-038a95fb13c8aa94", "rated_matches": 48, "raw_elo_rating": 1496.6194788828827, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 31.85095840873223, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 52, "generated_at": "2026-07-01T00:15:48Z", "losses": 2, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-23b12c36ef5c7ef8", "rated_matches": 54, "raw_elo_rating": 1477.0288370659568, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 27.93608010856464, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 53, "generated_at": "2026-07-02T06:10:40Z", "losses": 3, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-786cc9019eb3ee2b", "rated_matches": 58, "raw_elo_rating": 1501.6383350101655, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 34.261028650582745, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 45, "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": 52, "raw_elo_rating": 1441.4318190228537, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 19.18930907265305, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 62, "generated_at": "2026-07-02T16:51:45Z", "losses": 2, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-51e935956fa76015", "rated_matches": 64, "raw_elo_rating": 1501.313222137573, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 34.77155592483919, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 58, "generated_at": "2026-07-10T05:30:29Z", "losses": 0, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-ba4589e1cf2c827b", "rated_matches": 58, "raw_elo_rating": 1488.7189255222488, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 31.173955008668692, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 42, "generated_at": "2026-07-10T05:30:29Z", "losses": 6, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-0420ca9039edc6fb", "rated_matches": 54, "raw_elo_rating": 1501.132056255132, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 33.69550841012682, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 57, "generated_at": "2026-07-10T05:30:29Z", "losses": 3, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-c6593bd789768bdb", "rated_matches": 62, "raw_elo_rating": 1477.2364928140053, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 28.8317503237067, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 60, "generated_at": "2026-07-24T13:40:00Z", "losses": 2, "model": "inclusionai/ling-3.0-flash", "point_rating_method": "sequential_elo", "public_id": "E-fc495094a55d2f94", "rated_matches": 62, "raw_elo_rating": 1472.8398095919308, "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": 27.7811694206549, "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": 63, "generated_at": "2026-07-24T13:40:00Z", "losses": 1, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-a0c74818516a7f27", "rated_matches": 64, "raw_elo_rating": 1480.524029567731, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 29.80400934470667, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 55, "generated_at": "2026-07-02T16:51:45Z", "losses": 1, "model": "minimax/minimax-m3", "point_rating_method": "sequential_elo", "public_id": "E-1e46941293882535", "rated_matches": 56, "raw_elo_rating": 1475.919430546933, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 27.899111953447644, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 31, "generated_at": "2026-07-24T14:00:00Z", "losses": 0, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-d3d3da42e99695b1", "rated_matches": 32, "raw_elo_rating": 1506.616689854054, "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": 31.255739040937716, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 38, "generated_at": "2026-07-21T14:20:15Z", "losses": 1, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-fc3ad6db6543001f", "rated_matches": 42, "raw_elo_rating": 1524.1490804380742, "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": 37.50759377970699, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 46, "generated_at": "2026-07-11T17:22:09Z", "losses": 5, "model": "nex-agi/nex-n2-pro", "point_rating_method": "sequential_elo", "public_id": "E-811f47e902ce0d21", "rated_matches": 52, "raw_elo_rating": 1466.422044691208, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 25.16068625041128, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 30, "generated_at": "2026-07-21T14:20:15Z", "losses": 1, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-e48b0ea99dfc517c", "rated_matches": 32, "raw_elo_rating": 1479.8188659817515, "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": 24.852438966409498, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 39, "generated_at": "2026-07-21T14:20:15Z", "losses": 1, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-18d1d6f3b7eabe0d", "rated_matches": 40, "raw_elo_rating": 1489.8564736994583, "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": 28.962153891671328, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 60, "generated_at": "2026-07-24T13:40:00Z", "losses": 2, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-d8c7a78cc7f666dc", "rated_matches": 64, "raw_elo_rating": 1477.653649416274, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 29.11813628556075, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 46, "generated_at": "2026-07-02T16:51:45Z", "losses": 1, "model": "qwen/qwen3.7-max", "point_rating_method": "sequential_elo", "public_id": "E-5f64c2ae9860ba38", "rated_matches": 50, "raw_elo_rating": 1502.5488228935112, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 33.53817330743257, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 48, "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": 48, "raw_elo_rating": 1495.4141301372438, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 31.562942122426243, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 57, "generated_at": "2026-07-02T16:51:45Z", "losses": 5, "model": "tencent/hy3-preview", "point_rating_method": "sequential_elo", "public_id": "E-d910e47dd13c2c71", "rated_matches": 62, "raw_elo_rating": 1466.7923583848676, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 26.336139967911993, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 64, "generated_at": "2026-07-24T13:40:00Z", "losses": 1, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-66a4f0abd099d8f1", "rated_matches": 66, "raw_elo_rating": 1499.1390170008954, "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": 34.43031617632999, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 37, "generated_at": "2026-07-21T14:20:15Z", "losses": 2, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-1331dea6489316f2", "rated_matches": 40, "raw_elo_rating": 1479.5752759796987, "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": 26.505477019739928, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 32, "generated_at": "2026-07-24T14:00:00Z", "losses": 1, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-1b0da3150a77b47b", "rated_matches": 34, "raw_elo_rating": 1494.8957020313685, "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": 28.93739708392125, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 53, "generated_at": "2026-07-01T00:15:48Z", "losses": 3, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-39b08fe4c0318552", "rated_matches": 56, "raw_elo_rating": 1468.5821896697769, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 26.14588918135212, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 56, "generated_at": "2026-07-02T16:51:45Z", "losses": 4, "model": "xiaomi/mimo-v2.5-pro", "point_rating_method": "sequential_elo", "public_id": "E-b9f44937a1269e8d", "rated_matches": 64, "raw_elo_rating": 1479.9188889322822, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 29.659411891774138, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 35, "generated_at": "2026-07-02T16:51:45Z", "losses": 3, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-4959351a96fd2b82", "rated_matches": 38, "raw_elo_rating": 1466.9306050201762, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 23.106093317802184, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 37, "generated_at": "2026-07-11T14:00:45Z", "losses": 1, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-925b589068dc7268", "rated_matches": 38, "raw_elo_rating": 1486.4015813825515, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 27.758654099843973, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 31, "generated_at": "2026-07-01T00:15:48Z", "losses": 4, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-b090ee9c8b9921ad", "rated_matches": 38, "raw_elo_rating": 1489.960530795913, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 28.609059757871027, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 3 } ], "GB2-03": [ { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 8, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 35, "generated_at": "2026-07-02T16:51:45Z", "losses": 9, "model": "claude-opus-4-5", "point_rating_method": "sequential_elo", "public_id": "E-1975db22db58e9b0", "rated_matches": 52, "raw_elo_rating": 1543.043331713756, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 53.68257145959784, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 4, "generated_at": "2026-07-25T15:48:00Z", "losses": 15, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-49aaba66f6b19080", "rated_matches": 42, "raw_elo_rating": 1584.378997703733, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 59.65363995882995, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 8, "generated_at": "2026-07-25T15:48:00Z", "losses": 15, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-ecf847457e616425", "rated_matches": 40, "raw_elo_rating": 1470.331123516614, "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": 40.10271772058338, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 4, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 13, "generated_at": "2026-07-02T16:51:45Z", "losses": 15, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-e7d1e6857fc48e7a", "rated_matches": 38, "raw_elo_rating": 1485.0924616716402, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 42.333305859069256, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 18, "generated_at": "2026-07-02T06:10:40Z", "losses": 17, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-4e52c100ed276347", "rated_matches": 46, "raw_elo_rating": 1454.2183123506989, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 38.073579139181625, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 26, "generated_at": "2026-07-02T16:51:45Z", "losses": 17, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-ae9d59ec3a8a1d63", "rated_matches": 60, "raw_elo_rating": 1491.0611475690398, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 45.51600526871697, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 14, "generated_at": "2026-07-02T16:51:45Z", "losses": 27, "model": "deepseek/deepseek-v4-pro", "point_rating_method": "sequential_elo", "public_id": "E-f82a334a0fd1fb8e", "rated_matches": 50, "raw_elo_rating": 1351.7838803092702, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 21.132140682151817, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-28274045fbc35ae9", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-6743f1c221046d65", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-80b8c1a18d6dd238", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 30, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 15, "draws": 10, "generated_at": "2026-07-02T16:51:45Z", "losses": 10, "model": "gpt-4.1", "point_rating_method": "sequential_elo", "public_id": "E-c7da9914f86ee846", "rated_matches": 30, "raw_elo_rating": 1527.2252132901654, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 48.1455251873211, "uncertainty": 46.05265101338746, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 2, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 29, "generated_at": "2026-07-02T16:51:45Z", "losses": 6, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-ebd456dc6b320c61", "rated_matches": 46, "raw_elo_rating": 1557.0056967199416, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 55.46990711066279, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 53, "generated_at": "2026-07-02T16:51:45Z", "losses": 1, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-35117a2e624d7970", "rated_matches": 54, "raw_elo_rating": 1502.2519514200912, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 46.949443459654866, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 20, "generated_at": "2026-07-01T00:15:48Z", "losses": 12, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-a51cd55f211305c2", "rated_matches": 44, "raw_elo_rating": 1520.2960001548722, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 49.03989221480356, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 20, "generated_at": "2026-07-02T06:10:40Z", "losses": 9, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-dfa5098ec9c3cf47", "rated_matches": 48, "raw_elo_rating": 1537.458648607366, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 52.36527852981392, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 9, "generated_at": "2026-07-01T00:15:48Z", "losses": 22, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-0ecb5b73c09f13b2", "rated_matches": 44, "raw_elo_rating": 1410.58480410516, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 30.471738541701946, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 32, "generated_at": "2026-07-02T06:10:40Z", "losses": 17, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-e4eac938bdd5d40e", "rated_matches": 58, "raw_elo_rating": 1427.2699988546833, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 34.57393560929241, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 20, "generated_at": "2026-07-09T17:30:50Z", "losses": 14, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-f2a7b43bf689e68e", "rated_matches": 50, "raw_elo_rating": 1515.3938290892593, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 48.822429192164726, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 2, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 19, "generated_at": "2026-07-02T16:51:45Z", "losses": 8, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-446036823932df16", "rated_matches": 42, "raw_elo_rating": 1532.8195170122888, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 50.9274169728892, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 19, "generated_at": "2026-07-10T05:30:29Z", "losses": 13, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-d192bb239087b778", "rated_matches": 46, "raw_elo_rating": 1482.3818845275205, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 42.8401440385904, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 7, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 24, "generated_at": "2026-07-10T05:30:29Z", "losses": 16, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-527999604d620080", "rated_matches": 54, "raw_elo_rating": 1492.4298015489974, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 45.28708633683153, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 10, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 23, "generated_at": "2026-07-10T10:07:13Z", "losses": 18, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-c2f0f8f062659e83", "rated_matches": 54, "raw_elo_rating": 1507.1274179692712, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 47.77459545300492, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 18, "generated_at": "2026-07-24T13:40:00Z", "losses": 22, "model": "inclusionai/ling-3.0-flash", "point_rating_method": "sequential_elo", "public_id": "E-2524de3c7d4a81b7", "rated_matches": 50, "raw_elo_rating": 1393.4427143645798, "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": 28.182721301387136, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 20, "generated_at": "2026-07-24T13:40:00Z", "losses": 19, "model": "inclusionai/ling-3.0-flash", "point_rating_method": "sequential_elo", "public_id": "E-641ddca04b054d56", "rated_matches": 46, "raw_elo_rating": 1394.77694351092, "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": 28.013380081134617, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 23, "generated_at": "2026-07-24T13:40:00Z", "losses": 18, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-198e8ddfe9f7ce20", "rated_matches": 48, "raw_elo_rating": 1423.0454733711274, "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": 33.00133486219263, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 5, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 23, "generated_at": "2026-07-24T13:40:00Z", "losses": 14, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-84709c769628f9a2", "rated_matches": 52, "raw_elo_rating": 1451.745342784988, "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": 38.23077483798092, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 20, "generated_at": "2026-07-02T16:51:45Z", "losses": 11, "model": "minimax/minimax-m3", "point_rating_method": "sequential_elo", "public_id": "E-44cc758f104a74ab", "rated_matches": 52, "raw_elo_rating": 1537.2180654375327, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 52.69666989897096, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 30, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 15, "draws": 9, "generated_at": "2026-07-24T14:00:00Z", "losses": 3, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-09859be1b47131a0", "rated_matches": 30, "raw_elo_rating": 1621.3908495614658, "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": 64.08265893453343, "uncertainty": 46.05265101338746, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 30, "capped_draws": 2, "coverage_status": "under_covered", "distinct_rated_opponents": 15, "draws": 14, "generated_at": "2026-07-21T14:20:15Z", "losses": 4, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-a12d08354d94b221", "rated_matches": 30, "raw_elo_rating": 1575.2218077884422, "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": 56.26874482687114, "uncertainty": 46.05265101338746, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 2, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 27, "generated_at": "2026-07-02T16:51:45Z", "losses": 13, "model": "nex-agi/nex-n2-pro", "point_rating_method": "sequential_elo", "public_id": "E-a05d4cef5f788f16", "rated_matches": 46, "raw_elo_rating": 1424.386156653482, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 33.02461357020887, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 30, "capped_draws": 4, "coverage_status": "under_covered", "distinct_rated_opponents": 15, "draws": 18, "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": 30, "raw_elo_rating": 1419.261890549445, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 29.873191643532166, "uncertainty": 46.05265101338746, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 30, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 15, "draws": 19, "generated_at": "2026-07-21T14:20:15Z", "losses": 9, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-08888c30d05ca8cb", "rated_matches": 30, "raw_elo_rating": 1439.6140997468228, "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": 33.31771655594664, "uncertainty": 46.05265101338746, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 30, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 15, "draws": 21, "generated_at": "2026-07-21T14:20:15Z", "losses": 5, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-c90a449ff5e7b79a", "rated_matches": 30, "raw_elo_rating": 1478.271732610354, "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": 39.860356628188114, "uncertainty": 46.05265101338746, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 15, "generated_at": "2026-07-24T13:40:00Z", "losses": 18, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-467272d131a1a99b", "rated_matches": 50, "raw_elo_rating": 1447.2211361430434, "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": 37.28449063609493, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 7, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 30, "generated_at": "2026-07-24T13:40:00Z", "losses": 13, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-91efdb0c216f8504", "rated_matches": 52, "raw_elo_rating": 1503.2618584047368, "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": 46.94972616813319, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 3, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 39, "generated_at": "2026-07-02T16:51:45Z", "losses": 7, "model": "qwen/qwen3.7-max", "point_rating_method": "sequential_elo", "public_id": "E-3325ebad2ef000c1", "rated_matches": 50, "raw_elo_rating": 1441.1397761187798, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 36.25524629697736, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 6, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 21, "generated_at": "2026-07-21T14:20:15Z", "losses": 10, "model": "stepfun/step-3.7-flash", "point_rating_method": "sequential_elo", "public_id": "E-02b2a2f01700292d", "rated_matches": 40, "raw_elo_rating": 1522.423633843672, "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": 48.91915370704513, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 23, "generated_at": "2026-07-02T16:51:45Z", "losses": 20, "model": "tencent/hy3-preview", "point_rating_method": "sequential_elo", "public_id": "E-2346cd049910cc0a", "rated_matches": 68, "raw_elo_rating": 1436.7909872054654, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 36.848972779507136, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 4, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 25, "generated_at": "2026-07-24T13:40:00Z", "losses": 14, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-78048b7c08122f1c", "rated_matches": 48, "raw_elo_rating": 1439.021547101438, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 35.70521744481249, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 8, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 20, "generated_at": "2026-07-24T13:40:00Z", "losses": 12, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-adf1f0bb193bd39b", "rated_matches": 48, "raw_elo_rating": 1607.2650933940686, "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": 64.17972264165327, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 30, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 15, "draws": 6, "generated_at": "2026-07-24T14:00:00Z", "losses": 22, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-02f7e54245bd5c85", "rated_matches": 30, "raw_elo_rating": 1311.9892901970238, "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": 11.717759928482549, "uncertainty": 46.05265101338746, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 1, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 25, "generated_at": "2026-07-21T14:20:15Z", "losses": 6, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-3c1904811d11cd84", "rated_matches": 38, "raw_elo_rating": 1513.251425681494, "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": 47.09909084580285, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 2, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 28, "generated_at": "2026-07-02T16:51:45Z", "losses": 9, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-b10e12eb6aef112e", "rated_matches": 46, "raw_elo_rating": 1525.5217643839485, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 50.14138536541297, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 4, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 28, "generated_at": "2026-07-02T16:51:45Z", "losses": 8, "model": "xiaomi/mimo-v2.5-pro", "point_rating_method": "sequential_elo", "public_id": "E-b0948c64dddf57ad", "rated_matches": 46, "raw_elo_rating": 1457.46717560364, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 38.62343543749571, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugin_count": 1, "attempted_matches": 28, "capped_draws": 1, "coverage_status": "under_covered", "distinct_rated_opponents": 14, "draws": 21, "generated_at": "2026-07-02T16:51:45Z", "losses": 4, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-4cab1ccd88bbeb2e", "rated_matches": 28, "raw_elo_rating": 1495.177496689084, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 42.309300256585786, "uncertainty": 49.09766908852594, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 4, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 16, "generated_at": "2026-07-11T14:00:45Z", "losses": 8, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-583be34ca1fb2631", "rated_matches": 32, "raw_elo_rating": 1500.5343821590034, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 44.002427693233535, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 28, "capped_draws": 5, "coverage_status": "under_covered", "distinct_rated_opponents": 14, "draws": 9, "generated_at": "2026-07-02T06:10:40Z", "losses": 14, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-f1af7b938699d971", "rated_matches": 28, "raw_elo_rating": 1362.9330880482946, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 19.927496115666777, "uncertainty": 49.09766908852594, "unilateral_faults": 0, "wins": 5 } ], "GB2-04": [ { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 33, "generated_at": "2026-07-02T16:51:45Z", "losses": 11, "model": "claude-opus-4-5", "point_rating_method": "sequential_elo", "public_id": "E-9a77e43e752532c8", "rated_matches": 52, "raw_elo_rating": 1529.4343084381378, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 41.48915163819359, "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": 34, "generated_at": "2026-07-02T16:51:45Z", "losses": 7, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-688a139ef8557587", "rated_matches": 44, "raw_elo_rating": 1481.9095702707032, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 31.08886348521295, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 26, "generated_at": "2026-07-25T15:48:00Z", "losses": 13, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-72e9307528761b35", "rated_matches": 54, "raw_elo_rating": 1518.397463557121, "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": 39.49140350885056, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 11, "generated_at": "2026-07-25T15:48:00Z", "losses": 16, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-9e7782014171d35f", "rated_matches": 50, "raw_elo_rating": 1606.4301741361776, "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": 56.614559798689946, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 29, "generated_at": "2026-07-02T16:51:45Z", "losses": 1, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-be938b7d5557f479", "rated_matches": 34, "raw_elo_rating": 1527.3928154870323, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 38.55892538039321, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 24, "generated_at": "2026-07-02T16:51:45Z", "losses": 19, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-81bc9a578754f220", "rated_matches": 44, "raw_elo_rating": 1349.6267070996366, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 4.737466105277937, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 63, "generated_at": "2026-07-01T00:15:48Z", "losses": 1, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-a43d18fadfcc5a89", "rated_matches": 66, "raw_elo_rating": 1508.500571188575, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 38.52950646636151, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 56, "generated_at": "2026-07-02T06:10:40Z", "losses": 0, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-cb48b9466ec54175", "rated_matches": 56, "raw_elo_rating": 1506.2532248930593, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 37.26239128422888, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-6a79049fd9ab6f5d", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-b05b0185d0e8dc2a", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-0b528ba96380a3b5", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-846809faa1345207", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 41, "generated_at": "2026-07-02T16:51:45Z", "losses": 4, "model": "google/gemma-4-31b-it", "point_rating_method": "sequential_elo", "public_id": "E-ec0cf4b37c805eee", "rated_matches": 48, "raw_elo_rating": 1490.2406649219877, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 33.243606728345505, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 23, "generated_at": "2026-07-02T16:51:45Z", "losses": 9, "model": "gpt-4.1", "point_rating_method": "sequential_elo", "public_id": "E-ecb06954153be8d5", "rated_matches": 34, "raw_elo_rating": 1458.5374385455698, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 24.842595418716364, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 49, "generated_at": "2026-07-02T16:51:45Z", "losses": 8, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-8d62bf1b340a70dc", "rated_matches": 68, "raw_elo_rating": 1494.2473590945217, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 35.83231653302763, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 42, "generated_at": "2026-07-02T16:51:45Z", "losses": 12, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-0880cdf1a43cb90c", "rated_matches": 70, "raw_elo_rating": 1490.3720877432415, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 35.19641529069496, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 52, "generated_at": "2026-07-02T06:10:40Z", "losses": 4, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-c9bf6a0be0c43fd1", "rated_matches": 62, "raw_elo_rating": 1469.9760007329758, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 30.55093983673764, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 35, "generated_at": "2026-07-01T00:15:48Z", "losses": 7, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-ff4778924359442b", "rated_matches": 48, "raw_elo_rating": 1471.8616369261956, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 29.582413898343336, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 41, "generated_at": "2026-07-01T00:15:48Z", "losses": 12, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-48f60c9100c65daa", "rated_matches": 58, "raw_elo_rating": 1472.887750806737, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 30.796250488236097, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 46, "generated_at": "2026-07-02T06:10:40Z", "losses": 8, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-c8f4bd9fcf2e481e", "rated_matches": 60, "raw_elo_rating": 1501.6481606432203, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 36.69694374378444, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 46, "generated_at": "2026-07-02T16:51:45Z", "losses": 12, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-ba1aa87056709e9a", "rated_matches": 64, "raw_elo_rating": 1496.2226687102534, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 35.93505786860947, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 42, "generated_at": "2026-07-10T05:30:29Z", "losses": 11, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-71a01107bf3f9fc1", "rated_matches": 60, "raw_elo_rating": 1496.0402265733064, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 35.57981567734945, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 45, "generated_at": "2026-07-10T10:07:13Z", "losses": 4, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-f0b7195272d6417e", "rated_matches": 52, "raw_elo_rating": 1480.2355614499472, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 31.688519104226355, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 37, "draws": 69, "generated_at": "2026-07-10T05:30:29Z", "losses": 1, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-50ee0aadbc66fe0e", "rated_matches": 74, "raw_elo_rating": 1520.6818659965604, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 41.48990096796995, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 55, "generated_at": "2026-07-24T13:40:00Z", "losses": 4, "model": "inclusionai/ling-3.0-flash", "point_rating_method": "sequential_elo", "public_id": "E-f38039bb8cc277a1", "rated_matches": 60, "raw_elo_rating": 1477.6032838196008, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 31.907085942540736, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 34, "generated_at": "2026-07-24T13:40:00Z", "losses": 11, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-9e1d4bf411e97fa6", "rated_matches": 60, "raw_elo_rating": 1569.103382231883, "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": 50.13435586825387, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 19, "generated_at": "2026-07-24T14:00:00Z", "losses": 6, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-3c06949f23d4a77f", "rated_matches": 32, "raw_elo_rating": 1514.4819621397323, "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": 35.584880493815724, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 28, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 14, "draws": 18, "generated_at": "2026-07-21T14:20:15Z", "losses": 5, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-818ed7ee27b56509", "rated_matches": 28, "raw_elo_rating": 1503.0402498423114, "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": 32.379915303068024, "uncertainty": 49.09766908852594, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 45, "generated_at": "2026-07-11T17:22:09Z", "losses": 3, "model": "nex-agi/nex-n2-pro", "point_rating_method": "sequential_elo", "public_id": "E-6f4b3b55e4ec7cf5", "rated_matches": 50, "raw_elo_rating": 1491.333286691229, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 33.686693364975824, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 27, "generated_at": "2026-07-02T16:51:45Z", "losses": 6, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-f36b99b3d76fbb35", "rated_matches": 38, "raw_elo_rating": 1495.9623564264125, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 33.00720768323213, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 28, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 14, "draws": 15, "generated_at": "2026-07-21T14:20:15Z", "losses": 8, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-a4643af0a1bcc24c", "rated_matches": 28, "raw_elo_rating": 1468.27005544933, "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": 25.45352145685857, "uncertainty": 49.09766908852594, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 22, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 11, "draws": 11, "generated_at": "2026-07-21T14:20:15Z", "losses": 10, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-f6de1ce39e48807c", "rated_matches": 22, "raw_elo_rating": 1422.0102326087713, "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": 14.420068188974202, "uncertainty": 60.5072070285374, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 34, "generated_at": "2026-07-02T16:51:45Z", "losses": 3, "model": "qwen/qwen3.7-plus", "point_rating_method": "sequential_elo", "public_id": "E-84b9a07f75f324e2", "rated_matches": 40, "raw_elo_rating": 1508.141304108455, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 35.74840773334668, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 24, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 12, "draws": 13, "generated_at": "2026-07-21T14:20:15Z", "losses": 3, "model": "stepfun/step-3.7-flash", "point_rating_method": "sequential_elo", "public_id": "E-fa23ca0bdb2bc960", "rated_matches": 24, "raw_elo_rating": 1529.6913005047602, "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": 36.549112144936515, "uncertainty": 56.25, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 33, "generated_at": "2026-07-02T16:51:45Z", "losses": 6, "model": "tencent/hy3-preview", "point_rating_method": "sequential_elo", "public_id": "E-3fd10f7865cc280e", "rated_matches": 48, "raw_elo_rating": 1517.8546980180151, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 38.74445802482134, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 28, "generated_at": "2026-07-24T13:40:00Z", "losses": 16, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-646ff33c7bab8b13", "rated_matches": 50, "raw_elo_rating": 1434.9202660770147, "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": 22.44894201932177, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 52, "generated_at": "2026-07-24T13:40:00Z", "losses": 6, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-ddc16fa197bfc7c5", "rated_matches": 62, "raw_elo_rating": 1510.686655827679, "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": 38.66070269098349, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 26, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 13, "draws": 19, "generated_at": "2026-07-21T14:20:15Z", "losses": 3, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-436af9e9ba989a11", "rated_matches": 26, "raw_elo_rating": 1528.1630099942583, "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": 36.846260866909006, "uncertainty": 52.475044864937615, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 35, "generated_at": "2026-07-24T14:00:00Z", "losses": 4, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-617354569710a53d", "rated_matches": 44, "raw_elo_rating": 1529.164083365473, "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": 40.50219505897332, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 39, "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": 54, "raw_elo_rating": 1491.3499007385865, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 34.10339587956107, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 44, "generated_at": "2026-07-02T06:10:40Z", "losses": 2, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-d58c55e107783a21", "rated_matches": 48, "raw_elo_rating": 1507.84708305417, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 36.750891871081286, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 25, "generated_at": "2026-07-02T16:51:45Z", "losses": 5, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-1d5f5ff0402ff944", "rated_matches": 36, "raw_elo_rating": 1540.7272314478314, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 41.58428267896779, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 34, "generated_at": "2026-07-02T06:10:40Z", "losses": 1, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-3efc86009429a22c", "rated_matches": 36, "raw_elo_rating": 1496.826980032491, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 32.83913653990452, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 28, "generated_at": "2026-07-01T00:15:48Z", "losses": 6, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-e6dc2409fc5fe917", "rated_matches": 38, "raw_elo_rating": 1486.5884066146955, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 31.139870746408565, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 16, "generated_at": "2026-07-11T14:00:45Z", "losses": 11, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-f776c26a98306f5d", "rated_matches": 38, "raw_elo_rating": 1506.0505372159496, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 35.01682294595854, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 11 } ], "GB2-05": [ { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 24, "model": "claude-opus-4-5", "point_rating_method": "sequential_elo", "public_id": "E-934b5bc34a7e20b9", "rated_matches": 62, "raw_elo_rating": 1523.974286932912, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 48.01327090561448, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 38 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 28, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-233f9cae6335e53d", "rated_matches": 56, "raw_elo_rating": 1426.356743667632, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 36.044276212350354, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 0, "generated_at": "2026-07-25T10:50:00Z", "losses": 15, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-09963ffe0b0fa5fd", "rated_matches": 58, "raw_elo_rating": 1817.924552575232, "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": 82.92397813412782, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 43 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 0, "generated_at": "2026-07-25T10:50:00Z", "losses": 14, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-b53cb955b1d8baab", "rated_matches": 56, "raw_elo_rating": 1810.6684408918225, "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": 81.94907240856237, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 42 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 27, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-e619c51e7d5d70d2", "rated_matches": 46, "raw_elo_rating": 1435.9565657354813, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 36.55014764549661, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 41, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-0dca18c79b6ac9d7", "rated_matches": 64, "raw_elo_rating": 1452.4159035831772, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 39.55918420487605, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 39, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-b8554f0ccf0845da", "rated_matches": 62, "raw_elo_rating": 1411.6622811428792, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 34.597963035941035, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 0, "generated_at": "2026-07-01T00:15:48Z", "losses": 38, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-efa8d9109b008ee9", "rated_matches": 68, "raw_elo_rating": 1439.1921009936452, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 38.15398238039824, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 30 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 39, "model": "deepseek/deepseek-v4-pro", "point_rating_method": "sequential_elo", "public_id": "E-da5f3b1a4e370e1a", "rated_matches": 70, "raw_elo_rating": 1407.767805319223, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 34.48204243070537, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 31 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 30, "model": "google/gemini-3.1-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-d979b43c3aeea657", "rated_matches": 46, "raw_elo_rating": 1305.284761574915, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 20.941820909912263, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-214f636367cbdac4", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-a870d09d3e1a40d4", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-9bef179ce22a6c93", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-e23af86eb5787555", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 38, "model": "google/gemma-4-31b-it", "point_rating_method": "sequential_elo", "public_id": "E-e8e17fbbdd12faa4", "rated_matches": 60, "raw_elo_rating": 1306.4883081561472, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 21.93738491295836, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 22 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 28, "model": "gpt-4.1", "point_rating_method": "sequential_elo", "public_id": "E-1b9f1f7b70f02927", "rated_matches": 46, "raw_elo_rating": 1343.9306693331305, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 25.5579502972611, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 80, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 40, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 25, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-6d3546010ef68f50", "rated_matches": 80, "raw_elo_rating": 1744.8030888257304, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 75.10136719944344, "uncertainty": 11.805555555555554, "unilateral_faults": 0, "wins": 55 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 37, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-427bdffeacc6c394", "rated_matches": 58, "raw_elo_rating": 1333.6735560249267, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 25.081754061810127, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 0, "generated_at": "2026-07-01T00:15:48Z", "losses": 26, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-8ed627956c0a0292", "rated_matches": 60, "raw_elo_rating": 1411.9678598975274, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 34.53657812130674, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 40, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-cdd304da89074d54", "rated_matches": 70, "raw_elo_rating": 1386.5322565424424, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 31.945524427861, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 30 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 0, "generated_at": "2026-07-09T17:30:50Z", "losses": 49, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-3311575b341ee4a8", "rated_matches": 70, "raw_elo_rating": 1344.61500478334, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 26.938643521021447, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 0, "generated_at": "2026-07-01T00:15:48Z", "losses": 46, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-49b3c6006a3b9fcc", "rated_matches": 68, "raw_elo_rating": 1391.6284739987418, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 32.472660111719044, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 22 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 41, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-6c37eeef15b82287", "rated_matches": 58, "raw_elo_rating": 1289.8416048261813, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 19.846168465030985, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 25, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-6f42dbbf02274b56", "rated_matches": 60, "raw_elo_rating": 1578.3209032811378, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 54.40691412278813, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 35 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 53, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-59156a669808a24f", "rated_matches": 58, "raw_elo_rating": 1123.6908903432654, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 0.0, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 25, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-471e9297eea18ffd", "rated_matches": 64, "raw_elo_rating": 1587.9373567546218, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 55.746785917192774, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 39 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 23, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-1f00b423eab1c19d", "rated_matches": 58, "raw_elo_rating": 1583.9989523111312, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 54.98231754257976, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 35 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 56, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-067ab716d64e3e9a", "rated_matches": 72, "raw_elo_rating": 1252.5131973626942, "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": 16.015593489602008, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 42, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-8cc657b7db4428cb", "rated_matches": 68, "raw_elo_rating": 1350.9008543530088, "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": 27.60787693468351, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 37, "model": "minimax/minimax-m3", "point_rating_method": "sequential_elo", "public_id": "E-33797d7b77c7800c", "rated_matches": 70, "raw_elo_rating": 1469.451876888559, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 41.85000638911461, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 33 }, { "admitted_plugin_count": 1, "attempted_matches": 76, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 38, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 39, "model": "mistralai/mistral-medium-3-5", "point_rating_method": "sequential_elo", "public_id": "E-4a7d37b86196302f", "rated_matches": 76, "raw_elo_rating": 1441.2006518851858, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 38.70088877553203, "uncertainty": 13.230288229818967, "unilateral_faults": 0, "wins": 37 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-24T14:00:00Z", "losses": 11, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-4419230379dcd41e", "rated_matches": 38, "raw_elo_rating": 1637.7681353062624, "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": 59.974415011480026, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 27 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-21T14:20:15Z", "losses": 14, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-91be72471ad409b6", "rated_matches": 38, "raw_elo_rating": 1613.8418822581664, "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": 57.11650103736769, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugin_count": 1, "attempted_matches": 76, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 38, "draws": 0, "generated_at": "2026-07-11T17:22:09Z", "losses": 42, "model": "nex-agi/nex-n2-pro", "point_rating_method": "sequential_elo", "public_id": "E-962a9da8812a74d4", "rated_matches": 76, "raw_elo_rating": 1459.739093474812, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 40.915245999404725, "uncertainty": 13.230288229818967, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 16, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-4477e0de2e04aad4", "rated_matches": 48, "raw_elo_rating": 1544.427991149785, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 49.650421679977455, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-21T14:20:15Z", "losses": 12, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-b556333d605791f4", "rated_matches": 38, "raw_elo_rating": 1603.7314964969933, "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": 55.9088479755849, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-21T14:20:15Z", "losses": 19, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-172336d3fd38632a", "rated_matches": 38, "raw_elo_rating": 1430.2908983914597, "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": 35.1919263578203, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 20, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-1ca53619662c7f6f", "rated_matches": 68, "raw_elo_rating": 1704.7305555195596, "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": 69.87169673911161, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 48 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 36, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-21623e96b2b104e9", "rated_matches": 64, "raw_elo_rating": 1390.6753030488358, "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": 32.1844680434074, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 34, "model": "qwen/qwen3.7-max", "point_rating_method": "sequential_elo", "public_id": "E-c577c41440c17864", "rated_matches": 62, "raw_elo_rating": 1521.2856555640442, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 47.692122535876926, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 37, "model": "qwen/qwen3.7-plus", "point_rating_method": "sequential_elo", "public_id": "E-94daaf1196d89c6c", "rated_matches": 70, "raw_elo_rating": 1416.7106818294349, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 35.55024026744643, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 33 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-21T14:20:15Z", "losses": 21, "model": "stepfun/step-3.7-flash", "point_rating_method": "sequential_elo", "public_id": "E-386b7a319dfe25ad", "rated_matches": 38, "raw_elo_rating": 1442.1903981687146, "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": 36.613283334610685, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 37, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 48, "model": "tencent/hy3-preview", "point_rating_method": "sequential_elo", "public_id": "E-1bb81f8a4ae78954", "rated_matches": 74, "raw_elo_rating": 1375.3160039220393, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 30.759058589728017, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 40, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-0f05573125dedc2b", "rated_matches": 72, "raw_elo_rating": 1434.6823288381802, "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": 37.77511034538186, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 45, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-f7a1d86c7e241f8d", "rated_matches": 70, "raw_elo_rating": 1465.738774441627, "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": 41.40648824404333, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-24T14:00:00Z", "losses": 18, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-f1d32edccc2b8ba2", "rated_matches": 38, "raw_elo_rating": 1542.9348479566636, "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": 48.64688384382832, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-21T14:20:15Z", "losses": 3, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-fcfafa8fb4ccd299", "rated_matches": 38, "raw_elo_rating": 1809.7776787372047, "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": 80.52040175097464, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 35 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 27, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-09d406abc15f7c9a", "rated_matches": 62, "raw_elo_rating": 1585.8100503760031, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 55.3993539704669, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 35 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 0, "generated_at": "2026-07-01T00:15:48Z", "losses": 39, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-9490f08c56c27d13", "rated_matches": 62, "raw_elo_rating": 1327.556766274441, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 24.55182978811308, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 25, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-be8fc9653466bbe1", "rated_matches": 60, "raw_elo_rating": 1454.1567111139825, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 39.57590070979902, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 35 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 37, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 48, "model": "xiaomi/mimo-v2.5-pro", "point_rating_method": "sequential_elo", "public_id": "E-af55f57b03605914", "rated_matches": 74, "raw_elo_rating": 1340.6671312177457, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 26.62036218416104, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 0, "generated_at": "2026-07-11T14:00:45Z", "losses": 22, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-38e323f4ce233fa1", "rated_matches": 46, "raw_elo_rating": 1454.1707872831807, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 38.72577782812944, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 0, "generated_at": "2026-07-01T00:15:48Z", "losses": 27, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-6370c4b68d38a97e", "rated_matches": 46, "raw_elo_rating": 1376.3332358443529, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 29.42833265271711, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 28, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-a6655b3c71893984", "rated_matches": 48, "raw_elo_rating": 1426.5839450762207, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 35.57432939078477, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 22, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-d8655d29a4806df8", "rated_matches": 46, "raw_elo_rating": 1579.0569863043886, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 53.64303263769047, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 24 } ], "GB2-06": [ { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 1, "generated_at": "2026-07-02T16:51:45Z", "losses": 34, "model": "claude-opus-4-5", "point_rating_method": "sequential_elo", "public_id": "E-40a259ca8a40b5b4", "rated_matches": 58, "raw_elo_rating": 1455.789381704686, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 46.195935526761325, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 3, "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": 60, "raw_elo_rating": 1494.5099950724373, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 51.49077663608371, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 11, "generated_at": "2026-07-25T10:50:00Z", "losses": 7, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-ca8985adf5006428", "rated_matches": 54, "raw_elo_rating": 1772.6067863963965, "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": 88.32799956129024, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 36 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 1, "generated_at": "2026-07-02T16:51:45Z", "losses": 21, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-500304c7462c6005", "rated_matches": 40, "raw_elo_rating": 1508.2219156109704, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 51.81947406397143, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 0, "generated_at": "2026-07-01T00:15:48Z", "losses": 30, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-8daa317358045ed1", "rated_matches": 50, "raw_elo_rating": 1368.50660805525, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 33.993570618074976, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 42, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-db0efb02339d9e80", "rated_matches": 56, "raw_elo_rating": 1217.0175055173588, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 14.134057602623102, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 6, "generated_at": "2026-07-02T16:51:45Z", "losses": 12, "model": "deepseek/deepseek-v4-pro", "point_rating_method": "sequential_elo", "public_id": "E-945bebaa34963e03", "rated_matches": 58, "raw_elo_rating": 1666.5668321788196, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 74.39181497022835, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 40 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 1, "generated_at": "2026-07-02T16:51:45Z", "losses": 19, "model": "google/gemini-3.1-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-dc1c0f46738d1091", "rated_matches": 40, "raw_elo_rating": 1420.038975375964, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 40.02316688669191, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-3efea50fdbbd1829", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-46f1468c28505bfe", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-5455742d003ec402", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-bb2e288b40b1a588", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 32, "model": "google/gemma-4-31b-it", "point_rating_method": "sequential_elo", "public_id": "E-da266f7bbd330107", "rated_matches": 56, "raw_elo_rating": 1400.355913354061, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 38.65939289391045, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 8, "generated_at": "2026-07-02T16:51:45Z", "losses": 16, "model": "gpt-4.1", "point_rating_method": "sequential_elo", "public_id": "E-4dcd6d3653c67437", "rated_matches": 42, "raw_elo_rating": 1498.497941533217, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 50.71534315686365, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 6, "generated_at": "2026-07-02T16:51:45Z", "losses": 15, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-00a57c19a4229948", "rated_matches": 56, "raw_elo_rating": 1628.545670896392, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 69.18453151488029, "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": 5, "generated_at": "2026-07-01T00:15:48Z", "losses": 37, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-050fceb6ddf16bc3", "rated_matches": 66, "raw_elo_rating": 1405.8139511588322, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 39.9397878877152, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 2, "generated_at": "2026-07-02T16:51:45Z", "losses": 33, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-144154b792c9e9a6", "rated_matches": 66, "raw_elo_rating": 1429.641609373582, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 43.127234063442, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 31 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 1, "generated_at": "2026-07-02T06:10:40Z", "losses": 24, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-e726e4bfd20b0da9", "rated_matches": 54, "raw_elo_rating": 1371.968874884054, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 34.734324203353026, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 2, "generated_at": "2026-07-02T06:10:40Z", "losses": 21, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-3d7e23d6ea4c2792", "rated_matches": 58, "raw_elo_rating": 1603.5431286227667, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 65.96108035630274, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 35 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 0, "generated_at": "2026-07-09T17:30:50Z", "losses": 35, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-a1fb59d78d39d217", "rated_matches": 62, "raw_elo_rating": 1408.7464674466262, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 40.12774007871851, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 27 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 18, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-d5866895bf388f66", "rated_matches": 58, "raw_elo_rating": 1641.8873925366609, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 71.09042526598186, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 40 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 45, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-ae522f9c5c491f57", "rated_matches": 54, "raw_elo_rating": 1184.250882263081, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 9.62312811760228, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 84, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 42, "draws": 1, "generated_at": "2026-07-10T05:30:29Z", "losses": 49, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-992b9a5ebbb74c80", "rated_matches": 84, "raw_elo_rating": 1408.9987545376268, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 41.09911159247618, "uncertainty": 10.482614454664043, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 1, "generated_at": "2026-07-10T05:30:29Z", "losses": 38, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-22ffdca36d9bac9c", "rated_matches": 62, "raw_elo_rating": 1357.4859927674747, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 33.27058263129217, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 3, "generated_at": "2026-07-24T13:40:00Z", "losses": 35, "model": "inclusionai/ling-3.0-flash", "point_rating_method": "sequential_elo", "public_id": "E-6807fffacebac165", "rated_matches": 64, "raw_elo_rating": 1385.9962675125475, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 37.18895084585539, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 57, "model": "inclusionai/ling-3.0-flash", "point_rating_method": "sequential_elo", "public_id": "E-9bde0475193e2c4a", "rated_matches": 60, "raw_elo_rating": 1109.5922398363446, "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": 20.268439966447993, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 2, "generated_at": "2026-07-24T13:40:00Z", "losses": 38, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-3e8b2d11481a50d7", "rated_matches": 64, "raw_elo_rating": 1462.238800043231, "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": 47.38797949367356, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 10, "generated_at": "2026-07-24T13:40:00Z", "losses": 27, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-e3023ff7ecf82fc4", "rated_matches": 66, "raw_elo_rating": 1536.234820835545, "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": 57.38629893548021, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 5, "generated_at": "2026-07-02T16:51:45Z", "losses": 32, "model": "mistralai/mistral-medium-3-5", "point_rating_method": "sequential_elo", "public_id": "E-cf0bc4a1e7a8d72a", "rated_matches": 60, "raw_elo_rating": 1331.884389148848, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 29.736210534597397, "uncertainty": 20.268439966447993, "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, "generated_at": "2026-07-21T14:20:15Z", "losses": 5, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-2f8c760ee4329d00", "rated_matches": 34, "raw_elo_rating": 1749.2444896549302, "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": 83.37330799031281, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 2, "generated_at": "2026-07-24T14:00:00Z", "losses": 20, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-95a5c0e17cd4b70a", "rated_matches": 42, "raw_elo_rating": 1490.7850976149205, "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": 49.683589443184225, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 2, "generated_at": "2026-07-11T17:22:09Z", "losses": 40, "model": "nex-agi/nex-n2-pro", "point_rating_method": "sequential_elo", "public_id": "E-973417dedd770061", "rated_matches": 62, "raw_elo_rating": 1338.9971736131567, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 30.7973175132515, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 25, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-6e76a1c11ba24bc6", "rated_matches": 40, "raw_elo_rating": 1365.0587937088449, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 32.66842106080365, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 1, "generated_at": "2026-07-21T14:20:15Z", "losses": 4, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-e4a4a86669325de4", "rated_matches": 34, "raw_elo_rating": 1750.2486128915534, "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": 83.5076304126712, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 1, "generated_at": "2026-07-21T14:20:15Z", "losses": 29, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-b75de88bfc62ab22", "rated_matches": 48, "raw_elo_rating": 1467.99966969457, "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": 47.15146009630666, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 2, "generated_at": "2026-07-24T13:40:00Z", "losses": 33, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-a29031412bc33c39", "rated_matches": 62, "raw_elo_rating": 1345.003199893997, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 31.60074877484011, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 27 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 32, "model": "qwen/qwen3.7-max", "point_rating_method": "sequential_elo", "public_id": "E-0c7e9f6c7d4cb892", "rated_matches": 52, "raw_elo_rating": 1354.7769806450185, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 32.299677169988506, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 44, "model": "qwen/qwen3.7-plus", "point_rating_method": "sequential_elo", "public_id": "E-2fb82a23fdec2792", "rated_matches": 60, "raw_elo_rating": 1347.1351283730276, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 31.776314936759203, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 0, "generated_at": "2026-07-21T14:20:15Z", "losses": 21, "model": "stepfun/step-3.7-flash", "point_rating_method": "sequential_elo", "public_id": "E-8a88dceef8a0239c", "rated_matches": 34, "raw_elo_rating": 1395.505080795559, "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": 36.05328535902041, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 39, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-02be9616e86c7055", "rated_matches": 64, "raw_elo_rating": 1418.0209855099072, "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": 41.47292470469752, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 2, "generated_at": "2026-07-24T14:00:00Z", "losses": 16, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-14f0700d6ad1d367", "rated_matches": 34, "raw_elo_rating": 1539.4815378267888, "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": 55.31313889657064, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 1, "generated_at": "2026-07-21T14:20:15Z", "losses": 15, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-9eb453b88beb68a4", "rated_matches": 34, "raw_elo_rating": 1561.2596701251873, "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": 58.2264182412455, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 28, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-d572bc902e0e416b", "rated_matches": 50, "raw_elo_rating": 1394.950915922396, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 37.53104825105106, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 22 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 34, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-d79ad8bc05d1b933", "rated_matches": 54, "raw_elo_rating": 1410.4158445729888, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 39.87740815221628, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 0, "generated_at": "2026-07-01T00:15:48Z", "losses": 22, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-ff7683792b6b3363", "rated_matches": 58, "raw_elo_rating": 1595.599320818678, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 64.89843040649872, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 36 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 32, "model": "xiaomi/mimo-v2.5-pro", "point_rating_method": "sequential_elo", "public_id": "E-6b662c734cdcff91", "rated_matches": 60, "raw_elo_rating": 1452.7547853739904, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 45.905146597643856, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 0, "generated_at": "2026-07-01T00:15:48Z", "losses": 33, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-18454080fac44f8c", "rated_matches": 40, "raw_elo_rating": 1201.0915329623122, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 10.734380648581704, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 4, "generated_at": "2026-07-11T14:00:45Z", "losses": 18, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-657c61c9039ce566", "rated_matches": 40, "raw_elo_rating": 1467.0377104482063, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 46.31022778960863, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 6, "generated_at": "2026-07-02T06:10:40Z", "losses": 19, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-6954e92d5890c32a", "rated_matches": 42, "raw_elo_rating": 1502.883231870553, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 51.30196718803007, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 3, "generated_at": "2026-07-02T16:51:45Z", "losses": 16, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-ec1479c855f477b4", "rated_matches": 40, "raw_elo_rating": 1596.696441786834, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 63.65478694142105, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 21 } ], "GB2-07": [ { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 31, "model": "claude-opus-4-5", "point_rating_method": "sequential_elo", "public_id": "E-ca22621c58b6f244", "rated_matches": 60, "raw_elo_rating": 1484.101949958685, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 45.759775387566016, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 25, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-76804598cce96e62", "rated_matches": 62, "raw_elo_rating": 1585.6437673215585, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 59.132337083693706, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 37 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 0, "generated_at": "2026-07-25T10:50:00Z", "losses": 18, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-914b104a64ab3110", "rated_matches": 52, "raw_elo_rating": 1741.5924576205412, "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": 78.91131680197287, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 20, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-cd6f193a087d8c8d", "rated_matches": 44, "raw_elo_rating": 1563.6722330880127, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 55.05572388516481, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 38, "model": "cohere/north-mini-code", "point_rating_method": "sequential_elo", "public_id": "E-3b908f26a42804a4", "rated_matches": 64, "raw_elo_rating": 1453.4820196031317, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 41.96870093034758, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 0, "generated_at": "2026-07-11T17:22:09Z", "losses": 52, "model": "cohere/north-mini-code", "point_rating_method": "sequential_elo", "public_id": "E-c7f5dc6d5d3c2a8d", "rated_matches": 66, "raw_elo_rating": 1225.971241468745, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 12.343986824956822, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 0, "generated_at": "2026-07-01T00:15:48Z", "losses": 33, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-8f6a725b68dde85b", "rated_matches": 56, "raw_elo_rating": 1417.6779691835304, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 36.85131172795486, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 40, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-c394c0713cfcfaa4", "rated_matches": 72, "raw_elo_rating": 1435.8767573923717, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 40.03419471161385, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 36, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-c8fd55a5d257c569", "rated_matches": 68, "raw_elo_rating": 1430.6978152659915, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 39.18283162698061, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 30, "model": "deepseek/deepseek-v4-pro", "point_rating_method": "sequential_elo", "public_id": "E-f76d96b0f3163d4b", "rated_matches": 60, "raw_elo_rating": 1427.2591466449226, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 38.33378677910713, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 30 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 38, "model": "google/gemini-3.1-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-3d6a15fe821fe6ad", "rated_matches": 42, "raw_elo_rating": 1143.6148913795123, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 0.0, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-455ee67905f5f955", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-e2e240babaf0b862", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-8e9b51be911dad38", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-a2d90fcdc2f4ef9d", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 36, "model": "google/gemma-4-31b-it", "point_rating_method": "sequential_elo", "public_id": "E-3f820f7e8ff15839", "rated_matches": 58, "raw_elo_rating": 1349.90531693581, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 28.115764310136107, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 22 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 19, "model": "gpt-4.1", "point_rating_method": "sequential_elo", "public_id": "E-fcfa606d3cbb0ba0", "rated_matches": 44, "raw_elo_rating": 1507.216526715812, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 47.68030592612551, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 32, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-c8176c382cf75e88", "rated_matches": 60, "raw_elo_rating": 1394.6909165849377, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 34.07904754522137, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 0, "generated_at": "2026-07-01T00:15:48Z", "losses": 38, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-022243613d51f0fb", "rated_matches": 64, "raw_elo_rating": 1355.2492138334867, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 29.135489791977815, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 45, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-6a87ebc54bdde781", "rated_matches": 60, "raw_elo_rating": 1251.8211628405084, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 15.414430356248433, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 42, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-c2ab31787514c10c", "rated_matches": 58, "raw_elo_rating": 1284.705843848199, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 19.59805377862727, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 42, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-4e14ae758717169e", "rated_matches": 66, "raw_elo_rating": 1422.57460456147, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 38.02840507316459, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 34, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-ce2925d9379d2a5d", "rated_matches": 60, "raw_elo_rating": 1335.0448852215657, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 26.28684301584092, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 28, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-4edfe4117ad3e936", "rated_matches": 60, "raw_elo_rating": 1456.9711745696457, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 42.21538951578612, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 46, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-ea529147555b5f2e", "rated_matches": 60, "raw_elo_rating": 1245.2596467020408, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 14.557228718434729, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 31, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-bef852aad169a609", "rated_matches": 60, "raw_elo_rating": 1573.8998861000514, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 57.49104851229338, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 33, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-8ebe8776c7d44d46", "rated_matches": 60, "raw_elo_rating": 1496.914059374072, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 47.433559455600474, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 27 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 32, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-c1f595f47c71e648", "rated_matches": 66, "raw_elo_rating": 1359.4019231798957, "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": 29.775476206938286, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 36, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-e2db910734ca5315", "rated_matches": 64, "raw_elo_rating": 1494.2969465629394, "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": 47.30079514437856, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 30, "model": "minimax/minimax-m3", "point_rating_method": "sequential_elo", "public_id": "E-24e15c4d7490cdf3", "rated_matches": 58, "raw_elo_rating": 1424.7213899013211, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 37.889795026123, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 0, "generated_at": "2026-07-24T14:00:00Z", "losses": 23, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-4d8815930b656774", "rated_matches": 40, "raw_elo_rating": 1454.786214678421, "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": 40.459614863654, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 0, "generated_at": "2026-07-21T14:20:15Z", "losses": 15, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-c00660d2a8eb25c9", "rated_matches": 36, "raw_elo_rating": 1542.0769976880406, "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": 51.43353155651955, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 0, "generated_at": "2026-07-11T17:22:09Z", "losses": 20, "model": "nex-agi/nex-n2-pro", "point_rating_method": "sequential_elo", "public_id": "E-1006c453b0c3a745", "rated_matches": 62, "raw_elo_rating": 1657.169899748788, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 68.47656737578293, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 42 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 0, "generated_at": "2026-07-03T18:15:00Z", "losses": 34, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-0e1c7f89e1c19b69", "rated_matches": 44, "raw_elo_rating": 1301.0437601099366, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 20.745733263714285, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-21T14:20:15Z", "losses": 16, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-3fae70801895971d", "rated_matches": 40, "raw_elo_rating": 1458.0625092856346, "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": 40.88763257236601, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 0, "generated_at": "2026-07-21T14:20:15Z", "losses": 23, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-759d747bb732d949", "rated_matches": 36, "raw_elo_rating": 1369.5464379088992, "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": 28.89400329893377, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 39, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-069a963abdd14cdf", "rated_matches": 66, "raw_elo_rating": 1497.5583703289335, "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": 47.82434330891513, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 27 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 28, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-d8e68d23876f6d21", "rated_matches": 68, "raw_elo_rating": 1585.8551435458874, "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": 59.45270723402088, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 40 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 22, "model": "qwen/qwen3.7-max", "point_rating_method": "sequential_elo", "public_id": "E-3142a09c7f192060", "rated_matches": 64, "raw_elo_rating": 1730.8896425336536, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 78.20945134532496, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 42 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 36, "model": "qwen/qwen3.7-plus", "point_rating_method": "sequential_elo", "public_id": "E-737a66790985a5e6", "rated_matches": 60, "raw_elo_rating": 1272.023445307137, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 18.05367245403799, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 0, "generated_at": "2026-07-21T14:20:15Z", "losses": 24, "model": "stepfun/step-3.7-flash", "point_rating_method": "sequential_elo", "public_id": "E-1140a7c92290e8f4", "rated_matches": 46, "raw_elo_rating": 1426.1484616915282, "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": 37.25705460545867, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 22 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 42, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-062d41f517db2ccb", "rated_matches": 66, "raw_elo_rating": 1358.1292477360432, "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": 29.609212884277255, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 0, "generated_at": "2026-07-21T14:20:15Z", "losses": 7, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-7e2507a947914c49", "rated_matches": 36, "raw_elo_rating": 1675.633825922066, "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": 68.88150081963373, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-24T14:00:00Z", "losses": 5, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-ca54791ad3682b4f", "rated_matches": 38, "raw_elo_rating": 1735.6551782099175, "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": 76.94591559158341, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 33 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 32, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-0984b025e9005f5b", "rated_matches": 56, "raw_elo_rating": 1353.1217849238958, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 28.41764095574733, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugin_count": 1, "attempted_matches": 76, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 38, "draws": 0, "generated_at": "2026-07-01T00:15:48Z", "losses": 44, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-47d67dcf0077af42", "rated_matches": 76, "raw_elo_rating": 1451.0459115638023, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 42.17688423878943, "uncertainty": 13.230288229818967, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 21, "model": "xiaomi/mimo-v2.5-pro", "point_rating_method": "sequential_elo", "public_id": "E-83580d03385c6759", "rated_matches": 54, "raw_elo_rating": 1636.5407743062012, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 65.31899895038302, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 33 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 0, "generated_at": "2026-07-11T14:00:45Z", "losses": 20, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-62e8714f035ebc68", "rated_matches": 46, "raw_elo_rating": 1538.4426521126998, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 51.927256112952506, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 23, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-e31f275ab7ef3741", "rated_matches": 44, "raw_elo_rating": 1531.359555833092, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 50.834370271069695, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 0, "generated_at": "2026-07-01T00:15:48Z", "losses": 18, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-f7579fbfcb1dcbb9", "rated_matches": 44, "raw_elo_rating": 1583.7592130000278, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 57.67990276637863, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 26 } ], "GB2-08": [ { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 6, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 6, "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": 70, "raw_elo_rating": 1636.0494722351684, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 57.75514722037097, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 45 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 21, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-c9d7578e8375d994", "rated_matches": 70, "raw_elo_rating": 1649.3609751746642, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 59.81731792757247, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 49 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 0, "generated_at": "2026-07-25T10:50:00Z", "losses": 25, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-5a7942274854aaa6", "rated_matches": 56, "raw_elo_rating": 1564.7574379284083, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 45.85724479955294, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 31 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 42, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 42, "generated_at": "2026-07-02T16:51:45Z", "losses": 2, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-cf0ed4bbe4aaadd7", "rated_matches": 44, "raw_elo_rating": 1446.1686024506469, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 26.45612575749886, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 49, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 49, "generated_at": "2026-07-11T17:22:09Z", "losses": 9, "model": "cohere/north-mini-code", "point_rating_method": "sequential_elo", "public_id": "E-c36a98e057c264eb", "rated_matches": 62, "raw_elo_rating": 1450.883258777918, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 28.6168805991318, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 44, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 44, "generated_at": "2026-07-02T16:51:45Z", "losses": 14, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-4375cf96eeb624e2", "rated_matches": 64, "raw_elo_rating": 1442.4688068125326, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 27.434390561039304, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 55, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 55, "generated_at": "2026-07-02T06:10:40Z", "losses": 7, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-95b070e1c29e44f0", "rated_matches": 62, "raw_elo_rating": 1422.4165040540342, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 24.206912169007527, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 56, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 56, "generated_at": "2026-07-01T00:15:48Z", "losses": 10, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-b53fd6f34eb6127d", "rated_matches": 70, "raw_elo_rating": 1445.3812885112827, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 28.217510106225216, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 57, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 57, "generated_at": "2026-07-02T16:51:45Z", "losses": 8, "model": "deepseek/deepseek-v4-pro", "point_rating_method": "sequential_elo", "public_id": "E-c296a7abab6975d7", "rated_matches": 68, "raw_elo_rating": 1446.802549177008, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 28.33186721946456, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-284d554eca16e6f6", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-af119b49b8f1d63d", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-657c523bc9e9f80c", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-c694a36a5e4e3f09", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 43, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 43, "generated_at": "2026-07-02T16:51:45Z", "losses": 10, "model": "google/gemma-4-31b-it", "point_rating_method": "sequential_elo", "public_id": "E-8546650b7690a81a", "rated_matches": 54, "raw_elo_rating": 1439.4942097257222, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 26.304012940866215, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 27, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 27, "generated_at": "2026-07-02T16:51:45Z", "losses": 14, "model": "gpt-4.1", "point_rating_method": "sequential_elo", "public_id": "E-eabc996d553eebe0", "rated_matches": 48, "raw_elo_rating": 1418.016037894468, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 22.47989431367969, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 49, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 49, "generated_at": "2026-07-02T16:51:45Z", "losses": 11, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-95f891d54f35bb4a", "rated_matches": 70, "raw_elo_rating": 1454.9766570016957, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 29.70399047704974, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 34, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 34, "generated_at": "2026-07-02T06:10:40Z", "losses": 25, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-00b5df785d927901", "rated_matches": 70, "raw_elo_rating": 1437.1119892602044, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 26.93645966720522, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 44, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 44, "generated_at": "2026-07-01T00:15:48Z", "losses": 9, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-7ff0b78720f446ad", "rated_matches": 56, "raw_elo_rating": 1443.119426246869, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 27.01351650590875, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 53, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 53, "generated_at": "2026-07-02T16:51:45Z", "losses": 5, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-bb8ac98c284a38ce", "rated_matches": 58, "raw_elo_rating": 1444.9709152618298, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 27.44065505559449, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 63, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 63, "generated_at": "2026-07-09T17:30:50Z", "losses": 9, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-024aff0a983df40d", "rated_matches": 72, "raw_elo_rating": 1409.60538534671, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 22.776674828792995, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 58, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 58, "generated_at": "2026-07-02T06:10:40Z", "losses": 4, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-814593575d73a7cd", "rated_matches": 62, "raw_elo_rating": 1433.2979485120743, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 25.892626856177163, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 48, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 48, "generated_at": "2026-07-01T00:15:48Z", "losses": 10, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-c320ceaf4558afab", "rated_matches": 62, "raw_elo_rating": 1459.2786323344658, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 29.91746202130612, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 3, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 3, "generated_at": "2026-07-02T16:51:45Z", "losses": 23, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-fd5a36e5fd795426", "rated_matches": 66, "raw_elo_rating": 1592.0368931255489, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 50.72053236540851, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 40 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 45, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 45, "generated_at": "2026-07-02T16:51:45Z", "losses": 8, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-c42fbee03a029c83", "rated_matches": 56, "raw_elo_rating": 1448.3295730196996, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 27.82065391961682, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 50, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 50, "generated_at": "2026-07-10T05:30:29Z", "losses": 7, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-8feb37d0677409f2", "rated_matches": 58, "raw_elo_rating": 1441.8619859707171, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 26.959030783411738, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 5, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 5, "generated_at": "2026-07-10T05:30:29Z", "losses": 21, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-994624d0bc2e266d", "rated_matches": 58, "raw_elo_rating": 1522.545055470742, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 39.45816504693588, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 53, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 53, "generated_at": "2026-07-10T05:30:29Z", "losses": 9, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-44cace55a6126cdf", "rated_matches": 66, "raw_elo_rating": 1449.6896851314627, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 28.668609009228703, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 54, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 54, "generated_at": "2026-07-24T13:40:00Z", "losses": 12, "model": "inclusionai/ling-3.0-flash", "point_rating_method": "sequential_elo", "public_id": "E-11d1ae7d9526f835", "rated_matches": 66, "raw_elo_rating": 1417.6213892585145, "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": 23.700702629337265, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 57, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 57, "generated_at": "2026-07-24T13:40:00Z", "losses": 11, "model": "inclusionai/ling-3.0-flash", "point_rating_method": "sequential_elo", "public_id": "E-28bcc8394e411616", "rated_matches": 72, "raw_elo_rating": 1423.9891223360928, "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": 25.00495222274436, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 55, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 55, "generated_at": "2026-07-24T13:40:00Z", "losses": 7, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-87d69837bf65e78b", "rated_matches": 66, "raw_elo_rating": 1421.9008639632525, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 24.36366363520058, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 56, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 56, "generated_at": "2026-07-24T13:40:00Z", "losses": 8, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-df8e0fab4bf8bb33", "rated_matches": 70, "raw_elo_rating": 1432.31833577945, "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": 26.193843913490717, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 7, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 7, "generated_at": "2026-07-02T16:51:45Z", "losses": 33, "model": "minimax/minimax-m3", "point_rating_method": "sequential_elo", "public_id": "E-e67e41d4491d7ad3", "rated_matches": 66, "raw_elo_rating": 1499.683273236858, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 36.413437929557105, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 47, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 47, "generated_at": "2026-07-02T16:51:45Z", "losses": 5, "model": "mistralai/mistral-medium-3-5", "point_rating_method": "sequential_elo", "public_id": "E-ba85be2fa53925f5", "rated_matches": 52, "raw_elo_rating": 1438.2888976809872, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 25.961097857676517, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 0, "generated_at": "2026-07-24T14:00:00Z", "losses": 1, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-3e1be56b9d966ded", "rated_matches": 36, "raw_elo_rating": 1792.9886993624134, "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": 79.23445145680559, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 35 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 11, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 11, "generated_at": "2026-07-21T14:20:15Z", "losses": 15, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-b88e77144afeb8fd", "rated_matches": 36, "raw_elo_rating": 1491.071352291259, "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": 32.46248949608453, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 48, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 48, "generated_at": "2026-07-11T17:22:09Z", "losses": 7, "model": "nex-agi/nex-n2-pro", "point_rating_method": "sequential_elo", "public_id": "E-506d972b5c69a00d", "rated_matches": 56, "raw_elo_rating": 1440.8610223975368, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 26.6636526111786, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 38, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 38, "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": 44, "raw_elo_rating": 1452.3898563879034, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 27.41990029819383, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 15, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 15, "generated_at": "2026-07-21T14:20:15Z", "losses": 13, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-cbb72b5e25b55cee", "rated_matches": 36, "raw_elo_rating": 1491.6615321357433, "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": 32.55391805924589, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 30, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 30, "generated_at": "2026-07-21T14:20:15Z", "losses": 4, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-f6e9da46c61ad315", "rated_matches": 36, "raw_elo_rating": 1440.4422887134535, "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": 24.61921497496216, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 60, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 60, "generated_at": "2026-07-24T13:40:00Z", "losses": 9, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-4030acdbccf3ca03", "rated_matches": 70, "raw_elo_rating": 1418.1879120868175, "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": 24.00480891483295, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 53, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 53, "generated_at": "2026-07-24T13:40:00Z", "losses": 14, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-e90a3ce84847ba43", "rated_matches": 70, "raw_elo_rating": 1414.5541574282531, "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": 23.441880562707087, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 47, "coverage_status": "rated", "distinct_rated_opponents": 37, "draws": 47, "generated_at": "2026-07-02T16:51:45Z", "losses": 22, "model": "qwen/qwen3.7-max", "point_rating_method": "sequential_elo", "public_id": "E-a667eb7d15f7f43e", "rated_matches": 74, "raw_elo_rating": 1456.5863157614344, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 30.15214880984472, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 28, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 28, "generated_at": "2026-07-21T14:20:15Z", "losses": 8, "model": "stepfun/step-3.7-flash", "point_rating_method": "sequential_elo", "public_id": "E-c38fe2712e69333b", "rated_matches": 36, "raw_elo_rating": 1405.73919833146, "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": 19.24313559757037, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 80, "capped_draws": 65, "coverage_status": "rated", "distinct_rated_opponents": 40, "draws": 65, "generated_at": "2026-07-02T16:51:45Z", "losses": 14, "model": "tencent/hy3-preview", "point_rating_method": "sequential_elo", "public_id": "E-56487337fad4192f", "rated_matches": 80, "raw_elo_rating": 1450.2389966102576, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 29.438953458145875, "uncertainty": 11.805555555555554, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 1, "generated_at": "2026-07-24T13:40:00Z", "losses": 38, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-68669040dc891a7d", "rated_matches": 68, "raw_elo_rating": 1637.7826189897944, "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": 57.91782061761204, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 1, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 1, "generated_at": "2026-07-21T14:20:15Z", "losses": 7, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-71860dfe49537041", "rated_matches": 36, "raw_elo_rating": 1693.453686427907, "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": 63.81484114327353, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 0, "generated_at": "2026-07-24T14:00:00Z", "losses": 7, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-b914d026c7631fcb", "rated_matches": 36, "raw_elo_rating": 1723.196572871152, "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": 68.42250336215771, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 45, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 45, "generated_at": "2026-07-02T16:51:45Z", "losses": 15, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-cabbf604f15eb575", "rated_matches": 62, "raw_elo_rating": 1374.319686659771, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 16.755924223402463, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 52, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 52, "generated_at": "2026-07-01T00:15:48Z", "losses": 6, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-d51fce0298267f96", "rated_matches": 58, "raw_elo_rating": 1444.0676433143008, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 27.30072337700811, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 37, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 37, "generated_at": "2026-07-11T14:00:45Z", "losses": 5, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-6a361d88d8c1fb48", "rated_matches": 44, "raw_elo_rating": 1467.5919279050256, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 29.77495116764729, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 15, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-97efd9455394f6d7", "rated_matches": 44, "raw_elo_rating": 1607.1365868151802, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 51.39271358402592, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 3, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 3, "generated_at": "2026-07-02T06:10:40Z", "losses": 17, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-b87c8a15936f0f63", "rated_matches": 44, "raw_elo_rating": 1535.0704831205398, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 40.22848902600901, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 24 } ] }, "full_freedom/intensive": { "GB2-01": [ { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 0, "generated_at": "2026-07-03T17:50:00Z", "losses": 22, "model": "claude-fable-5", "point_rating_method": "sequential_elo", "public_id": "E-8000131e469a8bb6", "rated_matches": 56, "raw_elo_rating": 1623.2307722548098, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 63.53247225350247, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 6, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 6, "generated_at": "2026-07-03T17:20:00Z", "losses": 19, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-3308d2952452916e", "rated_matches": 58, "raw_elo_rating": 1594.7574022863707, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 59.955367539088286, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 33 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 0, "generated_at": "2026-07-25T15:48:00Z", "losses": 9, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-700f3dddd611df07", "rated_matches": 40, "raw_elo_rating": 1805.259587968875, "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": 85.92088891471201, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 31 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 0, "generated_at": "2026-07-25T15:48:00Z", "losses": 21, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-bf06fe9df8858291", "rated_matches": 40, "raw_elo_rating": 1471.5263340702886, "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": 42.616536692597606, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 76, "capped_draws": 14, "coverage_status": "rated", "distinct_rated_opponents": 38, "draws": 14, "generated_at": "2026-07-03T16:50:00Z", "losses": 19, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-5e353d79b07fa294", "rated_matches": 76, "raw_elo_rating": 1579.7115495088487, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 58.84535558133786, "uncertainty": 13.230288229818967, "unilateral_faults": 0, "wins": 43 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 18, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 18, "generated_at": "2026-07-02T16:51:45Z", "losses": 28, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-b9882650a0cde9ac", "rated_matches": 62, "raw_elo_rating": 1398.523019485064, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 34.71053990472652, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 12, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 12, "generated_at": "2026-07-02T06:10:40Z", "losses": 25, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-cb8739e00cafec5b", "rated_matches": 60, "raw_elo_rating": 1502.4012326532502, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 48.08316982071216, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 12, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 12, "generated_at": "2026-07-02T16:51:45Z", "losses": 22, "model": "deepseek/deepseek-v4-pro", "point_rating_method": "sequential_elo", "public_id": "E-e192048d4eaa3c43", "rated_matches": 62, "raw_elo_rating": 1481.3892527994904, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 45.46304512513314, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-3ade0bdbb45d890e", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-401e0639de33ca9e", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-e9260a0da3a64563", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 7, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 7, "generated_at": "2026-07-02T16:51:45Z", "losses": 17, "model": "gpt-5", "point_rating_method": "sequential_elo", "public_id": "E-3e63b136f656e976", "rated_matches": 38, "raw_elo_rating": 1501.6538251001646, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 46.32055634462709, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 2, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-5d8a6b14c27539ab", "rated_matches": 60, "raw_elo_rating": 1902.50819139413, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 100.0, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 58 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 4, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 4, "generated_at": "2026-07-02T06:10:40Z", "losses": 19, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-ca99b677101014a8", "rated_matches": 58, "raw_elo_rating": 1534.387956889026, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 52.12198654872786, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 35 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 31, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 31, "generated_at": "2026-07-09T17:30:50Z", "losses": 18, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-db1fc33e2a2467d5", "rated_matches": 58, "raw_elo_rating": 1423.3031461244054, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 37.70791268679307, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 7, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 7, "generated_at": "2026-07-02T06:10:40Z", "losses": 46, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-fbb3f2dccb7c7fba", "rated_matches": 60, "raw_elo_rating": 1251.7532336757345, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 15.559742488568526, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 19, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 19, "generated_at": "2026-07-02T16:51:45Z", "losses": 12, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-8c61292c31db2722", "rated_matches": 60, "raw_elo_rating": 1726.5259512130235, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 77.1650058104334, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 18, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-38187ed58fb76057", "rated_matches": 54, "raw_elo_rating": 1644.4759251533983, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 66.16530892077893, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 36 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 16, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-9e683b3cd6c7f7c3", "rated_matches": 58, "raw_elo_rating": 1715.0185204641425, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 75.5601349974072, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 42 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 12, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 12, "generated_at": "2026-07-10T05:30:29Z", "losses": 23, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-36d36f4895d90b11", "rated_matches": 54, "raw_elo_rating": 1472.4808055170065, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 43.84767304178936, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 4, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 4, "generated_at": "2026-07-02T16:51:45Z", "losses": 24, "model": "mistralai/mistral-medium-3-5", "point_rating_method": "sequential_elo", "public_id": "E-99c7b0d758665b66", "rated_matches": 32, "raw_elo_rating": 1298.4459745174713, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 19.228817981447683, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 1, "generated_at": "2026-07-17T22:36:00Z", "losses": 22, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-c89e5a24623ed70c", "rated_matches": 46, "raw_elo_rating": 1534.568054263408, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "score": 51.331720665259695, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 16, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 16, "generated_at": "2026-07-17T22:36:00Z", "losses": 13, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-d2f6679f6ac952b3", "rated_matches": 42, "raw_elo_rating": 1488.9186014394677, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "score": 45.064065005716344, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 5, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 5, "generated_at": "2026-07-24T14:00:00Z", "losses": 16, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-dbb89dcf5242a5a0", "rated_matches": 40, "raw_elo_rating": 1522.6758079990068, "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": 49.25355835319051, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 7, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 7, "generated_at": "2026-07-11T17:22:09Z", "losses": 20, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-ce064a9927030b28", "rated_matches": 32, "raw_elo_rating": 1351.452075561629, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 26.106750709825747, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 1, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 1, "generated_at": "2026-07-02T16:51:45Z", "losses": 28, "model": "stepfun/step-3.7-flash", "point_rating_method": "sequential_elo", "public_id": "E-4b0ce2bc67b08d8a", "rated_matches": 32, "raw_elo_rating": 1255.183036226893, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 13.615132512548884, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 4, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 4, "generated_at": "2026-07-02T16:51:45Z", "losses": 19, "model": "tencent/hy3-preview", "point_rating_method": "sequential_elo", "public_id": "E-29e8870e43d717e5", "rated_matches": 38, "raw_elo_rating": 1536.6261809793127, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 50.85847757164384, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 5, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 5, "generated_at": "2026-07-17T22:36:00Z", "losses": 8, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-098480b7039ef18d", "rated_matches": 32, "raw_elo_rating": 1626.3766914348796, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 61.78024821487967, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 8, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 8, "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": 32, "raw_elo_rating": 1671.8403327933106, "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": 67.67949114523401, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 3, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 3, "generated_at": "2026-07-17T22:36:00Z", "losses": 14, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-f9b8636a677996e4", "rated_matches": 34, "raw_elo_rating": 1582.2881600523183, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 56.321380026095234, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 31, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 31, "generated_at": "2026-07-02T06:10:40Z", "losses": 11, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-8478c64d84536b61", "rated_matches": 42, "raw_elo_rating": 1308.1269234889603, "reasoning": "highest", "reasoning_bracket": "highest", "reasoning_setting": "highest", "repair_status": "repaired", "score": 21.605010778009973, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 34, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 34, "generated_at": "2026-07-11T14:00:45Z", "losses": 11, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-5ab5088af70c19d6", "rated_matches": 58, "raw_elo_rating": 1469.3129924928696, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 43.678029747500474, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 34, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 34, "generated_at": "2026-07-03T18:27:00Z", "losses": 17, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-88bed07a2e526eed", "rated_matches": 62, "raw_elo_rating": 1527.2478732087454, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 51.413539501777066, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 11 } ], "GB2-02": [ { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 26, "generated_at": "2026-07-03T17:50:00Z", "losses": 3, "model": "claude-fable-5", "point_rating_method": "sequential_elo", "public_id": "E-f6a30e7d9986c9b8", "rated_matches": 58, "raw_elo_rating": 1659.3993318565135, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 71.95778371836957, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 20, "generated_at": "2026-07-03T17:20:00Z", "losses": 3, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-a81bd03e764818f6", "rated_matches": 58, "raw_elo_rating": 1735.4526025988669, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 90.13059941166075, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 35 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 12, "generated_at": "2026-07-25T15:48:01Z", "losses": 7, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-6b45cf5aebf0c66e", "rated_matches": 40, "raw_elo_rating": 1653.9188004065568, "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": 68.16460233811627, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 7, "generated_at": "2026-07-25T15:48:01Z", "losses": 7, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-fcdd98d74e80134a", "rated_matches": 40, "raw_elo_rating": 1741.313699122259, "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": 89.04748313195766, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 39, "generated_at": "2026-07-03T16:50:00Z", "losses": 10, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-e35d82f3fd09a1f4", "rated_matches": 56, "raw_elo_rating": 1527.5674418666176, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 40.24032728154734, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 52, "generated_at": "2026-07-02T16:51:45Z", "losses": 2, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-12dcb25370550495", "rated_matches": 58, "raw_elo_rating": 1477.211294899079, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 28.424223822355827, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 52, "generated_at": "2026-07-02T06:10:40Z", "losses": 6, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-f2e6dd87c5656ee3", "rated_matches": 60, "raw_elo_rating": 1491.731421574102, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 32.099476295000294, "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, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-939a2dc80becc700", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-a3da6c33bd873fb7", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 25, "generated_at": "2026-07-02T16:51:45Z", "losses": 9, "model": "gpt-5", "point_rating_method": "sequential_elo", "public_id": "E-5bccb9b671ce5eae", "rated_matches": 38, "raw_elo_rating": 1486.0056946936531, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 27.664057565565336, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 37, "generated_at": "2026-07-02T16:51:45Z", "losses": 7, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-4aa582caf9d9f6da", "rated_matches": 64, "raw_elo_rating": 1595.2075134501106, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 57.20745689293141, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 49, "generated_at": "2026-07-02T16:51:45Z", "losses": 5, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-59f362f57892ab54", "rated_matches": 56, "raw_elo_rating": 1487.0058745879062, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 30.548201233685464, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 56, "generated_at": "2026-07-02T06:10:40Z", "losses": 3, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-7ef67fa468b6c12c", "rated_matches": 60, "raw_elo_rating": 1475.998136939331, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 28.340031380574597, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 58, "generated_at": "2026-07-09T17:30:50Z", "losses": 4, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-1ce420518fc32de1", "rated_matches": 62, "raw_elo_rating": 1469.6780915147815, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 27.025681598377982, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 37, "draws": 58, "generated_at": "2026-07-02T16:51:45Z", "losses": 10, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-b084ba147f956b49", "rated_matches": 74, "raw_elo_rating": 1491.998524626864, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 33.364429917630005, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 64, "generated_at": "2026-07-10T05:30:29Z", "losses": 6, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-a30e455ba172d80e", "rated_matches": 70, "raw_elo_rating": 1473.232701299803, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 28.573734971782702, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 11, "generated_at": "2026-07-10T05:30:29Z", "losses": 4, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-33dc9365cfacf9c0", "rated_matches": 58, "raw_elo_rating": 1776.7560641910516, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 100.0, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 43 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 37, "generated_at": "2026-07-10T05:30:29Z", "losses": 10, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-1b12482867c807c9", "rated_matches": 60, "raw_elo_rating": 1547.1720098303158, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 45.346922229587115, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 28, "generated_at": "2026-07-24T14:00:00Z", "losses": 8, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-1beeecccf3f2c84f", "rated_matches": 40, "raw_elo_rating": 1493.0455285004546, "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": 29.724173783368585, "uncertainty": 34.33688094430304, "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, "generated_at": "2026-07-18T00:14:00Z", "losses": 6, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-97d6a124a1509fc1", "rated_matches": 32, "raw_elo_rating": 1497.4506468576496, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "score": 29.065526728113745, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 30, "generated_at": "2026-07-17T22:36:00Z", "losses": 3, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-b0de9fa15f139d69", "rated_matches": 34, "raw_elo_rating": 1466.881464973261, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "score": 22.2434368915999, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 33, "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": 40, "raw_elo_rating": 1470.497735408151, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 24.3364122294304, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 29, "generated_at": "2026-07-11T17:22:09Z", "losses": 4, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-abd2cae3e3ff9bdb", "rated_matches": 34, "raw_elo_rating": 1473.2584552355572, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 23.76720921044226, "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": 28, "generated_at": "2026-07-02T16:51:45Z", "losses": 4, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-e5b4a3586049e1c9", "rated_matches": 32, "raw_elo_rating": 1451.3761190633325, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 18.05608698162218, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 27, "generated_at": "2026-07-02T16:51:45Z", "losses": 5, "model": "tencent/hy3-preview", "point_rating_method": "sequential_elo", "public_id": "E-fbf6af15f65f01d7", "rated_matches": 32, "raw_elo_rating": 1440.1843320024248, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 15.381826143775362, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-9468e854340a4e9b", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 16, "generated_at": "2026-07-24T14:00:00Z", "losses": 7, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-0576181f89efa7a7", "rated_matches": 32, "raw_elo_rating": 1529.6313657780952, "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": 36.75506155167247, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 23, "generated_at": "2026-07-17T22:36:00Z", "losses": 6, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-8728b59f87c3369e", "rated_matches": 34, "raw_elo_rating": 1498.4288375296255, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 29.781634545407535, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 33, "generated_at": "2026-07-02T06:10:40Z", "losses": 3, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-9077f1e8e006290b", "rated_matches": 38, "raw_elo_rating": 1483.571469812471, "reasoning": "highest", "reasoning_bracket": "highest", "reasoning_setting": "highest", "repair_status": "repaired", "score": 27.082403158201195, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 55, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 45, "generated_at": "2026-07-11T14:00:45Z", "losses": 7, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-4442c0e8a06187bf", "rated_matches": 55, "raw_elo_rating": 1482.9029089130715, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 29.455269920534768, "uncertainty": 23.065310478106092, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 56, "generated_at": "2026-07-02T16:51:45Z", "losses": 4, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-98394109d97d67ee", "rated_matches": 60, "raw_elo_rating": 1470.0478126035491, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 26.918210248965437, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 45, "generated_at": "2026-07-02T06:10:40Z", "losses": 8, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-dd5764d86cd88052", "rated_matches": 60, "raw_elo_rating": 1498.8427257391668, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 33.79871182648007, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 7 } ], "GB2-03": [ { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 20, "generated_at": "2026-07-03T17:50:00Z", "losses": 4, "model": "claude-fable-5", "point_rating_method": "sequential_elo", "public_id": "E-04fa5b762ca703f0", "rated_matches": 42, "raw_elo_rating": 1640.156750580333, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 69.09378758500024, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 1, "generated_at": "2026-07-25T15:48:00Z", "losses": 2, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-38759212c025e8eb", "rated_matches": 40, "raw_elo_rating": 1824.2382806143908, "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": 34.33688094430304, "unilateral_faults": 0, "wins": 37 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 0, "generated_at": "2026-07-25T15:48:00Z", "losses": 4, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-7caa6c5081d57676", "rated_matches": 40, "raw_elo_rating": 1812.5461454407864, "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": 98.02115581192106, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 36 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 1, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 18, "generated_at": "2026-07-19T15:25:00Z", "losses": 7, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-1c251b669239429c", "rated_matches": 38, "raw_elo_rating": 1577.5269529910452, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 57.97745068031415, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 3, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 10, "generated_at": "2026-07-03T16:50:00Z", "losses": 25, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-2e43b0d163a7f12d", "rated_matches": 38, "raw_elo_rating": 1321.905658074529, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 14.714632872946382, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 2, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 18, "generated_at": "2026-07-19T15:25:00Z", "losses": 12, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-d49e8df479ed0377", "rated_matches": 48, "raw_elo_rating": 1537.0474990137684, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 52.29569320842981, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 18, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 9, "draws": 13, "generated_at": "2026-07-02T16:51:45Z", "losses": 1, "model": "google/gemini-3.5-flash", "point_rating_method": "sequential_elo", "public_id": "E-46c3bb79de67d970", "rated_matches": 18, "raw_elo_rating": 1531.1346465855556, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 45.43509859730099, "uncertainty": 70.95786693528086, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-dc837629b72c2e03", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-e9957a543416b0ad", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-ed24a723621c4481", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 22, "capped_draws": 1, "coverage_status": "under_covered", "distinct_rated_opponents": 11, "draws": 7, "generated_at": "2026-07-02T16:51:45Z", "losses": 9, "model": "gpt-5", "point_rating_method": "sequential_elo", "public_id": "E-cc568b7069d5a0fd", "rated_matches": 21, "raw_elo_rating": 1451.3965923614944, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 33.03750091731303, "uncertainty": 62.850358177805205, "unilateral_faults": 1, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 7, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 14, "generated_at": "2026-07-02T16:51:45Z", "losses": 18, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-4b75acaf58f14113", "rated_matches": 44, "raw_elo_rating": 1458.1644256131383, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 38.52438727472494, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 3, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 13, "generated_at": "2026-07-02T06:10:40Z", "losses": 23, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-6c4158c55a35d268", "rated_matches": 48, "raw_elo_rating": 1425.7024844756863, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 33.451022699687655, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 2, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 20, "generated_at": "2026-07-02T16:51:45Z", "losses": 10, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-e53a932f820d9724", "rated_matches": 39, "raw_elo_rating": 1525.5179367164974, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 49.31150841617975, "uncertainty": 35.30694150420948, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 2, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 17, "generated_at": "2026-07-10T10:07:13Z", "losses": 20, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-3bca3b4e02f2acf9", "rated_matches": 46, "raw_elo_rating": 1409.5840570079213, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 30.519421112195783, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 3, "generated_at": "2026-07-10T05:30:29Z", "losses": 13, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-2ac4e83a1b9ba989", "rated_matches": 44, "raw_elo_rating": 1596.3466678596478, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 61.911144518391616, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 11, "generated_at": "2026-07-10T05:30:29Z", "losses": 13, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-39e763b7d49209b4", "rated_matches": 42, "raw_elo_rating": 1548.5258455371809, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 53.585646325873974, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 18, "capped_draws": 2, "coverage_status": "under_covered", "distinct_rated_opponents": 9, "draws": 9, "generated_at": "2026-07-24T14:00:00Z", "losses": 5, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-c0c60ca46f3ce498", "rated_matches": 18, "raw_elo_rating": 1496.1192712489474, "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": 39.50889513237049, "uncertainty": 70.95786693528086, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 16, "generated_at": "2026-07-19T14:50:00Z", "losses": 14, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-714519b339aeb2e2", "rated_matches": 50, "raw_elo_rating": 1550.5281831108805, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 54.7687692938897, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 7, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 22, "generated_at": "2026-07-11T15:43:48Z", "losses": 17, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-bd2653f21938737f", "rated_matches": 46, "raw_elo_rating": 1432.4628967056365, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 34.391567498941406, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 7 } ], "GB2-04": [ { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 9, "generated_at": "2026-07-03T17:50:00Z", "losses": 1, "model": "claude-fable-5", "point_rating_method": "sequential_elo", "public_id": "E-0ca15b39b465b370", "rated_matches": 56, "raw_elo_rating": 1821.193278726695, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 100.0, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 46 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 30, "generated_at": "2026-07-03T17:20:00Z", "losses": 10, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-6344242dae68be1b", "rated_matches": 66, "raw_elo_rating": 1579.7087489959974, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 52.71452593995635, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 10, "generated_at": "2026-07-25T15:48:00Z", "losses": 8, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-4c98514bdb0eaf10", "rated_matches": 40, "raw_elo_rating": 1641.4937123917894, "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": 62.31286376346142, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 22 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 10, "generated_at": "2026-07-25T15:48:00Z", "losses": 3, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-a02883202d334eec", "rated_matches": 40, "raw_elo_rating": 1753.0553776456218, "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": 84.5364965379449, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 27 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 43, "generated_at": "2026-07-03T16:50:00Z", "losses": 8, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-8e980ad934b3251e", "rated_matches": 62, "raw_elo_rating": 1533.6717755962163, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 43.23945167121127, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 22, "generated_at": "2026-07-02T16:51:45Z", "losses": 19, "model": "deepseek/deepseek-v4-pro", "point_rating_method": "sequential_elo", "public_id": "E-38bc194a470fbf62", "rated_matches": 48, "raw_elo_rating": 1440.733349521438, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 23.38150584800255, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 18, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 9, "draws": 14, "generated_at": "2026-07-02T16:51:45Z", "losses": 4, "model": "google/gemini-3.1-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-2be6f5c895691cb3", "rated_matches": 18, "raw_elo_rating": 1450.1042275565585, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 18.351071939009746, "uncertainty": 70.95786693528086, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 7, "generated_at": "2026-07-02T16:51:45Z", "losses": 16, "model": "google/gemini-3.5-flash", "point_rating_method": "sequential_elo", "public_id": "E-8e95359e4cbd1851", "rated_matches": 32, "raw_elo_rating": 1479.715243612519, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 28.659179057173933, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-6c734fef813f984b", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-d7f1cd65263dbed7", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-ccfb6c993d1622b0", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 28, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 14, "draws": 21, "generated_at": "2026-07-02T16:51:45Z", "losses": 5, "model": "gpt-5", "point_rating_method": "sequential_elo", "public_id": "E-7e3da77777a95e31", "rated_matches": 28, "raw_elo_rating": 1469.1198423892715, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 25.622803197560856, "uncertainty": 49.09766908852594, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 27, "generated_at": "2026-07-02T16:51:45Z", "losses": 13, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-9279285adff8ed29", "rated_matches": 68, "raw_elo_rating": 1617.3769690127422, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 60.360340816834494, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 36, "generated_at": "2026-07-02T06:10:40Z", "losses": 12, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-040a4b654fceeb0c", "rated_matches": 56, "raw_elo_rating": 1477.865432695363, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 31.60740336660926, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 15, "generated_at": "2026-07-09T17:30:50Z", "losses": 21, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-3403c285ceec6345", "rated_matches": 66, "raw_elo_rating": 1532.0327204441571, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 43.21722641263964, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 30 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 26, "generated_at": "2026-07-02T06:10:40Z", "losses": 22, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-bbf36865f2b7fe63", "rated_matches": 56, "raw_elo_rating": 1377.564471203454, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 11.626958201577812, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 40, "generated_at": "2026-07-02T16:51:45Z", "losses": 13, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-64bf5daf186f8119", "rated_matches": 64, "raw_elo_rating": 1470.1339268004403, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 30.738052083219, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 33, "generated_at": "2026-07-10T05:30:29Z", "losses": 15, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-e348813cda8b38b7", "rated_matches": 60, "raw_elo_rating": 1515.0969212350349, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 39.376003042374144, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 26, "generated_at": "2026-07-10T05:30:29Z", "losses": 2, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-270a233119b6cc62", "rated_matches": 54, "raw_elo_rating": 1653.7320041970793, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 66.45071005956129, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 27, "generated_at": "2026-07-10T05:30:29Z", "losses": 12, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-b85c80e7475ef9ec", "rated_matches": 58, "raw_elo_rating": 1560.7829388596697, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 48.305404528632984, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 30, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 15, "draws": 15, "generated_at": "2026-07-17T22:36:00Z", "losses": 7, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-2a7239d6b25916b0", "rated_matches": 30, "raw_elo_rating": 1533.727851065557, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "score": 38.97830256660651, "uncertainty": 46.05265101338746, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 11, "generated_at": "2026-07-24T14:00:00Z", "losses": 7, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-601725df2c678708", "rated_matches": 32, "raw_elo_rating": 1573.848549836008, "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": 47.41099693833408, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 8, "generated_at": "2026-07-17T22:36:00Z", "losses": 10, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-6f3da6d3b01bcfad", "rated_matches": 32, "raw_elo_rating": 1540.2303591629875, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "score": 40.71408790278068, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 26, "generated_at": "2026-07-11T17:22:09Z", "losses": 5, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-958dea26b779a042", "rated_matches": 32, "raw_elo_rating": 1453.741817911068, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 23.485144828023245, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 21, "generated_at": "2026-07-02T16:51:45Z", "losses": 9, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-3a27113d21c73b01", "rated_matches": 34, "raw_elo_rating": 1458.9537932238363, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 24.925535319735957, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 18, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 9, "draws": 11, "generated_at": "2026-07-02T16:51:45Z", "losses": 6, "model": "tencent/hy3-preview", "point_rating_method": "sequential_elo", "public_id": "E-51c104b34ef2a244", "rated_matches": 18, "raw_elo_rating": 1437.608554413027, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 15.86187235078222, "uncertainty": 70.95786693528086, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 14, "generated_at": "2026-07-24T14:00:00Z", "losses": 12, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-07caaa12175b0b3c", "rated_matches": 34, "raw_elo_rating": 1490.9811128639078, "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": 31.30553501598018, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 24, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 12, "draws": 15, "generated_at": "2026-07-17T22:36:00Z", "losses": 9, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-70da8ff73f18e636", "rated_matches": 24, "raw_elo_rating": 1401.3535350181637, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 10.983597639729526, "uncertainty": 56.25, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 20, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 10, "draws": 11, "generated_at": "2026-07-17T22:36:00Z", "losses": 6, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-dac812d348a29158", "rated_matches": 20, "raw_elo_rating": 1465.4677734092577, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 22.30383211035796, "uncertainty": 65.3589451179962, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 28, "generated_at": "2026-07-02T06:10:40Z", "losses": 6, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-f8929b12716a2221", "rated_matches": 38, "raw_elo_rating": 1495.7904116780787, "reasoning": "highest", "reasoning_bracket": "highest", "reasoning_setting": "highest", "repair_status": "repaired", "score": 32.97295544313002, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 80, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 40, "draws": 57, "generated_at": "2026-07-11T15:43:48Z", "losses": 12, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-6d59400949b2dde9", "rated_matches": 80, "raw_elo_rating": 1514.0198533112462, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 40.51012439121856, "uncertainty": 11.805555555555554, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 25, "generated_at": "2026-07-02T06:10:40Z", "losses": 16, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-f9359f32abb5e3c8", "rated_matches": 50, "raw_elo_rating": 1438.9648484544537, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 23.25464273450773, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 9 } ], "GB2-05": [ { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 8, "model": "claude-fable-5", "point_rating_method": "sequential_elo", "public_id": "E-5aa4402ccce7b855", "rated_matches": 64, "raw_elo_rating": 1895.2246300132751, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 92.451262399467, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 56 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 35, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-6774d700e60de31a", "rated_matches": 64, "raw_elo_rating": 1538.3667950040874, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 49.82574174672981, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 0, "generated_at": "2026-07-25T10:50:00Z", "losses": 0, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-3f3686d02d1503fa", "rated_matches": 40, "raw_elo_rating": 1971.2777366099735, "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": 34.33688094430304, "unilateral_faults": 0, "wins": 40 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 0, "generated_at": "2026-07-25T10:50:00Z", "losses": 12, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-a35dfc1adc62e4eb", "rated_matches": 40, "raw_elo_rating": 1739.552877541597, "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": 72.32121086617754, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 76, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 38, "draws": 0, "generated_at": "2026-07-03T16:50:00Z", "losses": 38, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-c902807aab849f31", "rated_matches": 76, "raw_elo_rating": 1549.2728597100909, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 51.609766414462925, "uncertainty": 13.230288229818967, "unilateral_faults": 0, "wins": 38 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 57, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-b306c8f5ffbbec38", "rated_matches": 70, "raw_elo_rating": 1284.9234124510494, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 19.808674799193287, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 29, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-b3d889b0631db85f", "rated_matches": 70, "raw_elo_rating": 1558.4723377992989, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 52.48321413406782, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 41 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 23, "model": "deepseek/deepseek-v4-pro", "point_rating_method": "sequential_elo", "public_id": "E-0ca4798825ceaccb", "rated_matches": 72, "raw_elo_rating": 1758.883007674556, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 76.49983872640665, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 49 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 34, "model": "google/gemini-3.1-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-a72dd193e1dc4331", "rated_matches": 38, "raw_elo_rating": 1230.2869285583215, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 11.30209542127282, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 18, "model": "google/gemini-3.5-flash", "point_rating_method": "sequential_elo", "public_id": "E-b50da126631c1ea1", "rated_matches": 38, "raw_elo_rating": 1495.28311322599, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 42.95503738948669, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-27023858537764ac", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-2aebd7296279d5e5", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-68cd3c6f37a30f06", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 14, "model": "gpt-5", "point_rating_method": "sequential_elo", "public_id": "E-c5ad048b6fb4e93d", "rated_matches": 38, "raw_elo_rating": 1612.8618408113805, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 56.99943823859395, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 4, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-f6403f7a30e19e82", "rated_matches": 64, "raw_elo_rating": 1931.051509970191, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 96.73066798261004, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 60 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 34, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-481582e8f8e3217e", "rated_matches": 64, "raw_elo_rating": 1546.876053971512, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 50.84214536260139, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 30 }, { "admitted_plugin_count": 1, "attempted_matches": 80, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 40, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 43, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-95d1a872f51b78e7", "rated_matches": 80, "raw_elo_rating": 1439.7622455160515, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 38.66521954952476, "uncertainty": 11.805555555555554, "unilateral_faults": 0, "wins": 37 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 35, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-54b9ca4996a5589d", "rated_matches": 69, "raw_elo_rating": 1568.89177719822, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 53.68742421303622, "uncertainty": 16.01143046671968, "unilateral_faults": 1, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 0, "generated_at": "2026-07-09T17:30:50Z", "losses": 23, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-b05a7e0987de9967", "rated_matches": 64, "raw_elo_rating": 1670.4608946585429, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 65.60395710462083, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 41 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 15, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-762e9d80a60b41ed", "rated_matches": 68, "raw_elo_rating": 1819.332270454036, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 83.56050300184323, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 53 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 31, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-25a83ddaeb1268a4", "rated_matches": 66, "raw_elo_rating": 1575.875340508706, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 54.39513803855472, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 35 }, { "admitted_plugin_count": 1, "attempted_matches": 76, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 38, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 21, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-af9c2c2998294ad0", "rated_matches": 76, "raw_elo_rating": 1721.279849578368, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 72.15544813911, "uncertainty": 13.230288229818967, "unilateral_faults": 0, "wins": 55 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 25, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-012ecb9ce0709c05", "rated_matches": 68, "raw_elo_rating": 1616.3524860198763, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 59.31522058212656, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 43 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 34, "model": "mistralai/mistral-medium-3-5", "point_rating_method": "sequential_elo", "public_id": "E-1954b83d439b455c", "rated_matches": 38, "raw_elo_rating": 1193.9561815045674, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 6.962504533968066, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 0, "generated_at": "2026-07-18T00:14:00Z", "losses": 27, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-288f9a63e6b6cae3", "rated_matches": 52, "raw_elo_rating": 1495.7378044213926, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "score": 44.09715494334264, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 0, "generated_at": "2026-07-17T22:08:39Z", "losses": 20, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-95ac38f534c0080f", "rated_matches": 45, "raw_elo_rating": 1510.0302066011964, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "score": 45.32266046602105, "uncertainty": 29.97097807744857, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 30, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-48ed5c5e00ef38fb", "rated_matches": 38, "raw_elo_rating": 1302.325804098009, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 19.906907410444493, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-11T17:22:09Z", "losses": 25, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-da3b98638ff53ea9", "rated_matches": 38, "raw_elo_rating": 1359.3589379658868, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 26.719331818929053, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 0, "generated_at": "2026-07-03T16:00:00Z", "losses": 25, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-4fc62dc65156d576", "rated_matches": 46, "raw_elo_rating": 1463.867990376425, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 39.884077549121216, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 22, "model": "stepfun/step-3.7-flash", "point_rating_method": "sequential_elo", "public_id": "E-358338a9fbdbcb6a", "rated_matches": 38, "raw_elo_rating": 1466.366711746241, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 39.50106623470973, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 0, "generated_at": "2026-07-03T19:10:00Z", "losses": 20, "model": "tencent/hy3-preview", "point_rating_method": "sequential_elo", "public_id": "E-92dc0ac61d798488", "rated_matches": 46, "raw_elo_rating": 1502.7156411525352, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 44.52430449110435, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-e9202aa1565d1c4e", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-18T00:06:00Z", "losses": 20, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-87d1c39ddc685d7b", "rated_matches": 38, "raw_elo_rating": 1525.5095353150684, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 46.56548629271222, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 0, "generated_at": "2026-07-18T00:06:00Z", "losses": 23, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-bd7fcc801178eba2", "rated_matches": 48, "raw_elo_rating": 1508.4017122615546, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 45.34719853580299, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 0, "generated_at": "2026-07-11T14:00:45Z", "losses": 40, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-235e4beedf22bc99", "rated_matches": 72, "raw_elo_rating": 1560.971808516761, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 52.859982516183955, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 39, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-503ecd021099d8f9", "rated_matches": 66, "raw_elo_rating": 1425.0310386049832, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 36.37727132706912, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 27 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 31, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-51c8f79c1671819e", "rated_matches": 72, "raw_elo_rating": 1572.3682314569317, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 54.22124858279859, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 41 } ], "GB2-06": [ { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 9, "generated_at": "2026-07-02T16:51:45Z", "losses": 11, "model": "claude-fable-5", "point_rating_method": "sequential_elo", "public_id": "E-499fbc92ee0778fb", "rated_matches": 58, "raw_elo_rating": 1703.812816431412, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 79.37424207225958, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 38 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 3, "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": 56, "raw_elo_rating": 1701.9160659633524, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 78.99935188287517, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 37 }, { "admitted_plugin_count": 1, "attempted_matches": 82, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 41, "draws": 10, "generated_at": "2026-07-03T16:50:00Z", "losses": 33, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-51f3682dc3b76107", "rated_matches": 82, "raw_elo_rating": 1510.098396671887, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 54.55378800839192, "uncertainty": 11.132129994845172, "unilateral_faults": 0, "wins": 39 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 46, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-5f5fd61f4544b8d7", "rated_matches": 66, "raw_elo_rating": 1325.6338857012756, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 29.214032099678494, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 41, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-f527097ad30176f4", "rated_matches": 58, "raw_elo_rating": 1343.8062559046955, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 31.215857213561456, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 2, "generated_at": "2026-07-02T16:51:45Z", "losses": 34, "model": "deepseek/deepseek-v4-pro", "point_rating_method": "sequential_elo", "public_id": "E-c9778645f1bbd12c", "rated_matches": 62, "raw_elo_rating": 1417.6969290178033, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 41.325050962101, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 35, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 30, "model": "google/gemini-3.1-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-6238c7d8dc9e77d9", "rated_matches": 35, "raw_elo_rating": 1272.8334742113475, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 19.769903428463778, "uncertainty": 39.583333333333336, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 6, "generated_at": "2026-07-02T16:51:45Z", "losses": 11, "model": "google/gemini-3.5-flash", "point_rating_method": "sequential_elo", "public_id": "E-5dcb27eaa0273049", "rated_matches": 36, "raw_elo_rating": 1611.2604574466968, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 65.16290957666871, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-48cc2611d5aa8816", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-9c3a169358692b43", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-280a7de63c992141", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-905531e52a8460f5", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 3, "generated_at": "2026-07-02T16:51:45Z", "losses": 15, "model": "gpt-5", "point_rating_method": "sequential_elo", "public_id": "E-1b082700b3692175", "rated_matches": 42, "raw_elo_rating": 1577.1374991955004, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 61.23502390233987, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 8, "generated_at": "2026-07-02T16:51:45Z", "losses": 9, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-6e5bbab022d4d9fa", "rated_matches": 54, "raw_elo_rating": 1777.2678447386463, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 88.95151331383552, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 37 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 8, "generated_at": "2026-07-02T06:10:40Z", "losses": 16, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-0b7e07d12feb8fb5", "rated_matches": 56, "raw_elo_rating": 1629.298913714669, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 69.28529344955604, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 39, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-eca073d7ce610515", "rated_matches": 62, "raw_elo_rating": 1446.9959798754076, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 45.24441000136599, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 5, "generated_at": "2026-07-02T06:10:40Z", "losses": 19, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-f9bb09fb2842dd1f", "rated_matches": 56, "raw_elo_rating": 1691.0689393099397, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 77.54832249268348, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 7, "generated_at": "2026-07-02T16:51:45Z", "losses": 20, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-4175a77ccf4c269b", "rated_matches": 64, "raw_elo_rating": 1710.4157199319804, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 80.58681788029159, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 37 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 13, "generated_at": "2026-07-10T05:30:29Z", "losses": 15, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-9eafeacabdedfdba", "rated_matches": 56, "raw_elo_rating": 1674.3560486853933, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 75.31262484978316, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 6, "generated_at": "2026-07-10T05:30:29Z", "losses": 21, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-eb315c759774ef38", "rated_matches": 56, "raw_elo_rating": 1674.4080128967423, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 75.31957614668558, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugin_count": 1, "attempted_matches": 78, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 39, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 29, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-e6571a10c1120fab", "rated_matches": 78, "raw_elo_rating": 1632.355051545612, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 70.76130982029495, "uncertainty": 12.5043950463012, "unilateral_faults": 0, "wins": 49 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 27, "model": "mistralai/mistral-medium-3-5", "point_rating_method": "sequential_elo", "public_id": "E-6c35f5ff426e7ada", "rated_matches": 34, "raw_elo_rating": 1300.921746746397, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 23.400792038637384, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 3, "generated_at": "2026-07-17T22:36:00Z", "losses": 8, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-026a38fa3b1622ee", "rated_matches": 36, "raw_elo_rating": 1660.204754074208, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "score": 71.71022990932427, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 3, "generated_at": "2026-07-17T22:36:00Z", "losses": 13, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-3f2124a8621f4c67", "rated_matches": 36, "raw_elo_rating": 1565.2453871015337, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "score": 59.00743434382783, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 35, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 2, "generated_at": "2026-07-11T17:22:09Z", "losses": 19, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-ba2fb1c121873708", "rated_matches": 35, "raw_elo_rating": 1440.5408052205207, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 42.20425623178018, "uncertainty": 39.583333333333336, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 4, "generated_at": "2026-07-03T16:00:00Z", "losses": 15, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-4162fe183e6383e1", "rated_matches": 36, "raw_elo_rating": 1472.1905548712289, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 46.55941001629329, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 2, "generated_at": "2026-07-02T16:51:45Z", "losses": 24, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-a97b527d9b41a80c", "rated_matches": 54, "raw_elo_rating": 1546.9530796525933, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 58.14211062009856, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 24, "model": "stepfun/step-3.7-flash", "point_rating_method": "sequential_elo", "public_id": "E-2d684425ca56be18", "rated_matches": 36, "raw_elo_rating": 1376.6840179889298, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 33.78341906498985, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 29, "model": "tencent/hy3-preview", "point_rating_method": "sequential_elo", "public_id": "E-3627e3dbf7a48738", "rated_matches": 34, "raw_elo_rating": 1262.482587295157, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 18.2587528719364, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-56e54327930d2f64", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 4, "generated_at": "2026-07-24T14:00:00Z", "losses": 21, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-5a1e23bce371a184", "rated_matches": 44, "raw_elo_rating": 1506.7109073693723, "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": 51.99739158842913, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 2, "generated_at": "2026-07-17T22:36:00Z", "losses": 23, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-5bedcf6c046c3b54", "rated_matches": 52, "raw_elo_rating": 1561.0529470310196, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 59.89338924507642, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 27 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 0, "generated_at": "2026-07-17T22:36:00Z", "losses": 21, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-cc9d4b5c56aea8b6", "rated_matches": 42, "raw_elo_rating": 1485.1406227167588, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 48.92852321863203, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 6, "generated_at": "2026-07-02T06:10:40Z", "losses": 18, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-51421c7ae2af8f7b", "rated_matches": 40, "raw_elo_rating": 1502.9248303375296, "reasoning": "highest", "reasoning_bracket": "highest", "reasoning_setting": "highest", "repair_status": "repaired", "score": 51.110878446006915, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 6, "generated_at": "2026-07-11T14:00:45Z", "losses": 17, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-f94d63d03c820dac", "rated_matches": 54, "raw_elo_rating": 1623.151639774578, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 68.3352570412757, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 31 } ], "GB2-07": [ { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 25, "model": "claude-fable-5", "point_rating_method": "sequential_elo", "public_id": "E-babd82321b910e7b", "rated_matches": 62, "raw_elo_rating": 1604.4884389644276, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 61.59421983387494, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 37 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 0, "generated_at": "2026-07-03T17:20:00Z", "losses": 20, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-5e09cecd1172d99b", "rated_matches": 54, "raw_elo_rating": 1620.9004693099198, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 63.275737183469275, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 0, "generated_at": "2026-07-25T10:50:00Z", "losses": 1, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-1e882072d8d97548", "rated_matches": 40, "raw_elo_rating": 1908.3795775583417, "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": 99.7174091533898, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 39 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 0, "generated_at": "2026-07-03T16:50:00Z", "losses": 39, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-2146a36b46e938d6", "rated_matches": 66, "raw_elo_rating": 1412.1255644657329, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 36.6633342427911, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 27 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 37, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-20285efe5ad468c1", "rated_matches": 64, "raw_elo_rating": 1415.1291155468884, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 36.958247328140686, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 27 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 25, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-ecf2a6ea6f9fe06c", "rated_matches": 60, "raw_elo_rating": 1614.4328114471043, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 62.78630181345937, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 35 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 36, "model": "deepseek/deepseek-v4-pro", "point_rating_method": "sequential_elo", "public_id": "E-f398fd6ac8c8bada", "rated_matches": 70, "raw_elo_rating": 1591.3212202571904, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 60.25603724598094, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 26, "model": "google/gemini-3.1-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-0d43f308cfa4da52", "rated_matches": 38, "raw_elo_rating": 1405.678612322642, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 33.83751705234364, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 20, "model": "google/gemini-3.5-flash", "point_rating_method": "sequential_elo", "public_id": "E-f7f306cca2bb9532", "rated_matches": 38, "raw_elo_rating": 1600.6146212924966, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 59.3041108443162, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-3e0523b11110a55d", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-82a1dfc4206e9ddd", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 21, "model": "gpt-5", "point_rating_method": "sequential_elo", "public_id": "E-15dad0db253c0497", "rated_matches": 46, "raw_elo_rating": 1534.7241252046786, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 51.4414648280507, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 6, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-80aa3ec3ac4ad97f", "rated_matches": 64, "raw_elo_rating": 1839.8110785855636, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 92.43903356479711, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 58 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 21, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-1b33882368041bb3", "rated_matches": 62, "raw_elo_rating": 1624.3020252285476, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 64.18268235353479, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 41 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 29, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-e453890c6dd35fa3", "rated_matches": 64, "raw_elo_rating": 1656.0079852411393, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 68.42685264118785, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 35 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 0, "generated_at": "2026-07-09T17:30:50Z", "losses": 32, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-b9e3f57bc887c6ae", "rated_matches": 66, "raw_elo_rating": 1613.0301221781451, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 62.90966394480689, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 39, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-e0e874b71d913c12", "rated_matches": 62, "raw_elo_rating": 1375.04515939356, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 31.619569024065452, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 8, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-6201278165db862a", "rated_matches": 66, "raw_elo_rating": 1810.7420076245985, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 88.73890042665397, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 58 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 21, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-73a7b73c1df452ad", "rated_matches": 54, "raw_elo_rating": 1626.8615300978795, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 64.05449486122448, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 33 }, { "admitted_plugin_count": 1, "attempted_matches": 78, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 39, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 28, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-1b522c9c14f3860c", "rated_matches": 78, "raw_elo_rating": 1544.0623728482103, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 54.40449302982698, "uncertainty": 12.5043950463012, "unilateral_faults": 0, "wins": 50 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 24, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-65bf9818e3e1b632", "rated_matches": 66, "raw_elo_rating": 1690.141060653709, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 72.98349769903467, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 42 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 38, "model": "mistralai/mistral-medium-3-5", "point_rating_method": "sequential_elo", "public_id": "E-d0d0df9d83b6e37e", "rated_matches": 38, "raw_elo_rating": 1159.7317422016708, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 1.7068241707303853, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 0, "generated_at": "2026-07-24T14:00:00Z", "losses": 22, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-1d1372c78963efdf", "rated_matches": 46, "raw_elo_rating": 1558.078983518453, "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": 54.49256191826528, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 0, "generated_at": "2026-07-17T22:36:00Z", "losses": 26, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-49105fbc7f72e6fe", "rated_matches": 52, "raw_elo_rating": 1541.5326452995262, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "score": 52.7753453034211, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 0, "generated_at": "2026-07-17T22:36:00Z", "losses": 15, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-77d9c422124dcbfe", "rated_matches": 42, "raw_elo_rating": 1514.214420946601, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "score": 48.41541451913415, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 27 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-03T16:00:00Z", "losses": 27, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-312d25e3a9eeeee3", "rated_matches": 38, "raw_elo_rating": 1346.88960039813, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 26.15727421765783, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 27, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-29bc7f4fdf0f7b14", "rated_matches": 38, "raw_elo_rating": 1341.589505961371, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 25.464865704765224, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 30, "model": "stepfun/step-3.7-flash", "point_rating_method": "sequential_elo", "public_id": "E-6a5e44fe2dde4257", "rated_matches": 38, "raw_elo_rating": 1290.3553975779018, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 18.771601420804853, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 27, "model": "tencent/hy3-preview", "point_rating_method": "sequential_elo", "public_id": "E-dfed1e345a939bcd", "rated_matches": 38, "raw_elo_rating": 1342.3629390250549, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 25.565907609553385, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-38e756fc6f3a2db6", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-17T22:36:00Z", "losses": 17, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-0929811cef80813b", "rated_matches": 38, "raw_elo_rating": 1479.193023754416, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 43.44149768005027, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 0, "generated_at": "2026-07-24T14:00:00Z", "losses": 25, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-436a3933a93e10cd", "rated_matches": 42, "raw_elo_rating": 1540.3467918300798, "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": 51.829368039715575, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-17T22:36:00Z", "losses": 13, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-8e7f3829f3e45642", "rated_matches": 38, "raw_elo_rating": 1680.1891759395735, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 69.69979335614812, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugin_count": 1, "attempted_matches": 76, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 38, "draws": 0, "generated_at": "2026-07-11T14:00:45Z", "losses": 28, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-c81741d135c9dc9c", "rated_matches": 76, "raw_elo_rating": 1580.6857304668326, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 59.113132316890294, "uncertainty": 13.230288229818967, "unilateral_faults": 0, "wins": 48 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 27, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-cb438d112c0ea172", "rated_matches": 60, "raw_elo_rating": 1542.4399698356713, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 53.38110026584942, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 33 }, { "admitted_plugin_count": 1, "attempted_matches": 78, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 39, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 37, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-d96269dd04d644e0", "rated_matches": 78, "raw_elo_rating": 1584.028671851824, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 59.62572181907002, "uncertainty": 12.5043950463012, "unilateral_faults": 0, "wins": 41 } ], "GB2-08": [ { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 1, "generated_at": "2026-07-02T16:51:45Z", "losses": 4, "model": "claude-fable-5", "point_rating_method": "sequential_elo", "public_id": "E-12891afa894223fd", "rated_matches": 66, "raw_elo_rating": 1910.1404215986424, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 100.0, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 61 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 0, "generated_at": "2026-07-03T17:20:00Z", "losses": 20, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-22dc6fe5ae5fb8b1", "rated_matches": 66, "raw_elo_rating": 1683.6684140637717, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 64.91576179922941, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 46 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 0, "generated_at": "2026-07-25T15:48:01Z", "losses": 10, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-a40851c4f03704e5", "rated_matches": 40, "raw_elo_rating": 1794.374151033846, "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": 79.95876977478349, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 30 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 0, "generated_at": "2026-07-25T15:48:01Z", "losses": 16, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-f5914ca845403384", "rated_matches": 40, "raw_elo_rating": 1577.758866326647, "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": 46.401500029537175, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugin_count": 1, "attempted_matches": 78, "capped_draws": 42, "coverage_status": "rated", "distinct_rated_opponents": 39, "draws": 42, "generated_at": "2026-07-03T16:50:00Z", "losses": 26, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-b5805acb90227d50", "rated_matches": 78, "raw_elo_rating": 1466.4677843586585, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 31.86645017234374, "uncertainty": 12.5043950463012, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 48, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 48, "generated_at": "2026-07-02T16:51:45Z", "losses": 14, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-a7310645c3b96434", "rated_matches": 66, "raw_elo_rating": 1432.8957272786026, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 26.06694876849134, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 54, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 54, "generated_at": "2026-07-02T16:51:45Z", "losses": 10, "model": "deepseek/deepseek-v4-pro", "point_rating_method": "sequential_elo", "public_id": "E-3a5b5c4507a989d3", "rated_matches": 70, "raw_elo_rating": 1442.2170907590032, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 27.727323840541924, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 29, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 29, "generated_at": "2026-07-02T16:51:45Z", "losses": 6, "model": "google/gemini-3.1-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-b335c9f92035f80b", "rated_matches": 38, "raw_elo_rating": 1424.7057372534773, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 22.446013309546696, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 25, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 25, "generated_at": "2026-07-02T16:51:45Z", "losses": 13, "model": "google/gemini-3.5-flash", "point_rating_method": "sequential_elo", "public_id": "E-fa332e578ae97122", "rated_matches": 38, "raw_elo_rating": 1374.610482889811, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 14.685434613954731, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-0d09401e4a31ea61", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-96566b3cf3a15c23", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-37e04d4125f1d7fa", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-ee7ca879a02fdaf7", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 27, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 27, "generated_at": "2026-07-02T16:51:45Z", "losses": 10, "model": "gpt-5", "point_rating_method": "sequential_elo", "public_id": "E-ebca8ea756b4a4ad", "rated_matches": 42, "raw_elo_rating": 1423.6771246206629, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 22.759443475663716, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 15, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 15, "generated_at": "2026-07-02T16:51:45Z", "losses": 28, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-ddc1f3e68bf1e74a", "rated_matches": 68, "raw_elo_rating": 1524.6754320667146, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 40.39565736475438, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 4, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 4, "generated_at": "2026-07-02T16:51:45Z", "losses": 30, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-1e5d07fc67fd8710", "rated_matches": 64, "raw_elo_rating": 1539.952499256562, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 42.53621759752361, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 30 }, { "admitted_plugin_count": 1, "attempted_matches": 80, "capped_draws": 48, "coverage_status": "rated", "distinct_rated_opponents": 40, "draws": 48, "generated_at": "2026-07-02T06:10:40Z", "losses": 20, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-b63acb1096519102", "rated_matches": 80, "raw_elo_rating": 1437.1977394594303, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 27.418648267683565, "uncertainty": 11.805555555555554, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 15, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-98e55f26cfe52488", "rated_matches": 70, "raw_elo_rating": 1747.046912507192, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 74.95047602311436, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 55 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 56, "coverage_status": "rated", "distinct_rated_opponents": 37, "draws": 56, "generated_at": "2026-07-02T06:10:40Z", "losses": 15, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-ba371b627387f273", "rated_matches": 74, "raw_elo_rating": 1434.4993035373657, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 26.73050740503117, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 47, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 47, "generated_at": "2026-07-09T17:30:50Z", "losses": 14, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-bb4437fab8180bfc", "rated_matches": 68, "raw_elo_rating": 1431.8775736806174, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 26.0197430803459, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 9, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 9, "generated_at": "2026-07-02T16:51:45Z", "losses": 16, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-3e859a6b27767128", "rated_matches": 68, "raw_elo_rating": 1686.9133200163933, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 65.52897413963234, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 43 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 5, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 5, "generated_at": "2026-07-10T05:30:29Z", "losses": 28, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-0fb7de4e8156a229", "rated_matches": 64, "raw_elo_rating": 1548.0692879399865, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 43.793641641644086, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 31 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 12, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 12, "generated_at": "2026-07-10T05:30:29Z", "losses": 32, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-3ae62f195160add3", "rated_matches": 64, "raw_elo_rating": 1370.0658232755432, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 16.21797777560009, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 9, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 9, "generated_at": "2026-07-10T05:30:29Z", "losses": 31, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-b061663dc342c859", "rated_matches": 66, "raw_elo_rating": 1541.4118035776828, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 42.877873486874975, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 25, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 25, "generated_at": "2026-07-18T00:14:00Z", "losses": 11, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-134262cb96978830", "rated_matches": 38, "raw_elo_rating": 1389.414900625589, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "score": 16.978882373434576, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 33, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 33, "generated_at": "2026-07-17T22:36:00Z", "losses": 14, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-b06cbc77b01de3b3", "rated_matches": 50, "raw_elo_rating": 1429.093839088688, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "score": 24.371339668629737, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 28, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 28, "generated_at": "2026-07-11T17:22:09Z", "losses": 10, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-2e3c01d0103fc439", "rated_matches": 42, "raw_elo_rating": 1438.8528329749015, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 25.11041025765575, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 28, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 28, "generated_at": "2026-07-02T16:51:45Z", "losses": 8, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-8c24e8bcbe9b1228", "rated_matches": 42, "raw_elo_rating": 1429.6542352216024, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 23.685396198732267, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 1, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 1, "generated_at": "2026-07-03T16:00:00Z", "losses": 15, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-1b6fc7dfefb8cea4", "rated_matches": 38, "raw_elo_rating": 1612.4707931407108, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 51.533908181121, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 22 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 32, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 32, "generated_at": "2026-07-02T16:51:45Z", "losses": 7, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-24a75273941e6ea3", "rated_matches": 44, "raw_elo_rating": 1439.7393158406376, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 25.460123534787694, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 28, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 28, "generated_at": "2026-07-02T16:51:45Z", "losses": 13, "model": "stepfun/step-3.7-flash", "point_rating_method": "sequential_elo", "public_id": "E-8b265019ada47f24", "rated_matches": 44, "raw_elo_rating": 1426.3919506761963, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 23.39239717920349, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 9, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 9, "generated_at": "2026-07-02T16:51:45Z", "losses": 22, "model": "tencent/hy3-preview", "point_rating_method": "sequential_elo", "public_id": "E-81a5e5ef15f371dc", "rated_matches": 46, "raw_elo_rating": 1431.9083099217262, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 24.445649616184685, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-d21921560d198b28", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-17T22:36:00Z", "losses": 13, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-1c7222840add0cf9", "rated_matches": 38, "raw_elo_rating": 1634.9673614218534, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 55.018996554146426, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-17T22:36:00Z", "losses": 10, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-60939cc4ea338b18", "rated_matches": 38, "raw_elo_rating": 1670.2667139146774, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 60.4874467377768, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-24T14:00:00Z", "losses": 4, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-707dd709e358a173", "rated_matches": 38, "raw_elo_rating": 1782.8058796629582, "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": 77.92161416979704, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 37, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 37, "generated_at": "2026-07-02T06:10:40Z", "losses": 5, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-5f664f9580459829", "rated_matches": 44, "raw_elo_rating": 1438.8587143860132, "reasoning": "highest", "reasoning_bracket": "highest", "reasoning_setting": "highest", "repair_status": "repaired", "score": 25.32370388835863, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 0, "generated_at": "2026-07-11T14:00:45Z", "losses": 23, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-907d60010bf80864", "rated_matches": 64, "raw_elo_rating": 1691.9955525601144, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 66.09018683609693, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 41 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 58, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 58, "generated_at": "2026-07-02T06:10:40Z", "losses": 14, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-9e8f3e43bfd2810e", "rated_matches": 72, "raw_elo_rating": 1402.0577696393814, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 21.607425038471657, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 30, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 30, "generated_at": "2026-07-02T16:51:45Z", "losses": 30, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-bc28f817090c9f60", "rated_matches": 62, "raw_elo_rating": 1308.0570686179608, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 6.490755028805242, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 2 } ] }, "full_freedom/mixed": { "GB2-01": [ { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 20, "model": "claude-fable-5", "point_rating_method": "sequential_elo", "public_id": "E-2dbc6efbd7db03b5", "rated_matches": 56, "raw_elo_rating": 1661.6976408495564, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 68.52383229044648, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 36 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 0, "generated_at": "2026-07-03T17:50:00Z", "losses": 22, "model": "claude-fable-5", "point_rating_method": "sequential_elo", "public_id": "E-8000131e469a8bb6", "rated_matches": 56, "raw_elo_rating": 1623.2307722548098, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 63.53247225350247, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 38, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 38, "generated_at": "2026-07-02T16:51:45Z", "losses": 8, "model": "claude-opus-4-5", "point_rating_method": "sequential_elo", "public_id": "E-2e3eca63f7980fac", "rated_matches": 56, "raw_elo_rating": 1445.0343615965558, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 40.41017310675189, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "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": "highest", "reasoning_policy_version": "legacy_reasoning_presets_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": 34, "capped_draws": 5, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 5, "losses": 14, "model": "claude-opus-4-5", "point_rating_method": "sequential_elo", "public_id": "E-5b675f86b98132f4", "rated_matches": 34, "raw_elo_rating": 1520.8126659647862, "reasoning": "legacy_shared_thinking_budget", "reasoning_bracket": "intensive", "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "legacy_shared_thinking_budget", "repair_status": "first_pass", "score": 48.34448105694433, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "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": "medium", "reasoning_policy_version": "legacy_reasoning_presets_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": 32, "capped_draws": 6, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 6, "losses": 12, "model": "claude-opus-4-5", "point_rating_method": "sequential_elo", "public_id": "E-829b603611fbdcef", "rated_matches": 32, "raw_elo_rating": 1537.4766861750218, "reasoning": "legacy_shared_thinking_budget", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "legacy_shared_thinking_budget", "repair_status": "first_pass", "score": 50.24481656295757, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 9, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 9, "generated_at": "2026-07-02T16:51:45Z", "losses": 23, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-13ec9509bc80f2bf", "rated_matches": 52, "raw_elo_rating": 1483.905475102522, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 45.19928208402567, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 6, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 6, "generated_at": "2026-07-03T17:20:00Z", "losses": 19, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-3308d2952452916e", "rated_matches": 58, "raw_elo_rating": 1594.7574022863707, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 59.955367539088286, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 33 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 14, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 14, "generated_at": "2026-07-02T16:51:45Z", "losses": 17, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-757a6149e87d8b53", "rated_matches": 54, "raw_elo_rating": 1577.025901566621, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 57.41317066463946, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 5, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 5, "generated_at": "2026-07-25T15:48:00Z", "losses": 16, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-0437af9582860271", "rated_matches": 50, "raw_elo_rating": 1554.5202933343148, "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": 54.2236275574193, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 34, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 34, "generated_at": "2026-07-25T15:48:00Z", "losses": 5, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-6c30dc38efb07e9e", "rated_matches": 50, "raw_elo_rating": 1537.6053460906055, "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": 52.028788341658505, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 0, "generated_at": "2026-07-25T15:48:00Z", "losses": 9, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-700f3dddd611df07", "rated_matches": 40, "raw_elo_rating": 1805.259587968875, "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": 85.92088891471201, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 31 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 10, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 10, "generated_at": "2026-07-25T15:48:00Z", "losses": 9, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-865d68ab219fd7ee", "rated_matches": 50, "raw_elo_rating": 1788.9102877159794, "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": 84.63745882976652, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 31 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 2, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 2, "generated_at": "2026-07-25T15:48:00Z", "losses": 18, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-93a6875407c22137", "rated_matches": 48, "raw_elo_rating": 1684.0720782689243, "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": 70.88708715244077, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 0, "generated_at": "2026-07-25T15:48:00Z", "losses": 21, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-bf06fe9df8858291", "rated_matches": 40, "raw_elo_rating": 1471.5263340702886, "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": 42.616536692597606, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 76, "capped_draws": 14, "coverage_status": "rated", "distinct_rated_opponents": 38, "draws": 14, "generated_at": "2026-07-03T16:50:00Z", "losses": 19, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-5e353d79b07fa294", "rated_matches": 76, "raw_elo_rating": 1579.7115495088487, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 58.84535558133786, "uncertainty": 13.230288229818967, "unilateral_faults": 0, "wins": 43 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 12, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 12, "generated_at": "2026-07-02T16:51:45Z", "losses": 9, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-73ff84eba4ec19cb", "rated_matches": 44, "raw_elo_rating": 1562.54730392307, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 54.79582315352283, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 7, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 7, "generated_at": "2026-07-02T16:51:45Z", "losses": 26, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-cd50a27a6bb44b58", "rated_matches": 60, "raw_elo_rating": 1450.988870016457, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 41.41203641046077, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 27 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 44, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 44, "generated_at": "2026-07-02T16:51:45Z", "losses": 11, "model": "cohere/north-mini-code", "point_rating_method": "sequential_elo", "public_id": "E-194759b182ce3244", "rated_matches": 68, "raw_elo_rating": 1469.458273446667, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 44.20568866165951, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 17, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 17, "generated_at": "2026-07-11T17:22:09Z", "losses": 44, "model": "cohere/north-mini-code", "point_rating_method": "sequential_elo", "public_id": "E-c309b463b29efb71", "rated_matches": 64, "raw_elo_rating": 1214.6977166091126, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 10.959238882028716, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 18, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 18, "generated_at": "2026-07-02T16:51:45Z", "losses": 28, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-b9882650a0cde9ac", "rated_matches": 62, "raw_elo_rating": 1398.523019485064, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 34.71053990472652, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 23, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 23, "generated_at": "2026-07-02T06:10:40Z", "losses": 21, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-c4c43ee3f29394f8", "rated_matches": 66, "raw_elo_rating": 1480.1694379737794, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 45.502967642683174, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 22 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 12, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 12, "generated_at": "2026-07-02T06:10:40Z", "losses": 25, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-cb8739e00cafec5b", "rated_matches": 60, "raw_elo_rating": 1502.4012326532502, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 48.08316982071216, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 20, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 20, "generated_at": "2026-07-02T06:10:40Z", "losses": 18, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-f1d9dfb787d0d902", "rated_matches": 42, "raw_elo_rating": 1354.422251343348, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 27.61217116800776, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 5, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 5, "generated_at": "2026-07-01T00:15:48Z", "losses": 19, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-fd9da5310ad15cac", "rated_matches": 42, "raw_elo_rating": 1603.5204746601908, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 59.934503672797355, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 27, "coverage_status": "rated", "distinct_rated_opponents": 37, "draws": 27, "generated_at": "2026-07-02T16:51:45Z", "losses": 24, "model": "deepseek/deepseek-v4-pro", "point_rating_method": "sequential_elo", "public_id": "E-e121525dd1846069", "rated_matches": 74, "raw_elo_rating": 1494.5716412258355, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 47.71947792576954, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 12, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 12, "generated_at": "2026-07-02T16:51:45Z", "losses": 22, "model": "deepseek/deepseek-v4-pro", "point_rating_method": "sequential_elo", "public_id": "E-e192048d4eaa3c43", "rated_matches": 62, "raw_elo_rating": 1481.3892527994904, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 45.46304512513314, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 29, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 29, "generated_at": "2026-07-02T16:51:45Z", "losses": 16, "model": "google/gemini-3.1-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-7669b8a03ef19548", "rated_matches": 58, "raw_elo_rating": 1458.4305805417964, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 42.26595649843005, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 23, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 23, "generated_at": "2026-07-02T16:51:45Z", "losses": 17, "model": "google/gemini-3.1-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-cc0af0bfa6a9a29f", "rated_matches": 46, "raw_elo_rating": 1340.1564195017108, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 26.105376543268523, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 0, "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": 56, "raw_elo_rating": 1819.728353888386, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 89.02948337376621, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 47 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "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": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-21c0edac8ac36f2e", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-3ade0bdbb45d890e", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-401e0639de33ca9e", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 20, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 20, "generated_at": "2026-07-24T13:40:00Z", "losses": 23, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-77d8df8cd762fd09", "rated_matches": 66, "raw_elo_rating": 1486.4532366607398, "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": 46.31833688879277, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-cf51875df5447bc2", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 11, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 11, "generated_at": "2026-07-24T13:40:00Z", "losses": 32, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-fc3c30006929710a", "rated_matches": 60, "raw_elo_rating": 1519.8637003276654, "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": 50.349053852364435, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 31, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 31, "generated_at": "2026-07-24T13:40:00Z", "losses": 18, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-4b36631072d1c39e", "rated_matches": 60, "raw_elo_rating": 1328.006075988608, "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": 25.454111428073276, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 2, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 2, "generated_at": "2026-07-24T13:40:00Z", "losses": 8, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-7484f4e7d8863a3b", "rated_matches": 60, "raw_elo_rating": 1834.1963383041368, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 91.13603300660792, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 50 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-e0c4f14c94c0a42a", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-e9260a0da3a64563", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-e9733de94d982ade", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 16, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 16, "generated_at": "2026-07-02T16:51:45Z", "losses": 17, "model": "google/gemma-4-31b-it", "point_rating_method": "sequential_elo", "public_id": "E-caaa54d3c88e6570", "rated_matches": 58, "raw_elo_rating": 1477.0492603937407, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 44.68186759149837, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 1, "generated_at": "2026-07-02T16:51:45Z", "losses": 22, "model": "gpt-4.1", "point_rating_method": "sequential_elo", "public_id": "E-f50ec6b60d5b85da", "rated_matches": 44, "raw_elo_rating": 1576.9979684590764, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 56.67090350467359, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 7, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 7, "generated_at": "2026-07-02T16:51:45Z", "losses": 17, "model": "gpt-5", "point_rating_method": "sequential_elo", "public_id": "E-3e63b136f656e976", "rated_matches": 38, "raw_elo_rating": 1501.6538251001646, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 46.32055634462709, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "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": 54, "capped_draws": 15, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 15, "generated_at": "2026-07-02T16:51:45Z", "losses": 25, "model": "gpt-5", "point_rating_method": "sequential_elo", "public_id": "E-adee794ecd761044", "rated_matches": 54, "raw_elo_rating": 1359.6393456579792, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 29.205660998009655, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 24, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 24, "generated_at": "2026-07-02T16:51:45Z", "losses": 11, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-586de6c9939561c3", "rated_matches": 58, "raw_elo_rating": 1653.411765004077, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 67.56620389662746, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 2, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-5d8a6b14c27539ab", "rated_matches": 60, "raw_elo_rating": 1902.50819139413, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 100.0, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 58 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 2, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 2, "generated_at": "2026-07-02T16:51:45Z", "losses": 6, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-60fa13e461853992", "rated_matches": 62, "raw_elo_rating": 1828.996677787992, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 90.56767341997636, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 54 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 19, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 19, "generated_at": "2026-07-01T00:15:48Z", "losses": 34, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-3834aa9e894c458b", "rated_matches": 62, "raw_elo_rating": 1301.9549941620744, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 22.18012606933584, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 5, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 5, "generated_at": "2026-07-02T16:51:45Z", "losses": 24, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-62424dfd649cbac9", "rated_matches": 60, "raw_elo_rating": 1586.2698676615937, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 58.96574405735956, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 31 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 16, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 16, "generated_at": "2026-07-01T00:15:48Z", "losses": 34, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-aa899d4eca8a2891", "rated_matches": 58, "raw_elo_rating": 1313.0379027856814, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 23.400183745738065, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 18, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 18, "generated_at": "2026-07-02T06:10:40Z", "losses": 32, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-b6ed01547d27188c", "rated_matches": 70, "raw_elo_rating": 1474.6255530349806, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 44.96481532557581, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 76, "capped_draws": 11, "coverage_status": "rated", "distinct_rated_opponents": 38, "draws": 11, "generated_at": "2026-07-02T06:10:40Z", "losses": 30, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-c675a6c67536654d", "rated_matches": 76, "raw_elo_rating": 1504.1241861334013, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 49.037337444355906, "uncertainty": 13.230288229818967, "unilateral_faults": 0, "wins": 35 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 4, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 4, "generated_at": "2026-07-02T06:10:40Z", "losses": 19, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-ca99b677101014a8", "rated_matches": 58, "raw_elo_rating": 1534.387956889026, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 52.12198654872786, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 35 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 28, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 28, "generated_at": "2026-07-02T16:51:45Z", "losses": 20, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-ea1cb793f92b3cff", "rated_matches": 64, "raw_elo_rating": 1438.6852463591326, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 40.02327361140479, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 17, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 17, "generated_at": "2026-07-02T06:10:40Z", "losses": 21, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-22c14c8deb751cb3", "rated_matches": 54, "raw_elo_rating": 1399.6655784138532, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 34.399360040992676, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 18, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 18, "generated_at": "2026-07-02T06:10:40Z", "losses": 35, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-5c28f8f5135ce060", "rated_matches": 72, "raw_elo_rating": 1403.576939064904, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 35.830699512360106, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 15, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 15, "generated_at": "2026-07-02T16:51:45Z", "losses": 26, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-9257cc1e94bf4b17", "rated_matches": 62, "raw_elo_rating": 1423.4427866640558, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 37.94406357252404, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 10, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 10, "generated_at": "2026-07-01T00:15:48Z", "losses": 45, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-98c36ba5e36ecf75", "rated_matches": 56, "raw_elo_rating": 1133.6056513286212, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 0.0, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 20, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 20, "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": 70, "raw_elo_rating": 1490.1659645875384, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 46.98129839307701, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 21, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 21, "generated_at": "2026-07-02T16:51:45Z", "losses": 25, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-a8887794a1195b75", "rated_matches": 60, "raw_elo_rating": 1522.347373894308, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 50.671328824001904, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 9, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 9, "generated_at": "2026-07-09T17:30:50Z", "losses": 46, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-c48c1aed1cdecc72", "rated_matches": 56, "raw_elo_rating": 1166.088389143785, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 4.214874912986324, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 31, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 31, "generated_at": "2026-07-09T17:30:50Z", "losses": 18, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-db1fc33e2a2467d5", "rated_matches": 58, "raw_elo_rating": 1423.3031461244054, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 37.70791268679307, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 17, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 17, "generated_at": "2026-07-01T00:15:48Z", "losses": 35, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-f491ad1b583dbcac", "rated_matches": 58, "raw_elo_rating": 1228.8312506207556, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 12.47374928888556, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 7, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 7, "generated_at": "2026-07-02T06:10:40Z", "losses": 46, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-fbb3f2dccb7c7fba", "rated_matches": 60, "raw_elo_rating": 1251.7532336757345, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 15.559742488568526, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 50, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 50, "generated_at": "2026-07-02T16:51:45Z", "losses": 9, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-58178b9b32a94ca0", "rated_matches": 66, "raw_elo_rating": 1489.9225771870858, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 46.76850942142567, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 19, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 19, "generated_at": "2026-07-02T16:51:45Z", "losses": 12, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-8c61292c31db2722", "rated_matches": 60, "raw_elo_rating": 1726.5259512130235, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 77.1650058104334, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 38, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 38, "generated_at": "2026-07-02T16:51:45Z", "losses": 3, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-e4496be687faac9d", "rated_matches": 56, "raw_elo_rating": 1578.7755636434526, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 57.76408091303755, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 18, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-38187ed58fb76057", "rated_matches": 54, "raw_elo_rating": 1644.4759251533983, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 66.16530892077893, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 36 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 8, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 8, "generated_at": "2026-07-10T05:30:29Z", "losses": 23, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-4f775a5b7b265dae", "rated_matches": 62, "raw_elo_rating": 1631.9779985185817, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 65.00304603642252, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 31 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 16, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 16, "generated_at": "2026-07-10T05:30:29Z", "losses": 31, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-959ed218b1c5605b", "rated_matches": 59, "raw_elo_rating": 1357.846690093915, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 29.271001037603703, "uncertainty": 20.79972243679028, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 15, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 15, "generated_at": "2026-07-10T05:30:29Z", "losses": 19, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-890c38b8e811c121", "rated_matches": 62, "raw_elo_rating": 1563.2313436316006, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 56.082660301584646, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 16, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-9e683b3cd6c7f7c3", "rated_matches": 58, "raw_elo_rating": 1715.0185204641425, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 75.5601349974072, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 42 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 25, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-bc834303cebba06a", "rated_matches": 54, "raw_elo_rating": 1589.1789388885927, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 58.990116931190066, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 12, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 12, "generated_at": "2026-07-10T05:30:29Z", "losses": 23, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-36d36f4895d90b11", "rated_matches": 54, "raw_elo_rating": 1472.4808055170065, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 43.84767304178936, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 18, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 18, "generated_at": "2026-07-10T05:30:29Z", "losses": 24, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-40742129939a44b5", "rated_matches": 60, "raw_elo_rating": 1564.6500398829733, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 56.16041187613398, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 20, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 20, "generated_at": "2026-07-10T05:30:29Z", "losses": 18, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-46de264ad4571b48", "rated_matches": 56, "raw_elo_rating": 1500.156493815032, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 47.5626764936281, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 22, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 22, "generated_at": "2026-07-24T13:40:00Z", "losses": 20, "model": "inclusionai/ling-3.0-flash", "point_rating_method": "sequential_elo", "public_id": "E-3c618b88b6bdb039", "rated_matches": 60, "raw_elo_rating": 1410.9705067906923, "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": 36.21935849707662, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "inclusionai/ling-3.0-flash", "point_rating_method": "sequential_elo", "public_id": "E-47f813dcedb11262", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 13, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 13, "generated_at": "2026-07-24T13:40:00Z", "losses": 33, "model": "inclusionai/ling-3.0-flash", "point_rating_method": "sequential_elo", "public_id": "E-f9af396559c3a1cd", "rated_matches": 64, "raw_elo_rating": 1531.3285214806754, "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": 52.04442214847159, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-5e8d45873865cc93", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 18, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 18, "generated_at": "2026-07-24T13:40:00Z", "losses": 23, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-9f5585b5fd96f2c3", "rated_matches": 62, "raw_elo_rating": 1501.8751700705743, "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": 48.12124405118231, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 23, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 23, "generated_at": "2026-07-24T13:40:00Z", "losses": 25, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-ed0f8e084958eebc", "rated_matches": 70, "raw_elo_rating": 1459.1960248159478, "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": 42.96272018877806, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 22 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 15, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 15, "generated_at": "2026-07-02T16:51:45Z", "losses": 23, "model": "minimax/minimax-m3", "point_rating_method": "sequential_elo", "public_id": "E-444510032bc433fc", "rated_matches": 70, "raw_elo_rating": 1497.3874694861893, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 47.91834193923778, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 1, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 1, "generated_at": "2026-07-02T16:51:45Z", "losses": 17, "model": "minimax/minimax-m3", "point_rating_method": "sequential_elo", "public_id": "E-e0a841a9daa66219", "rated_matches": 34, "raw_elo_rating": 1460.7073343854129, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 40.54537078329118, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 4, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 4, "generated_at": "2026-07-02T16:51:45Z", "losses": 24, "model": "mistralai/mistral-medium-3-5", "point_rating_method": "sequential_elo", "public_id": "E-99c7b0d758665b66", "rated_matches": 32, "raw_elo_rating": 1298.4459745174713, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 19.228817981447683, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 6, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 6, "generated_at": "2026-07-02T16:51:45Z", "losses": 37, "model": "mistralai/mistral-medium-3-5", "point_rating_method": "sequential_elo", "public_id": "E-a0a38f5e77e983bc", "rated_matches": 61, "raw_elo_rating": 1393.6204375879504, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 34.02186953365919, "uncertainty": 19.750063500095248, "unilateral_faults": 3, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 30, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 15, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 14, "model": "moonshotai/kimi-k2.7-code", "point_rating_method": "sequential_elo", "public_id": "E-4935e918b1e70ea1", "rated_matches": 30, "raw_elo_rating": 1510.1966215730497, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 46.4181257426225, "uncertainty": 46.05265101338746, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 5, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 5, "generated_at": "2026-07-21T14:20:15Z", "losses": 13, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-2292c77f8fb54ff1", "rated_matches": 38, "raw_elo_rating": 1583.3568125453553, "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": 56.92212183021899, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 30, "capped_draws": 19, "coverage_status": "under_covered", "distinct_rated_opponents": 15, "draws": 19, "generated_at": "2026-07-24T14:00:00Z", "losses": 6, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-6cc4477cf8936e55", "rated_matches": 30, "raw_elo_rating": 1505.7367507618944, "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": 45.83942459667651, "uncertainty": 46.05265101338746, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 1, "generated_at": "2026-07-17T22:36:00Z", "losses": 22, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-c89e5a24623ed70c", "rated_matches": 46, "raw_elo_rating": 1534.568054263408, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "score": 51.331720665259695, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 16, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 16, "generated_at": "2026-07-17T22:36:00Z", "losses": 13, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-d2f6679f6ac952b3", "rated_matches": 42, "raw_elo_rating": 1488.9186014394677, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "score": 45.064065005716344, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 5, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 5, "generated_at": "2026-07-24T14:00:00Z", "losses": 16, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-dbb89dcf5242a5a0", "rated_matches": 40, "raw_elo_rating": 1522.6758079990068, "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": 49.25355835319051, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 30, "capped_draws": 11, "coverage_status": "under_covered", "distinct_rated_opponents": 15, "draws": 11, "generated_at": "2026-07-21T14:43:57Z", "losses": 6, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-ee608da1db5fc482", "rated_matches": 30, "raw_elo_rating": 1590.2168161325296, "reasoning": "high", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 56.80133643441302, "uncertainty": 46.05265101338746, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 24, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 24, "generated_at": "2026-07-24T14:00:00Z", "losses": 5, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-fb8801908d28001f", "rated_matches": 38, "raw_elo_rating": 1564.779507444791, "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": 54.5115794164355, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 11, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 11, "generated_at": "2026-07-02T16:51:45Z", "losses": 17, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-0ce5e196701b51f3", "rated_matches": 44, "raw_elo_rating": 1551.1970854508706, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 53.32304855651662, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 14, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 14, "generated_at": "2026-07-02T16:51:45Z", "losses": 26, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-b851008baae8f441", "rated_matches": 64, "raw_elo_rating": 1508.9996053111847, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 49.14708051635627, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 7, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 7, "generated_at": "2026-07-11T17:22:09Z", "losses": 20, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-ce064a9927030b28", "rated_matches": 32, "raw_elo_rating": 1351.452075561629, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 26.106750709825747, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 7, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 7, "generated_at": "2026-07-02T16:51:45Z", "losses": 21, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-428923c2eb87dc7a", "rated_matches": 54, "raw_elo_rating": 1521.3936825716696, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 50.19447975472116, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 7, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 7, "generated_at": "2026-07-21T14:20:15Z", "losses": 15, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-fbf1a1af436a64a7", "rated_matches": 38, "raw_elo_rating": 1483.123014784552, "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": 43.91604697226371, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 11, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 11, "generated_at": "2026-07-21T14:20:15Z", "losses": 15, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-55f6c0e3dc8a8065", "rated_matches": 38, "raw_elo_rating": 1413.0817228894214, "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": 34.827672532836864, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 18, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 18, "generated_at": "2026-07-02T16:51:45Z", "losses": 22, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-a3e0c8f8ea39b5ec", "rated_matches": 56, "raw_elo_rating": 1406.1009817298916, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 35.358279790014166, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 7, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 7, "generated_at": "2026-07-24T13:40:00Z", "losses": 29, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-8461eb1b16e40129", "rated_matches": 66, "raw_elo_rating": 1645.1563970303832, "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": 66.9112429750953, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 30 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 22, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 22, "generated_at": "2026-07-24T13:40:00Z", "losses": 24, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-c58ec61528547516", "rated_matches": 68, "raw_elo_rating": 1512.7646082145152, "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": 49.825005143695144, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 22 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-ffd72d2c5c11728a", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 30, "capped_draws": 7, "coverage_status": "under_covered", "distinct_rated_opponents": 15, "draws": 7, "generated_at": "2026-07-02T16:51:45Z", "losses": 14, "model": "qwen/qwen3.7-max", "point_rating_method": "sequential_elo", "public_id": "E-24581eb49b81bf8f", "rated_matches": 30, "raw_elo_rating": 1452.8629061397091, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 38.978653114934275, "uncertainty": 46.05265101338746, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 17, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 17, "generated_at": "2026-07-02T16:51:45Z", "losses": 18, "model": "qwen/qwen3.7-max", "point_rating_method": "sequential_elo", "public_id": "E-8a70cd704fcbcf6f", "rated_matches": 64, "raw_elo_rating": 1582.8274794165334, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 58.72679193774028, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 3, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 3, "generated_at": "2026-07-02T16:51:45Z", "losses": 18, "model": "qwen/qwen3.7-plus", "point_rating_method": "sequential_elo", "public_id": "E-1e5dceaf2ba3ca9a", "rated_matches": 40, "raw_elo_rating": 1493.5331251706154, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 45.47208022011386, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 18, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 18, "generated_at": "2026-07-03T18:55:00Z", "losses": 32, "model": "qwen/qwen3.7-plus", "point_rating_method": "sequential_elo", "public_id": "E-5e09f0c994a59f3c", "rated_matches": 66, "raw_elo_rating": 1378.486150271109, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 32.3088107693705, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 13, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 13, "generated_at": "2026-07-21T14:20:15Z", "losses": 25, "model": "stepfun/step-3.7-flash", "point_rating_method": "sequential_elo", "public_id": "E-09ecaa63c419b917", "rated_matches": 56, "raw_elo_rating": 1479.5735802409645, "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": 44.89189158155693, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 1, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 1, "generated_at": "2026-07-02T16:51:45Z", "losses": 28, "model": "stepfun/step-3.7-flash", "point_rating_method": "sequential_elo", "public_id": "E-4b0ce2bc67b08d8a", "rated_matches": 32, "raw_elo_rating": 1255.183036226893, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 13.615132512548884, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 4, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 4, "generated_at": "2026-07-02T16:51:45Z", "losses": 19, "model": "tencent/hy3-preview", "point_rating_method": "sequential_elo", "public_id": "E-29e8870e43d717e5", "rated_matches": 38, "raw_elo_rating": 1536.6261809793127, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 50.85847757164384, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 15, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 15, "generated_at": "2026-07-02T16:51:45Z", "losses": 15, "model": "tencent/hy3-preview", "point_rating_method": "sequential_elo", "public_id": "E-3407ff2dd1928eb5", "rated_matches": 72, "raw_elo_rating": 1676.59501851212, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 71.25680984831166, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 42 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 13, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 13, "generated_at": "2026-07-24T13:40:00Z", "losses": 22, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-7382cf954e1b755d", "rated_matches": 62, "raw_elo_rating": 1458.1859571349817, "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": 42.45224630172584, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 27 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 33, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 33, "generated_at": "2026-07-24T13:40:00Z", "losses": 24, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-9e638fc0ac98df4f", "rated_matches": 62, "raw_elo_rating": 1356.7506640572788, "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": 29.29026856088901, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 24, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 24, "generated_at": "2026-07-24T13:40:00Z", "losses": 26, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-bc7c657b08ebac66", "rated_matches": 60, "raw_elo_rating": 1308.7036654237002, "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": 22.949481229931152, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 20, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 20, "generated_at": "2026-07-24T13:40:00Z", "losses": 27, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-c9890f6abafaf54f", "rated_matches": 60, "raw_elo_rating": 1303.8451033164808, "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": 22.319046946483994, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 5, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 5, "generated_at": "2026-07-17T22:36:00Z", "losses": 8, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-098480b7039ef18d", "rated_matches": 32, "raw_elo_rating": 1626.3766914348796, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 61.78024821487967, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 8, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 8, "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": 32, "raw_elo_rating": 1671.8403327933106, "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": 67.67949114523401, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 23, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 23, "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": 38, "raw_elo_rating": 1547.678016157504, "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": 52.29253473456167, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 76, "capped_draws": 7, "coverage_status": "rated", "distinct_rated_opponents": 38, "draws": 7, "generated_at": "2026-07-17T22:36:00Z", "losses": 37, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-abb31ae26e404d88", "rated_matches": 76, "raw_elo_rating": 1464.725832992289, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 43.92511041434462, "uncertainty": 13.230288229818967, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 6, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 6, "generated_at": "2026-07-24T14:00:00Z", "losses": 10, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-d709aeb6802f9289", "rated_matches": 72, "raw_elo_rating": 1810.7375600339055, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 88.66279441284121, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 56 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 12, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 12, "generated_at": "2026-07-21T14:20:15Z", "losses": 7, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-dc626769adfba01d", "rated_matches": 38, "raw_elo_rating": 1630.6217680312, "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": 63.05509856002232, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 3, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 3, "generated_at": "2026-07-17T22:36:00Z", "losses": 14, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-f9b8636a677996e4", "rated_matches": 34, "raw_elo_rating": 1582.2881600523183, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 56.321380026095234, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 12, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 12, "generated_at": "2026-07-17T22:36:00Z", "losses": 20, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-fcb362c12bec2a34", "rated_matches": 60, "raw_elo_rating": 1620.4063338934643, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 63.39520243483502, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 5, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 5, "generated_at": "2026-07-02T16:51:45Z", "losses": 16, "model": "x-ai/grok-build-0.1", "point_rating_method": "sequential_elo", "public_id": "E-f1ded648f3ab17dc", "rated_matches": 40, "raw_elo_rating": 1516.3694881573388, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 48.43526682108, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 3, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 3, "generated_at": "2026-07-02T16:51:45Z", "losses": 16, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-1208f50b0908ecb4", "rated_matches": 38, "raw_elo_rating": 1508.5308307724358, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 47.21289857419709, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 4, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 4, "generated_at": "2026-07-02T06:10:40Z", "losses": 18, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-2a71bee21bd7c0b9", "rated_matches": 36, "raw_elo_rating": 1489.219330088802, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 44.48542000207563, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 3, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 3, "generated_at": "2026-07-02T06:10:40Z", "losses": 26, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-2cdd8ae895784956", "rated_matches": 62, "raw_elo_rating": 1601.4159101664063, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 61.03738956321968, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 33 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 31, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 31, "generated_at": "2026-07-02T06:10:40Z", "losses": 11, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-8478c64d84536b61", "rated_matches": 42, "raw_elo_rating": 1308.1269234889603, "reasoning": "highest", "reasoning_bracket": "highest", "reasoning_setting": "highest", "repair_status": "repaired", "score": 21.605010778009973, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 23, "coverage_status": "rated", "distinct_rated_opponents": 37, "draws": 23, "generated_at": "2026-07-02T16:51:45Z", "losses": 27, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-912a4a40bbdcbd45", "rated_matches": 74, "raw_elo_rating": 1469.798556983822, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 44.5049874513793, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 25, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 25, "generated_at": "2026-07-01T00:15:48Z", "losses": 29, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-a168350bd057f924", "rated_matches": 68, "raw_elo_rating": 1414.8676050846543, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 37.12214663168973, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 76, "capped_draws": 24, "coverage_status": "rated", "distinct_rated_opponents": 38, "draws": 24, "generated_at": "2026-07-02T16:51:45Z", "losses": 29, "model": "xiaomi/mimo-v2.5-pro", "point_rating_method": "sequential_elo", "public_id": "E-9ce4191c7f1f3b3e", "rated_matches": 76, "raw_elo_rating": 1431.6560101881555, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 39.63405689209577, "uncertainty": 13.230288229818967, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 34, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 34, "generated_at": "2026-07-11T14:00:45Z", "losses": 11, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-5ab5088af70c19d6", "rated_matches": 58, "raw_elo_rating": 1469.3129924928696, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 43.678029747500474, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 2, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 2, "generated_at": "2026-07-01T00:15:48Z", "losses": 22, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-5bc0612062635fa8", "rated_matches": 46, "raw_elo_rating": 1519.9526508967542, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 49.43526423526853, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 22 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 12, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 12, "generated_at": "2026-07-11T14:00:45Z", "losses": 22, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-5c3b7f5666a38043", "rated_matches": 46, "raw_elo_rating": 1453.34418739154, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 40.79232460935949, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 8, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 8, "generated_at": "2026-07-02T06:10:40Z", "losses": 13, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-6a7eb114b16dc845", "rated_matches": 42, "raw_elo_rating": 1559.2129908058334, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 54.1852807095748, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 34, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 34, "generated_at": "2026-07-03T18:27:00Z", "losses": 17, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-88bed07a2e526eed", "rated_matches": 62, "raw_elo_rating": 1527.2478732087454, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 51.413539501777066, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 32, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 32, "generated_at": "2026-07-01T00:15:48Z", "losses": 7, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-b2a148bd3f2766ff", "rated_matches": 44, "raw_elo_rating": 1467.924210170858, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 42.51777854057247, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 1, "generated_at": "2026-07-02T16:51:45Z", "losses": 23, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-c8076ea61de8da45", "rated_matches": 42, "raw_elo_rating": 1384.7748989366414, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 31.55065115733814, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 3, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 3, "generated_at": "2026-07-11T17:22:09Z", "losses": 18, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-f889d782e3cce209", "rated_matches": 44, "raw_elo_rating": 1443.3557138091094, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 39.32983485324606, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 23 } ], "GB2-02": [ { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 28, "generated_at": "2026-07-02T16:51:45Z", "losses": 9, "model": "claude-fable-5", "point_rating_method": "sequential_elo", "public_id": "E-cd3608270e8c00fd", "rated_matches": 58, "raw_elo_rating": 1624.075614202798, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 63.51723403185436, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 26, "generated_at": "2026-07-03T17:50:00Z", "losses": 3, "model": "claude-fable-5", "point_rating_method": "sequential_elo", "public_id": "E-f6a30e7d9986c9b8", "rated_matches": 58, "raw_elo_rating": 1659.3993318565135, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 71.95778371836957, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 31, "losses": 4, "model": "claude-opus-4-5", "point_rating_method": "sequential_elo", "public_id": "E-03472a04778e9928", "rated_matches": 36, "raw_elo_rating": 1481.9224428584423, "reasoning": "legacy_shared_thinking_budget", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "legacy_shared_thinking_budget", "repair_status": "first_pass", "score": 26.280166905425435, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "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": "highest", "reasoning_policy_version": "legacy_reasoning_presets_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": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 50, "generated_at": "2026-07-02T16:51:45Z", "losses": 5, "model": "claude-opus-4-5", "point_rating_method": "sequential_elo", "public_id": "E-16462f3d1f3a7b19", "rated_matches": 58, "raw_elo_rating": 1507.016974397993, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 35.54624651592337, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "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": "medium", "reasoning_policy_version": "legacy_reasoning_presets_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": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 31, "losses": 3, "model": "claude-opus-4-5", "point_rating_method": "sequential_elo", "public_id": "E-63fde27ceab11930", "rated_matches": 34, "raw_elo_rating": 1461.1475591575331, "reasoning": "legacy_shared_thinking_budget", "reasoning_bracket": "intensive", "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "legacy_shared_thinking_budget", "repair_status": "first_pass", "score": 20.873328642805216, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 20, "generated_at": "2026-07-03T17:20:00Z", "losses": 3, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-a81bd03e764818f6", "rated_matches": 58, "raw_elo_rating": 1735.4526025988669, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 90.13059941166075, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 35 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 44, "generated_at": "2026-07-02T16:51:45Z", "losses": 7, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-c142942f4138c871", "rated_matches": 54, "raw_elo_rating": 1477.334204135014, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 28.009047114593564, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 39, "generated_at": "2026-07-02T16:51:45Z", "losses": 3, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-ed71c4ecf219b609", "rated_matches": 44, "raw_elo_rating": 1477.1586139699823, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 26.60687800872694, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 21, "generated_at": "2026-07-25T10:50:00Z", "losses": 10, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-50b401cafe71e710", "rated_matches": 50, "raw_elo_rating": 1639.4351675605897, "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": 66.24696134878403, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 17, "generated_at": "2026-07-25T10:50:00Z", "losses": 11, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-51ddad48e10b006f", "rated_matches": 50, "raw_elo_rating": 1644.470715376277, "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": 67.45019799430912, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 22 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 12, "generated_at": "2026-07-25T15:48:01Z", "losses": 7, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-6b45cf5aebf0c66e", "rated_matches": 40, "raw_elo_rating": 1653.9188004065568, "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": 68.16460233811627, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 32, "generated_at": "2026-07-25T10:50:00Z", "losses": 3, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-772d1a710082ddb3", "rated_matches": 50, "raw_elo_rating": 1583.7397660803254, "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": 52.938628174086666, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 24, "generated_at": "2026-07-25T10:50:00Z", "losses": 7, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-8a5bf2e23121edf6", "rated_matches": 48, "raw_elo_rating": 1621.3399904009398, "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": 61.65273875121062, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 7, "generated_at": "2026-07-25T15:48:01Z", "losses": 7, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-fcdd98d74e80134a", "rated_matches": 40, "raw_elo_rating": 1741.313699122259, "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": 89.04748313195766, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 50, "generated_at": "2026-07-02T16:51:45Z", "losses": 3, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-a1a16bb5799cfdbe", "rated_matches": 54, "raw_elo_rating": 1489.9472910874329, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 31.022925443196662, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 39, "generated_at": "2026-07-03T16:50:00Z", "losses": 10, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-e35d82f3fd09a1f4", "rated_matches": 56, "raw_elo_rating": 1527.5674418666176, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 40.24032728154734, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 35, "generated_at": "2026-07-02T16:51:45Z", "losses": 3, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-e501d6808bd19ccc", "rated_matches": 38, "raw_elo_rating": 1479.446255038946, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 26.09668923633087, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 30, "generated_at": "2026-07-02T06:10:40Z", "losses": 6, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-08e2baea96c43eb4", "rated_matches": 36, "raw_elo_rating": 1449.9398243337023, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 18.637967876169636, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 52, "generated_at": "2026-07-02T16:51:45Z", "losses": 2, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-12dcb25370550495", "rated_matches": 58, "raw_elo_rating": 1477.211294899079, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 28.424223822355827, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 38, "generated_at": "2026-07-01T00:15:48Z", "losses": 0, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-1e168b9e73c26073", "rated_matches": 38, "raw_elo_rating": 1494.110316710008, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 29.60064491715948, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 58, "generated_at": "2026-07-02T16:51:45Z", "losses": 2, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-3358fbcda6ab6f4d", "rated_matches": 60, "raw_elo_rating": 1490.412478398123, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 31.784316788866928, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 48, "generated_at": "2026-07-02T06:10:40Z", "losses": 0, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-bc9a8c3886a48505", "rated_matches": 48, "raw_elo_rating": 1494.553696664807, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 31.357342826586542, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 52, "generated_at": "2026-07-02T06:10:40Z", "losses": 6, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-f2e6dd87c5656ee3", "rated_matches": 60, "raw_elo_rating": 1491.731421574102, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 32.099476295000294, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 48, "generated_at": "2026-07-02T16:51:45Z", "losses": 1, "model": "deepseek/deepseek-v4-pro", "point_rating_method": "sequential_elo", "public_id": "E-6c3b019c1b20a09b", "rated_matches": 50, "raw_elo_rating": 1502.3246516528714, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 33.484607923588854, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 34, "generated_at": "2026-07-02T16:51:45Z", "losses": 3, "model": "google/gemini-3.1-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-20b3484be872df52", "rated_matches": 38, "raw_elo_rating": 1495.250360698582, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 29.873056729095698, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-21T14:20:15Z", "losses": 0, "model": "google/gemini-3.5-flash", "point_rating_method": "sequential_elo", "public_id": "E-cbf88e49a4581eb0", "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": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 45, "generated_at": "2026-07-02T16:51:45Z", "losses": 2, "model": "google/gemini-3.5-flash", "point_rating_method": "sequential_elo", "public_id": "E-ef7a835bdb46a90e", "rated_matches": 54, "raw_elo_rating": 1499.278211372801, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 33.25253493848372, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-1010911d64a09b68", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 57, "generated_at": "2026-07-24T13:40:00Z", "losses": 3, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-60dfb882a81b3944", "rated_matches": 64, "raw_elo_rating": 1490.350042065004, "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": 32.15192038613775, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-939a2dc80becc700", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-a3da6c33bd873fb7", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-e65fdcb71f09a611", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 63, "generated_at": "2026-07-24T13:40:00Z", "losses": 1, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-f2b9f6de4830b5f8", "rated_matches": 64, "raw_elo_rating": 1482.1921841435394, "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": 30.20261239436096, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-4492f6d65cd6280b", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 62, "generated_at": "2026-07-24T13:40:00Z", "losses": 4, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-62275b0c39dda32a", "rated_matches": 66, "raw_elo_rating": 1470.9407016695134, "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": 27.69237075496183, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-9c8b43dc41bad760", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 61, "generated_at": "2026-07-24T13:40:00Z", "losses": 1, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-e49b9c0097a352eb", "rated_matches": 62, "raw_elo_rating": 1481.9137366439209, "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": 29.94937076585172, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 31, "generated_at": "2026-07-02T16:51:45Z", "losses": 10, "model": "gpt-4.1", "point_rating_method": "sequential_elo", "public_id": "E-e4707b8e4c581ede", "rated_matches": 44, "raw_elo_rating": 1461.1826663180202, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 22.789449128010855, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "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": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 25, "generated_at": "2026-07-02T16:51:45Z", "losses": 9, "model": "gpt-5", "point_rating_method": "sequential_elo", "public_id": "E-5bccb9b671ce5eae", "rated_matches": 38, "raw_elo_rating": 1486.0056946936531, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 27.664057565565336, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 37, "generated_at": "2026-07-02T16:51:45Z", "losses": 7, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-4aa582caf9d9f6da", "rated_matches": 64, "raw_elo_rating": 1595.2075134501106, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 57.20745689293141, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 60, "generated_at": "2026-07-02T16:51:45Z", "losses": 1, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-98ddce22d3eb5886", "rated_matches": 62, "raw_elo_rating": 1488.5809352786268, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 31.542487942751787, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 59, "generated_at": "2026-07-02T16:51:45Z", "losses": 6, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-f4948a32cdd115a9", "rated_matches": 68, "raw_elo_rating": 1462.112751652437, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 25.753419845975525, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 44, "generated_at": "2026-07-02T06:10:40Z", "losses": 3, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-3082b8a32a9c1e1f", "rated_matches": 50, "raw_elo_rating": 1498.9538966960165, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 32.67917105045695, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 59, "generated_at": "2026-07-02T16:51:45Z", "losses": 1, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-322cbb8be1559087", "rated_matches": 60, "raw_elo_rating": 1485.7642934893795, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 30.67363993262635, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 54, "generated_at": "2026-07-01T00:15:48Z", "losses": 4, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-4f2717a1b63468f4", "rated_matches": 58, "raw_elo_rating": 1481.8972078750385, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 29.54391574402747, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 49, "generated_at": "2026-07-02T16:51:45Z", "losses": 5, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-59f362f57892ab54", "rated_matches": 56, "raw_elo_rating": 1487.0058745879062, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 30.548201233685464, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 46, "generated_at": "2026-07-02T16:51:45Z", "losses": 2, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-6724998b59176607", "rated_matches": 48, "raw_elo_rating": 1480.1650165924148, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 27.919189168328465, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 56, "generated_at": "2026-07-02T06:10:40Z", "losses": 3, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-7ef67fa468b6c12c", "rated_matches": 60, "raw_elo_rating": 1475.998136939331, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 28.340031380574597, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 55, "generated_at": "2026-07-02T06:10:40Z", "losses": 1, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-b45c06f99639b8db", "rated_matches": 58, "raw_elo_rating": 1501.6284527576236, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 34.2586673010664, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 48, "generated_at": "2026-07-01T00:15:48Z", "losses": 2, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-dd45dfa7984ab9fa", "rated_matches": 52, "raw_elo_rating": 1509.4348665175428, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 35.43853591905222, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 45, "generated_at": "2026-07-09T17:30:50Z", "losses": 2, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-038a95fb13c8aa94", "rated_matches": 48, "raw_elo_rating": 1496.6194788828827, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 31.85095840873223, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 58, "generated_at": "2026-07-09T17:30:50Z", "losses": 4, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-1ce420518fc32de1", "rated_matches": 62, "raw_elo_rating": 1469.6780915147815, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 27.025681598377982, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 52, "generated_at": "2026-07-01T00:15:48Z", "losses": 2, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-23b12c36ef5c7ef8", "rated_matches": 54, "raw_elo_rating": 1477.0288370659568, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 27.93608010856464, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 59, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 51, "generated_at": "2026-07-01T00:15:48Z", "losses": 6, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-6a4ccfcf11c5e3f3", "rated_matches": 59, "raw_elo_rating": 1480.7550497920456, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 29.375129293410357, "uncertainty": 20.79972243679028, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 53, "generated_at": "2026-07-02T06:10:40Z", "losses": 3, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-786cc9019eb3ee2b", "rated_matches": 58, "raw_elo_rating": 1501.6383350101655, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 34.261028650582745, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 43, "generated_at": "2026-07-02T06:10:40Z", "losses": 2, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-a92f8113f0090156", "rated_matches": 46, "raw_elo_rating": 1477.3205291766571, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 26.95201475987576, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 37, "draws": 58, "generated_at": "2026-07-02T16:51:45Z", "losses": 10, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-b084ba147f956b49", "rated_matches": 74, "raw_elo_rating": 1491.998524626864, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 33.364429917630005, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 45, "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": 52, "raw_elo_rating": 1441.4318190228537, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 19.18930907265305, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 55, "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": 58, "raw_elo_rating": 1485.0578421415407, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 30.29914459136565, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 62, "generated_at": "2026-07-02T16:51:45Z", "losses": 2, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-51e935956fa76015", "rated_matches": 64, "raw_elo_rating": 1501.313222137573, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 34.77155592483919, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 30, "generated_at": "2026-07-02T16:51:45Z", "losses": 12, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-8460841e3919c568", "rated_matches": 56, "raw_elo_rating": 1534.4980840240307, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 41.89639389555927, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 64, "generated_at": "2026-07-10T05:30:29Z", "losses": 6, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-a30e455ba172d80e", "rated_matches": 70, "raw_elo_rating": 1473.232701299803, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 28.573734971782702, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 58, "generated_at": "2026-07-10T05:30:29Z", "losses": 0, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-ba4589e1cf2c827b", "rated_matches": 58, "raw_elo_rating": 1488.7189255222488, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 31.173955008668692, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 50, "generated_at": "2026-07-10T05:30:29Z", "losses": 0, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-e2dda893ae4363f2", "rated_matches": 50, "raw_elo_rating": 1491.9181454193697, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 30.997988769059855, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 42, "generated_at": "2026-07-10T05:30:29Z", "losses": 6, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-0420ca9039edc6fb", "rated_matches": 54, "raw_elo_rating": 1501.132056255132, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 33.69550841012682, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 25, "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": 58, "raw_elo_rating": 1554.6276258057092, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 46.92274071038185, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 22 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 11, "generated_at": "2026-07-10T05:30:29Z", "losses": 4, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-33dc9365cfacf9c0", "rated_matches": 58, "raw_elo_rating": 1776.7560641910516, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 100.0, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 43 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 37, "generated_at": "2026-07-10T05:30:29Z", "losses": 10, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-1b12482867c807c9", "rated_matches": 60, "raw_elo_rating": 1547.1720098303158, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 45.346922229587115, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 50, "generated_at": "2026-07-10T05:30:29Z", "losses": 2, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-82ad98d8d570daab", "rated_matches": 52, "raw_elo_rating": 1487.2623907567247, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 30.140455882095676, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 57, "generated_at": "2026-07-10T05:30:29Z", "losses": 3, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-c6593bd789768bdb", "rated_matches": 62, "raw_elo_rating": 1477.2364928140053, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 28.8317503237067, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "inclusionai/ling-3.0-flash", "point_rating_method": "sequential_elo", "public_id": "E-129026c5e53b35ad", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 60, "generated_at": "2026-07-24T13:40:00Z", "losses": 2, "model": "inclusionai/ling-3.0-flash", "point_rating_method": "sequential_elo", "public_id": "E-fc495094a55d2f94", "rated_matches": 62, "raw_elo_rating": 1472.8398095919308, "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": 27.7811694206549, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "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": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 63, "generated_at": "2026-07-24T13:40:00Z", "losses": 1, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-a0c74818516a7f27", "rated_matches": 64, "raw_elo_rating": 1480.524029567731, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 29.80400934470667, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 55, "generated_at": "2026-07-02T16:51:45Z", "losses": 1, "model": "minimax/minimax-m3", "point_rating_method": "sequential_elo", "public_id": "E-1e46941293882535", "rated_matches": 56, "raw_elo_rating": 1475.919430546933, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 27.899111953447644, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 26, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 13, "draws": 24, "generated_at": "2026-07-02T16:51:45Z", "losses": 2, "model": "minimax/minimax-m3", "point_rating_method": "sequential_elo", "public_id": "E-cad87bcb23d33fef", "rated_matches": 26, "raw_elo_rating": 1468.2779761828997, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 20.338734282488755, "uncertainty": 52.475044864937615, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 25, "generated_at": "2026-07-02T16:51:45Z", "losses": 5, "model": "moonshotai/kimi-k2.7-code", "point_rating_method": "sequential_elo", "public_id": "E-85c8a9372a607001", "rated_matches": 32, "raw_elo_rating": 1459.5981620032649, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 20.020731887899807, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 28, "generated_at": "2026-07-24T14:00:00Z", "losses": 8, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-1beeecccf3f2c84f", "rated_matches": 40, "raw_elo_rating": 1493.0455285004546, "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": 29.724173783368585, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 28, "generated_at": "2026-07-24T14:00:00Z", "losses": 4, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-8825a1d540d89836", "rated_matches": 32, "raw_elo_rating": 1469.0416443249453, "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": 22.277237914000036, "uncertainty": 43.288827977848925, "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, "generated_at": "2026-07-18T00:14:00Z", "losses": 6, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-97d6a124a1509fc1", "rated_matches": 32, "raw_elo_rating": 1497.4506468576496, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "score": 29.065526728113745, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 30, "generated_at": "2026-07-17T22:36:00Z", "losses": 3, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-b0de9fa15f139d69", "rated_matches": 34, "raw_elo_rating": 1466.881464973261, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "score": 22.2434368915999, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 30, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 15, "draws": 24, "generated_at": "2026-07-21T14:43:57Z", "losses": 3, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-be8e56a3b58c5bcc", "rated_matches": 30, "raw_elo_rating": 1513.034788159119, "reasoning": "high", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 32.26100494924303, "uncertainty": 46.05265101338746, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 31, "generated_at": "2026-07-24T14:00:00Z", "losses": 0, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-d3d3da42e99695b1", "rated_matches": 32, "raw_elo_rating": 1506.616689854054, "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": 31.255739040937716, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 38, "generated_at": "2026-07-21T14:20:15Z", "losses": 1, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-fc3ad6db6543001f", "rated_matches": 42, "raw_elo_rating": 1524.1490804380742, "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": 37.50759377970699, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 46, "generated_at": "2026-07-11T17:22:09Z", "losses": 5, "model": "nex-agi/nex-n2-pro", "point_rating_method": "sequential_elo", "public_id": "E-811f47e902ce0d21", "rated_matches": 52, "raw_elo_rating": 1466.422044691208, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 25.16068625041128, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 33, "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": 40, "raw_elo_rating": 1470.497735408151, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 24.3364122294304, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 29, "generated_at": "2026-07-11T17:22:09Z", "losses": 4, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-abd2cae3e3ff9bdb", "rated_matches": 34, "raw_elo_rating": 1473.2584552355572, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 23.76720921044226, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 52, "generated_at": "2026-07-02T16:51:45Z", "losses": 2, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-bd70ebbd81fdbef0", "rated_matches": 54, "raw_elo_rating": 1479.6156043304468, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 28.554184291069387, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 30, "generated_at": "2026-07-21T14:20:15Z", "losses": 1, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-e48b0ea99dfc517c", "rated_matches": 32, "raw_elo_rating": 1479.8188659817515, "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": 24.852438966409498, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 39, "generated_at": "2026-07-21T14:20:15Z", "losses": 1, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-18d1d6f3b7eabe0d", "rated_matches": 40, "raw_elo_rating": 1489.8564736994583, "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": 28.962153891671328, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 45, "generated_at": "2026-07-02T16:51:45Z", "losses": 2, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-8f0c6569aa132f8e", "rated_matches": 48, "raw_elo_rating": 1484.5879724595852, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 28.976047880768927, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 28, "generated_at": "2026-07-02T16:51:45Z", "losses": 4, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-e5b4a3586049e1c9", "rated_matches": 32, "raw_elo_rating": 1451.3761190633325, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 18.05608698162218, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "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": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "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": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 60, "generated_at": "2026-07-24T13:40:00Z", "losses": 2, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-d8c7a78cc7f666dc", "rated_matches": 64, "raw_elo_rating": 1477.653649416274, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 29.11813628556075, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 46, "generated_at": "2026-07-02T16:51:45Z", "losses": 1, "model": "qwen/qwen3.7-max", "point_rating_method": "sequential_elo", "public_id": "E-5f64c2ae9860ba38", "rated_matches": 50, "raw_elo_rating": 1502.5488228935112, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 33.53817330743257, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 30, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 15, "draws": 26, "generated_at": "2026-07-02T16:51:45Z", "losses": 2, "model": "qwen/qwen3.7-max", "point_rating_method": "sequential_elo", "public_id": "E-95265340f8562bfd", "rated_matches": 30, "raw_elo_rating": 1499.9888156481884, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 29.143689261610728, "uncertainty": 46.05265101338746, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 48, "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": 48, "raw_elo_rating": 1495.4141301372438, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 31.562942122426243, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 28, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 14, "draws": 25, "generated_at": "2026-07-02T16:51:45Z", "losses": 2, "model": "qwen/qwen3.7-plus", "point_rating_method": "sequential_elo", "public_id": "E-57293d5b71f14882", "rated_matches": 28, "raw_elo_rating": 1497.4309640195622, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 27.950412402617552, "uncertainty": 49.09766908852594, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 49, "generated_at": "2026-07-02T16:51:45Z", "losses": 4, "model": "stepfun/step-3.7-flash", "point_rating_method": "sequential_elo", "public_id": "E-0ccea44addccfff0", "rated_matches": 54, "raw_elo_rating": 1497.5007403786417, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 32.827810893590744, "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": 57, "generated_at": "2026-07-02T16:51:45Z", "losses": 5, "model": "tencent/hy3-preview", "point_rating_method": "sequential_elo", "public_id": "E-d910e47dd13c2c71", "rated_matches": 62, "raw_elo_rating": 1466.7923583848676, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 26.336139967911993, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 27, "generated_at": "2026-07-02T16:51:45Z", "losses": 5, "model": "tencent/hy3-preview", "point_rating_method": "sequential_elo", "public_id": "E-fbf6af15f65f01d7", "rated_matches": 32, "raw_elo_rating": 1440.1843320024248, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 15.381826143775362, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 63, "generated_at": "2026-07-24T13:40:00Z", "losses": 5, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-63e0985794df5d5b", "rated_matches": 68, "raw_elo_rating": 1476.5603955656177, "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": 29.205662826109684, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 64, "generated_at": "2026-07-24T13:40:00Z", "losses": 1, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-66a4f0abd099d8f1", "rated_matches": 66, "raw_elo_rating": 1499.1390170008954, "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": 34.43031617632999, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-9468e854340a4e9b", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 16, "generated_at": "2026-07-24T14:00:00Z", "losses": 7, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-0576181f89efa7a7", "rated_matches": 32, "raw_elo_rating": 1529.6313657780952, "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": 36.75506155167247, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 29, "generated_at": "2026-07-17T22:36:00Z", "losses": 8, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-081ac2f1dd1c34b2", "rated_matches": 54, "raw_elo_rating": 1579.9832825904505, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 52.5368914222546, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 37, "generated_at": "2026-07-21T14:20:15Z", "losses": 2, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-1331dea6489316f2", "rated_matches": 40, "raw_elo_rating": 1479.5752759796987, "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": 26.505477019739928, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 32, "generated_at": "2026-07-24T14:00:00Z", "losses": 1, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-1b0da3150a77b47b", "rated_matches": 34, "raw_elo_rating": 1494.8957020313685, "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": 28.93739708392125, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 23, "generated_at": "2026-07-17T22:36:00Z", "losses": 6, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-8728b59f87c3369e", "rated_matches": 34, "raw_elo_rating": 1498.4288375296255, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 29.781634545407535, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 78, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 39, "draws": 52, "generated_at": "2026-07-24T14:00:00Z", "losses": 13, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-da5ea0258e71b6ab", "rated_matches": 78, "raw_elo_rating": 1504.8822556582252, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 36.72601406890413, "uncertainty": 12.5043950463012, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 26, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 13, "draws": 23, "generated_at": "2026-07-02T16:51:45Z", "losses": 2, "model": "x-ai/grok-build-0.1", "point_rating_method": "sequential_elo", "public_id": "E-99592fa0331c6679", "rated_matches": 26, "raw_elo_rating": 1495.6785070208127, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 26.8860502881689, "uncertainty": 52.475044864937615, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 53, "generated_at": "2026-07-01T00:15:48Z", "losses": 3, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-39b08fe4c0318552", "rated_matches": 56, "raw_elo_rating": 1468.5821896697769, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 26.14588918135212, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 28, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 14, "draws": 26, "generated_at": "2026-07-02T16:51:45Z", "losses": 1, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-5b213ae773e821cc", "rated_matches": 28, "raw_elo_rating": 1493.0334253932465, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 26.899627101997144, "uncertainty": 49.09766908852594, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 33, "generated_at": "2026-07-02T06:10:40Z", "losses": 3, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-9077f1e8e006290b", "rated_matches": 38, "raw_elo_rating": 1483.571469812471, "reasoning": "highest", "reasoning_bracket": "highest", "reasoning_setting": "highest", "repair_status": "repaired", "score": 27.082403158201195, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 26, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 13, "draws": 23, "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": 26, "raw_elo_rating": 1464.4614016431726, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 19.426769484483785, "uncertainty": 52.475044864937615, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 30, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 15, "draws": 25, "generated_at": "2026-07-02T06:10:40Z", "losses": 3, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-c37f25e181320efb", "rated_matches": 30, "raw_elo_rating": 1484.770314980792, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 25.507251208949754, "uncertainty": 46.05265101338746, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 56, "generated_at": "2026-07-02T16:51:45Z", "losses": 4, "model": "xiaomi/mimo-v2.5-pro", "point_rating_method": "sequential_elo", "public_id": "E-b9f44937a1269e8d", "rated_matches": 64, "raw_elo_rating": 1479.9188889322822, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 29.659411891774138, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 38, "generated_at": "2026-07-11T17:22:09Z", "losses": 2, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-32435b01ac08ed41", "rated_matches": 40, "raw_elo_rating": 1470.8448216282686, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 24.41934796442663, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 55, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 45, "generated_at": "2026-07-11T14:00:45Z", "losses": 7, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-4442c0e8a06187bf", "rated_matches": 55, "raw_elo_rating": 1482.9029089130715, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 29.455269920534768, "uncertainty": 23.065310478106092, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 35, "generated_at": "2026-07-02T16:51:45Z", "losses": 3, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-4959351a96fd2b82", "rated_matches": 38, "raw_elo_rating": 1466.9306050201762, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 23.106093317802184, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 37, "generated_at": "2026-07-11T14:00:45Z", "losses": 1, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-925b589068dc7268", "rated_matches": 38, "raw_elo_rating": 1486.4015813825515, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 27.758654099843973, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 56, "generated_at": "2026-07-02T16:51:45Z", "losses": 4, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-98394109d97d67ee", "rated_matches": 60, "raw_elo_rating": 1470.0478126035491, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 26.918210248965437, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 31, "generated_at": "2026-07-01T00:15:48Z", "losses": 4, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-b090ee9c8b9921ad", "rated_matches": 38, "raw_elo_rating": 1489.960530795913, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 28.609059757871027, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 45, "generated_at": "2026-07-02T06:10:40Z", "losses": 8, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-dd5764d86cd88052", "rated_matches": 60, "raw_elo_rating": 1498.8427257391668, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 33.79871182648007, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 7 } ], "GB2-03": [ { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 20, "generated_at": "2026-07-03T17:50:00Z", "losses": 4, "model": "claude-fable-5", "point_rating_method": "sequential_elo", "public_id": "E-04fa5b762ca703f0", "rated_matches": 42, "raw_elo_rating": 1640.156750580333, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 69.09378758500024, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 8, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 35, "generated_at": "2026-07-02T16:51:45Z", "losses": 9, "model": "claude-opus-4-5", "point_rating_method": "sequential_elo", "public_id": "E-1975db22db58e9b0", "rated_matches": 52, "raw_elo_rating": 1543.043331713756, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 53.68257145959784, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "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": "medium", "reasoning_policy_version": "legacy_reasoning_presets_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": 20, "capped_draws": 1, "coverage_status": "under_covered", "distinct_rated_opponents": 10, "draws": 4, "losses": 8, "model": "claude-opus-4-5", "point_rating_method": "sequential_elo", "public_id": "E-d5810442d7094396", "rated_matches": 20, "raw_elo_rating": 1470.7028387586076, "reasoning": "legacy_shared_thinking_budget", "reasoning_bracket": "intensive", "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "legacy_shared_thinking_budget", "repair_status": "first_pass", "score": 35.965346928221244, "uncertainty": 65.3589451179962, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 22, "capped_draws": 3, "coverage_status": "under_covered", "distinct_rated_opponents": 11, "draws": 11, "losses": 6, "model": "claude-opus-4-5", "point_rating_method": "sequential_elo", "public_id": "E-dfb18dba94eee30b", "rated_matches": 22, "raw_elo_rating": 1509.099478672596, "reasoning": "legacy_shared_thinking_budget", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "legacy_shared_thinking_budget", "repair_status": "first_pass", "score": 43.12072389484681, "uncertainty": 60.5072070285374, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 5, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 23, "generated_at": "2026-07-02T16:51:45Z", "losses": 10, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-823b961281482cd1", "rated_matches": 40, "raw_elo_rating": 1461.662536911419, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 38.63559627801959, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 1, "generated_at": "2026-07-25T15:48:00Z", "losses": 2, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-38759212c025e8eb", "rated_matches": 40, "raw_elo_rating": 1824.2382806143908, "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": 34.33688094430304, "unilateral_faults": 0, "wins": 37 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 4, "generated_at": "2026-07-25T15:48:00Z", "losses": 15, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-49aaba66f6b19080", "rated_matches": 42, "raw_elo_rating": 1584.378997703733, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 59.65363995882995, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 0, "generated_at": "2026-07-25T15:48:00Z", "losses": 4, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-7caa6c5081d57676", "rated_matches": 40, "raw_elo_rating": 1812.5461454407864, "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": 98.02115581192106, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 36 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 0, "generated_at": "2026-07-25T15:48:00Z", "losses": 9, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-bd02f4c2907d0a7c", "rated_matches": 40, "raw_elo_rating": 1762.3109287237023, "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": 89.51905887569116, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 31 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 2, "generated_at": "2026-07-25T15:48:00Z", "losses": 4, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-d8babc5495b1a188", "rated_matches": 40, "raw_elo_rating": 1790.8153742206016, "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": 94.34331513585578, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 8, "generated_at": "2026-07-25T15:48:00Z", "losses": 15, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-ecf847457e616425", "rated_matches": 40, "raw_elo_rating": 1470.331123516614, "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": 40.10271772058338, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 1, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 18, "generated_at": "2026-07-19T15:25:00Z", "losses": 7, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-1c251b669239429c", "rated_matches": 38, "raw_elo_rating": 1577.5269529910452, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 57.97745068031415, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 3, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 10, "generated_at": "2026-07-03T16:50:00Z", "losses": 25, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-2e43b0d163a7f12d", "rated_matches": 38, "raw_elo_rating": 1321.905658074529, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 14.714632872946382, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 2, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 18, "generated_at": "2026-07-19T15:25:00Z", "losses": 12, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-d49e8df479ed0377", "rated_matches": 48, "raw_elo_rating": 1537.0474990137684, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 52.29569320842981, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 4, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 13, "generated_at": "2026-07-02T16:51:45Z", "losses": 15, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-e7d1e6857fc48e7a", "rated_matches": 38, "raw_elo_rating": 1485.0924616716402, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 42.333305859069256, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugin_count": 1, "attempted_matches": 22, "capped_draws": 1, "coverage_status": "under_covered", "distinct_rated_opponents": 11, "draws": 11, "generated_at": "2026-07-02T16:51:45Z", "losses": 8, "model": "cohere/north-mini-code", "point_rating_method": "sequential_elo", "public_id": "E-0f669ae82234cf76", "rated_matches": 22, "raw_elo_rating": 1447.2565796679385, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 32.65407606258489, "uncertainty": 60.5072070285374, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 30, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 15, "draws": 9, "generated_at": "2026-07-01T00:15:48Z", "losses": 9, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-32e04fe5ad231857", "rated_matches": 30, "raw_elo_rating": 1546.9358887216838, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 51.48147323629893, "uncertainty": 46.05265101338746, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 18, "generated_at": "2026-07-02T06:10:40Z", "losses": 17, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-4e52c100ed276347", "rated_matches": 46, "raw_elo_rating": 1454.2183123506989, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 38.073579139181625, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 26, "generated_at": "2026-07-02T16:51:45Z", "losses": 17, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-ae9d59ec3a8a1d63", "rated_matches": 60, "raw_elo_rating": 1491.0611475690398, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 45.51600526871697, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 14, "generated_at": "2026-07-02T16:51:45Z", "losses": 27, "model": "deepseek/deepseek-v4-pro", "point_rating_method": "sequential_elo", "public_id": "E-f82a334a0fd1fb8e", "rated_matches": 50, "raw_elo_rating": 1351.7838803092702, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 21.132140682151817, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 18, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 9, "draws": 13, "generated_at": "2026-07-02T16:51:45Z", "losses": 1, "model": "google/gemini-3.5-flash", "point_rating_method": "sequential_elo", "public_id": "E-46c3bb79de67d970", "rated_matches": 18, "raw_elo_rating": 1531.1346465855556, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 45.43509859730099, "uncertainty": 70.95786693528086, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 14, "generated_at": "2026-07-02T16:51:45Z", "losses": 13, "model": "google/gemini-3.5-flash", "point_rating_method": "sequential_elo", "public_id": "E-8ed795ea8fd1e0aa", "rated_matches": 50, "raw_elo_rating": 1586.8467498305283, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 60.91553236200583, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-21T14:20:15Z", "losses": 0, "model": "google/gemini-3.5-flash", "point_rating_method": "sequential_elo", "public_id": "E-d2c81e6c396a15b0", "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": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-28274045fbc35ae9", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 3, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 21, "generated_at": "2026-07-24T13:40:00Z", "losses": 16, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-36e89f1dca2cd568", "rated_matches": 52, "raw_elo_rating": 1539.062970554589, "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": 53.008912249425926, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-dc837629b72c2e03", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 17, "generated_at": "2026-07-24T13:40:00Z", "losses": 16, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-e51f710b50e975e5", "rated_matches": 50, "raw_elo_rating": 1502.0617027417863, "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": 46.56602346765769, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-e9957a543416b0ad", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-6743f1c221046d65", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-80b8c1a18d6dd238", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 2, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 24, "generated_at": "2026-07-24T13:40:00Z", "losses": 12, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-9b5d467ecf278026", "rated_matches": 50, "raw_elo_rating": 1566.0655294136466, "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": 57.39839912393218, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-ed24a723621c4481", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 3, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 13, "generated_at": "2026-07-24T13:40:00Z", "losses": 18, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-f44c7c8e627e08cd", "rated_matches": 54, "raw_elo_rating": 1552.608731840876, "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": 55.47211453610619, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 30, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 15, "draws": 10, "generated_at": "2026-07-02T16:51:45Z", "losses": 10, "model": "gpt-4.1", "point_rating_method": "sequential_elo", "public_id": "E-c7da9914f86ee846", "rated_matches": 30, "raw_elo_rating": 1527.2252132901654, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 48.1455251873211, "uncertainty": 46.05265101338746, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "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": 22, "capped_draws": 1, "coverage_status": "under_covered", "distinct_rated_opponents": 11, "draws": 7, "generated_at": "2026-07-02T16:51:45Z", "losses": 9, "model": "gpt-5", "point_rating_method": "sequential_elo", "public_id": "E-cc568b7069d5a0fd", "rated_matches": 21, "raw_elo_rating": 1451.3965923614944, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 33.03750091731303, "uncertainty": 62.850358177805205, "unilateral_faults": 1, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 26, "generated_at": "2026-07-02T16:51:45Z", "losses": 11, "model": "gpt-5", "point_rating_method": "sequential_elo", "public_id": "E-e724ba162431d43a", "rated_matches": 42, "raw_elo_rating": 1435.8623185574695, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 34.51782318989246, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 2, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 24, "generated_at": "2026-07-02T16:51:45Z", "losses": 19, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-496f83ad0bd69447", "rated_matches": 54, "raw_elo_rating": 1403.617820599916, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 30.256036000566052, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 7, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 14, "generated_at": "2026-07-02T16:51:45Z", "losses": 18, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-4b75acaf58f14113", "rated_matches": 44, "raw_elo_rating": 1458.1644256131383, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 38.52438727472494, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 2, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 29, "generated_at": "2026-07-02T16:51:45Z", "losses": 6, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-ebd456dc6b320c61", "rated_matches": 46, "raw_elo_rating": 1557.0056967199416, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 55.46990711066279, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 53, "generated_at": "2026-07-02T16:51:45Z", "losses": 1, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-35117a2e624d7970", "rated_matches": 54, "raw_elo_rating": 1502.2519514200912, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 46.949443459654866, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 7, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 18, "generated_at": "2026-07-01T00:15:48Z", "losses": 12, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-3e164d6fc6c16cbb", "rated_matches": 44, "raw_elo_rating": 1548.059725737291, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 53.73878477740568, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 13, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 25, "generated_at": "2026-07-02T06:10:40Z", "losses": 9, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-7cbcc752e71e2d3b", "rated_matches": 40, "raw_elo_rating": 1468.4407340067614, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 39.782777329950335, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 9, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 34, "generated_at": "2026-07-02T16:51:45Z", "losses": 7, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-9e39bdd48b7328c7", "rated_matches": 52, "raw_elo_rating": 1527.160673130626, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 50.99449899363607, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 20, "generated_at": "2026-07-01T00:15:48Z", "losses": 12, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-a51cd55f211305c2", "rated_matches": 44, "raw_elo_rating": 1520.2960001548722, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 49.03989221480356, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 20, "generated_at": "2026-07-02T06:10:40Z", "losses": 9, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-dfa5098ec9c3cf47", "rated_matches": 48, "raw_elo_rating": 1537.458648607366, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 52.36527852981392, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 4, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 24, "generated_at": "2026-07-01T00:15:48Z", "losses": 15, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-0ad5302188ed9e2f", "rated_matches": 48, "raw_elo_rating": 1411.064865920198, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 30.973667967146064, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 9, "generated_at": "2026-07-01T00:15:48Z", "losses": 22, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-0ecb5b73c09f13b2", "rated_matches": 44, "raw_elo_rating": 1410.58480410516, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 30.471738541701946, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 3, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 13, "generated_at": "2026-07-02T06:10:40Z", "losses": 23, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-6c4158c55a35d268", "rated_matches": 48, "raw_elo_rating": 1425.7024844756863, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 33.451022699687655, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 32, "generated_at": "2026-07-02T06:10:40Z", "losses": 17, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-e4eac938bdd5d40e", "rated_matches": 58, "raw_elo_rating": 1427.2699988546833, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 34.57393560929241, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 20, "generated_at": "2026-07-09T17:30:50Z", "losses": 14, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-f2a7b43bf689e68e", "rated_matches": 50, "raw_elo_rating": 1515.3938290892593, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 48.822429192164726, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 2, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 19, "generated_at": "2026-07-02T16:51:45Z", "losses": 8, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-446036823932df16", "rated_matches": 42, "raw_elo_rating": 1532.8195170122888, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 50.9274169728892, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 2, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 19, "generated_at": "2026-07-02T16:51:45Z", "losses": 13, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-c002b0ea38b845f8", "rated_matches": 40, "raw_elo_rating": 1471.7215759387857, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 40.338045883793995, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 2, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 20, "generated_at": "2026-07-02T16:51:45Z", "losses": 10, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-e53a932f820d9724", "rated_matches": 39, "raw_elo_rating": 1525.5179367164974, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 49.31150841617975, "uncertainty": 35.30694150420948, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 15, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 32, "generated_at": "2026-07-10T05:30:29Z", "losses": 4, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-0300c20cb034e3a4", "rated_matches": 40, "raw_elo_rating": 1487.0489962766576, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 42.932146636436144, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 2, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 17, "generated_at": "2026-07-10T10:07:13Z", "losses": 20, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-3bca3b4e02f2acf9", "rated_matches": 46, "raw_elo_rating": 1409.5840570079213, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 30.519421112195783, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 19, "generated_at": "2026-07-10T05:30:29Z", "losses": 13, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-d192bb239087b778", "rated_matches": 46, "raw_elo_rating": 1482.3818845275205, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 42.8401440385904, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 3, "generated_at": "2026-07-10T05:30:29Z", "losses": 13, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-2ac4e83a1b9ba989", "rated_matches": 44, "raw_elo_rating": 1596.3466678596478, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 61.911144518391616, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 7, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 24, "generated_at": "2026-07-10T05:30:29Z", "losses": 16, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-527999604d620080", "rated_matches": 54, "raw_elo_rating": 1492.4298015489974, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 45.28708633683153, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 2, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 12, "generated_at": "2026-07-10T05:30:29Z", "losses": 9, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-b741de451c385e8e", "rated_matches": 44, "raw_elo_rating": 1594.5085265402074, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 61.60004691193783, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 11, "generated_at": "2026-07-10T05:30:29Z", "losses": 13, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-39e763b7d49209b4", "rated_matches": 42, "raw_elo_rating": 1548.5258455371809, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 53.585646325873974, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 10, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 23, "generated_at": "2026-07-10T10:07:13Z", "losses": 18, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-c2f0f8f062659e83", "rated_matches": 54, "raw_elo_rating": 1507.1274179692712, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 47.77459545300492, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 24, "generated_at": "2026-07-10T05:30:29Z", "losses": 8, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-e44c62bb88a3042a", "rated_matches": 38, "raw_elo_rating": 1504.641480334261, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 45.64189418693135, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 18, "generated_at": "2026-07-24T13:40:00Z", "losses": 22, "model": "inclusionai/ling-3.0-flash", "point_rating_method": "sequential_elo", "public_id": "E-2524de3c7d4a81b7", "rated_matches": 50, "raw_elo_rating": 1393.4427143645798, "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": 28.182721301387136, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 20, "generated_at": "2026-07-24T13:40:00Z", "losses": 19, "model": "inclusionai/ling-3.0-flash", "point_rating_method": "sequential_elo", "public_id": "E-641ddca04b054d56", "rated_matches": 46, "raw_elo_rating": 1394.77694351092, "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": 28.013380081134617, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 23, "generated_at": "2026-07-24T13:40:00Z", "losses": 18, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-198e8ddfe9f7ce20", "rated_matches": 48, "raw_elo_rating": 1423.0454733711274, "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": 33.00133486219263, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-3dc5f5cc9bb215b7", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 5, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 23, "generated_at": "2026-07-24T13:40:00Z", "losses": 14, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-84709c769628f9a2", "rated_matches": 52, "raw_elo_rating": 1451.745342784988, "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": 38.23077483798092, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 20, "generated_at": "2026-07-02T16:51:45Z", "losses": 11, "model": "minimax/minimax-m3", "point_rating_method": "sequential_elo", "public_id": "E-44cc758f104a74ab", "rated_matches": 52, "raw_elo_rating": 1537.2180654375327, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 52.69666989897096, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 30, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 15, "draws": 9, "generated_at": "2026-07-24T14:00:00Z", "losses": 3, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-09859be1b47131a0", "rated_matches": 30, "raw_elo_rating": 1621.3908495614658, "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": 64.08265893453343, "uncertainty": 46.05265101338746, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 18, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 9, "draws": 7, "generated_at": "2026-07-21T14:43:57Z", "losses": 1, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-0d3d2270a391a708", "rated_matches": 18, "raw_elo_rating": 1615.5137739533775, "reasoning": "high", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 59.715907303989454, "uncertainty": 70.95786693528086, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugin_count": 1, "attempted_matches": 30, "capped_draws": 2, "coverage_status": "under_covered", "distinct_rated_opponents": 15, "draws": 14, "generated_at": "2026-07-21T14:20:15Z", "losses": 4, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-a12d08354d94b221", "rated_matches": 30, "raw_elo_rating": 1575.2218077884422, "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": 56.26874482687114, "uncertainty": 46.05265101338746, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugin_count": 1, "attempted_matches": 20, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 10, "draws": 4, "generated_at": "2026-07-24T14:00:00Z", "losses": 8, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-b97350a867368460", "rated_matches": 20, "raw_elo_rating": 1515.952994031412, "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": 43.623743400869515, "uncertainty": 65.3589451179962, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 26, "capped_draws": 2, "coverage_status": "under_covered", "distinct_rated_opponents": 13, "draws": 16, "generated_at": "2026-07-02T16:51:45Z", "losses": 7, "model": "nex-agi/nex-n2-pro", "point_rating_method": "sequential_elo", "public_id": "E-57ad2863cbf32d58", "rated_matches": 26, "raw_elo_rating": 1476.5001108946622, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 38.690946889939994, "uncertainty": 52.475044864937615, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 2, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 27, "generated_at": "2026-07-02T16:51:45Z", "losses": 13, "model": "nex-agi/nex-n2-pro", "point_rating_method": "sequential_elo", "public_id": "E-a05d4cef5f788f16", "rated_matches": 46, "raw_elo_rating": 1424.386156653482, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 33.02461357020887, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 30, "capped_draws": 4, "coverage_status": "under_covered", "distinct_rated_opponents": 15, "draws": 18, "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": 30, "raw_elo_rating": 1419.261890549445, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 29.873191643532166, "uncertainty": 46.05265101338746, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 30, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 15, "draws": 19, "generated_at": "2026-07-21T14:20:15Z", "losses": 9, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-08888c30d05ca8cb", "rated_matches": 30, "raw_elo_rating": 1439.6140997468228, "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": 33.31771655594664, "uncertainty": 46.05265101338746, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 4, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 28, "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": 46, "raw_elo_rating": 1431.961147134627, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 34.30664851641847, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 30, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 15, "draws": 21, "generated_at": "2026-07-21T14:20:15Z", "losses": 5, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-c90a449ff5e7b79a", "rated_matches": 30, "raw_elo_rating": 1478.271732610354, "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": 39.860356628188114, "uncertainty": 46.05265101338746, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-08762a3df1a52f6b", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 15, "generated_at": "2026-07-24T13:40:00Z", "losses": 18, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-467272d131a1a99b", "rated_matches": 50, "raw_elo_rating": 1447.2211361430434, "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": 37.28449063609493, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 7, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 30, "generated_at": "2026-07-24T13:40:00Z", "losses": 13, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-91efdb0c216f8504", "rated_matches": 52, "raw_elo_rating": 1503.2618584047368, "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": 46.94972616813319, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-936fb7956df3d03b", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 3, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 39, "generated_at": "2026-07-02T16:51:45Z", "losses": 7, "model": "qwen/qwen3.7-max", "point_rating_method": "sequential_elo", "public_id": "E-3325ebad2ef000c1", "rated_matches": 50, "raw_elo_rating": 1441.1397761187798, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 36.25524629697736, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 6, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 21, "generated_at": "2026-07-21T14:20:15Z", "losses": 10, "model": "stepfun/step-3.7-flash", "point_rating_method": "sequential_elo", "public_id": "E-02b2a2f01700292d", "rated_matches": 40, "raw_elo_rating": 1522.423633843672, "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": 48.91915370704513, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 23, "generated_at": "2026-07-02T16:51:45Z", "losses": 20, "model": "tencent/hy3-preview", "point_rating_method": "sequential_elo", "public_id": "E-2346cd049910cc0a", "rated_matches": 68, "raw_elo_rating": 1436.7909872054654, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 36.848972779507136, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 4, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 25, "generated_at": "2026-07-24T13:40:00Z", "losses": 14, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-78048b7c08122f1c", "rated_matches": 48, "raw_elo_rating": 1439.021547101438, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 35.70521744481249, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 8, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 20, "generated_at": "2026-07-24T13:40:00Z", "losses": 12, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-adf1f0bb193bd39b", "rated_matches": 48, "raw_elo_rating": 1607.2650933940686, "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": 64.17972264165327, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 30, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 15, "draws": 6, "generated_at": "2026-07-24T14:00:00Z", "losses": 22, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-02f7e54245bd5c85", "rated_matches": 30, "raw_elo_rating": 1311.9892901970238, "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": 11.717759928482549, "uncertainty": 46.05265101338746, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 5, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 29, "generated_at": "2026-07-17T22:36:00Z", "losses": 14, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-09ef87ab56d05a09", "rated_matches": 54, "raw_elo_rating": 1491.5322019169912, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 45.135171413796165, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 1, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 25, "generated_at": "2026-07-21T14:20:15Z", "losses": 6, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-3c1904811d11cd84", "rated_matches": 38, "raw_elo_rating": 1513.251425681494, "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": 47.09909084580285, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 18, "capped_draws": 2, "coverage_status": "under_covered", "distinct_rated_opponents": 9, "draws": 9, "generated_at": "2026-07-24T14:00:00Z", "losses": 5, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-c0c60ca46f3ce498", "rated_matches": 18, "raw_elo_rating": 1496.1192712489474, "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": 39.50889513237049, "uncertainty": 70.95786693528086, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 4, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 22, "generated_at": "2026-07-24T14:00:00Z", "losses": 15, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-cbed46472ce4dd05", "rated_matches": 60, "raw_elo_rating": 1541.5973937371334, "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": 54.06905016019426, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 7, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 19, "generated_at": "2026-07-17T22:36:00Z", "losses": 9, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-d5ed477108214e1c", "rated_matches": 42, "raw_elo_rating": 1542.807683594637, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 52.6178717185429, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 20, "capped_draws": 1, "coverage_status": "under_covered", "distinct_rated_opponents": 10, "draws": 10, "generated_at": "2026-07-02T16:51:45Z", "losses": 5, "model": "x-ai/grok-build-0.1", "point_rating_method": "sequential_elo", "public_id": "E-2a93343a8a88fd59", "rated_matches": 20, "raw_elo_rating": 1527.633626050185, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 45.60064072888019, "uncertainty": 65.3589451179962, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 2, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 28, "generated_at": "2026-07-02T16:51:45Z", "losses": 9, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-b10e12eb6aef112e", "rated_matches": 46, "raw_elo_rating": 1525.5217643839485, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 50.14138536541297, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 4, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 28, "generated_at": "2026-07-02T16:51:45Z", "losses": 8, "model": "xiaomi/mimo-v2.5-pro", "point_rating_method": "sequential_elo", "public_id": "E-b0948c64dddf57ad", "rated_matches": 46, "raw_elo_rating": 1457.46717560364, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 38.62343543749571, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugin_count": 1, "attempted_matches": 30, "capped_draws": 6, "coverage_status": "under_covered", "distinct_rated_opponents": 15, "draws": 19, "generated_at": "2026-07-11T17:22:09Z", "losses": 6, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-40aa28533b1afda1", "rated_matches": 30, "raw_elo_rating": 1483.8175424040835, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 40.79896136680666, "uncertainty": 46.05265101338746, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 28, "capped_draws": 1, "coverage_status": "under_covered", "distinct_rated_opponents": 14, "draws": 21, "generated_at": "2026-07-02T16:51:45Z", "losses": 4, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-4cab1ccd88bbeb2e", "rated_matches": 28, "raw_elo_rating": 1495.177496689084, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 42.309300256585786, "uncertainty": 49.09766908852594, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 4, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 16, "generated_at": "2026-07-11T14:00:45Z", "losses": 8, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-583be34ca1fb2631", "rated_matches": 32, "raw_elo_rating": 1500.5343821590034, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 44.002427693233535, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 16, "generated_at": "2026-07-19T14:50:00Z", "losses": 14, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-714519b339aeb2e2", "rated_matches": 50, "raw_elo_rating": 1550.5281831108805, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 54.7687692938897, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 7, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 22, "generated_at": "2026-07-11T15:43:48Z", "losses": 17, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-bd2653f21938737f", "rated_matches": 46, "raw_elo_rating": 1432.4628967056365, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 34.391567498941406, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 28, "capped_draws": 5, "coverage_status": "under_covered", "distinct_rated_opponents": 14, "draws": 9, "generated_at": "2026-07-02T06:10:40Z", "losses": 14, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-f1af7b938699d971", "rated_matches": 28, "raw_elo_rating": 1362.9330880482946, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 19.927496115666777, "uncertainty": 49.09766908852594, "unilateral_faults": 0, "wins": 5 } ], "GB2-04": [ { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 9, "generated_at": "2026-07-03T17:50:00Z", "losses": 1, "model": "claude-fable-5", "point_rating_method": "sequential_elo", "public_id": "E-0ca15b39b465b370", "rated_matches": 56, "raw_elo_rating": 1821.193278726695, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 100.0, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 46 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 24, "generated_at": "2026-07-02T16:51:45Z", "losses": 15, "model": "claude-fable-5", "point_rating_method": "sequential_elo", "public_id": "E-eb1f17ce19beffd0", "rated_matches": 56, "raw_elo_rating": 1566.7841216373108, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 49.32044382130511, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "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": "medium", "reasoning_policy_version": "legacy_reasoning_presets_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": 52, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 33, "generated_at": "2026-07-02T16:51:45Z", "losses": 11, "model": "claude-opus-4-5", "point_rating_method": "sequential_elo", "public_id": "E-9a77e43e752532c8", "rated_matches": 52, "raw_elo_rating": 1529.4343084381378, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 41.48915163819359, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 43, "losses": 12, "model": "claude-opus-4-5", "point_rating_method": "sequential_elo", "public_id": "E-cbae2963ded72d76", "rated_matches": 60, "raw_elo_rating": 1448.2115010457887, "reasoning": "legacy_shared_thinking_budget", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "legacy_shared_thinking_budget", "repair_status": "first_pass", "score": 26.052098160972545, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "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": "highest", "reasoning_policy_version": "legacy_reasoning_presets_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": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 17, "losses": 11, "model": "claude-opus-4-5", "point_rating_method": "sequential_elo", "public_id": "E-f40463f635c43598", "rated_matches": 32, "raw_elo_rating": 1424.5955289820936, "reasoning": "legacy_shared_thinking_budget", "reasoning_bracket": "intensive", "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "legacy_shared_thinking_budget", "repair_status": "first_pass", "score": 17.67906062855609, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 30, "generated_at": "2026-07-03T17:20:00Z", "losses": 10, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-6344242dae68be1b", "rated_matches": 66, "raw_elo_rating": 1579.7087489959974, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 52.71452593995635, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 34, "generated_at": "2026-07-02T16:51:45Z", "losses": 7, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-688a139ef8557587", "rated_matches": 44, "raw_elo_rating": 1481.9095702707032, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 31.08886348521295, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 40, "generated_at": "2026-07-02T16:51:45Z", "losses": 6, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-caf91ab5b69b1e64", "rated_matches": 50, "raw_elo_rating": 1471.7037725606615, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 29.776397542600765, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 28, "generated_at": "2026-07-25T15:48:00Z", "losses": 10, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-048d3dcf802043b4", "rated_matches": 52, "raw_elo_rating": 1542.4583062266756, "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": 44.083596095880694, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 10, "generated_at": "2026-07-25T15:48:00Z", "losses": 8, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-4c98514bdb0eaf10", "rated_matches": 40, "raw_elo_rating": 1641.4937123917894, "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": 62.31286376346142, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 22 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 26, "generated_at": "2026-07-25T15:48:00Z", "losses": 13, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-72e9307528761b35", "rated_matches": 54, "raw_elo_rating": 1518.397463557121, "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": 39.49140350885056, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 11, "generated_at": "2026-07-25T15:48:00Z", "losses": 16, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-9e7782014171d35f", "rated_matches": 50, "raw_elo_rating": 1606.4301741361776, "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": 56.614559798689946, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 10, "generated_at": "2026-07-25T15:48:00Z", "losses": 3, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-a02883202d334eec", "rated_matches": 40, "raw_elo_rating": 1753.0553776456218, "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": 84.5364965379449, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 27 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 17, "generated_at": "2026-07-25T15:48:00Z", "losses": 14, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-d0f0a2b1c4bbddae", "rated_matches": 48, "raw_elo_rating": 1533.973142353106, "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": 41.95533146404428, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 43, "generated_at": "2026-07-03T16:50:00Z", "losses": 8, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-8e980ad934b3251e", "rated_matches": 62, "raw_elo_rating": 1533.6717755962163, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 43.23945167121127, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 32, "generated_at": "2026-07-02T16:51:45Z", "losses": 7, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-b1fc5b99a5deb881", "rated_matches": 46, "raw_elo_rating": 1487.5701896988592, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 32.47196362002854, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 29, "generated_at": "2026-07-02T16:51:45Z", "losses": 1, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-be938b7d5557f479", "rated_matches": 34, "raw_elo_rating": 1527.3928154870323, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 38.55892538039321, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 18, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 9, "draws": 12, "generated_at": "2026-07-02T16:51:45Z", "losses": 4, "model": "cohere/north-mini-code", "point_rating_method": "sequential_elo", "public_id": "E-1460cf3cd86be35c", "rated_matches": 18, "raw_elo_rating": 1479.047030105418, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 24.11662065009035, "uncertainty": 70.95786693528086, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 33, "generated_at": "2026-07-01T00:15:48Z", "losses": 4, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-5d143d6301429619", "rated_matches": 38, "raw_elo_rating": 1471.716990074414, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 28.177411381216853, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 24, "generated_at": "2026-07-02T16:51:45Z", "losses": 19, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-81bc9a578754f220", "rated_matches": 44, "raw_elo_rating": 1349.6267070996366, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 4.737466105277937, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 63, "generated_at": "2026-07-01T00:15:48Z", "losses": 1, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-a43d18fadfcc5a89", "rated_matches": 66, "raw_elo_rating": 1508.500571188575, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 38.52950646636151, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 56, "generated_at": "2026-07-02T06:10:40Z", "losses": 0, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-cb48b9466ec54175", "rated_matches": 56, "raw_elo_rating": 1506.2532248930593, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 37.26239128422888, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 22, "generated_at": "2026-07-02T16:51:45Z", "losses": 19, "model": "deepseek/deepseek-v4-pro", "point_rating_method": "sequential_elo", "public_id": "E-38bc194a470fbf62", "rated_matches": 48, "raw_elo_rating": 1440.733349521438, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 23.38150584800255, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 18, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 9, "draws": 14, "generated_at": "2026-07-02T16:51:45Z", "losses": 4, "model": "google/gemini-3.1-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-2be6f5c895691cb3", "rated_matches": 18, "raw_elo_rating": 1450.1042275565585, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 18.351071939009746, "uncertainty": 70.95786693528086, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 36, "generated_at": "2026-07-02T16:51:45Z", "losses": 2, "model": "google/gemini-3.1-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-860c31323fa5eda7", "rated_matches": 42, "raw_elo_rating": 1497.0294371743323, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 33.82771565073253, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 32, "generated_at": "2026-07-02T16:51:45Z", "losses": 8, "model": "google/gemini-3.5-flash", "point_rating_method": "sequential_elo", "public_id": "E-32cfa6c9dfb1d16f", "rated_matches": 52, "raw_elo_rating": 1535.795958549268, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 42.75642364948741, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "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": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 7, "generated_at": "2026-07-02T16:51:45Z", "losses": 16, "model": "google/gemini-3.5-flash", "point_rating_method": "sequential_elo", "public_id": "E-8e95359e4cbd1851", "rated_matches": 32, "raw_elo_rating": 1479.715243612519, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 28.659179057173933, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 50, "generated_at": "2026-07-24T13:40:00Z", "losses": 4, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-2fe680857b884561", "rated_matches": 61, "raw_elo_rating": 1505.7253482509934, "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": 37.5917500959702, "uncertainty": 19.750063500095248, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 48, "generated_at": "2026-07-24T13:40:00Z", "losses": 11, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-5c270e2afa7b70f5", "rated_matches": 63, "raw_elo_rating": 1472.9002203129974, "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": 31.212197117191156, "uncertainty": 18.75, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-6a79049fd9ab6f5d", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-6c734fef813f984b", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-b05b0185d0e8dc2a", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-d7f1cd65263dbed7", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-0b528ba96380a3b5", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 63, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 37, "generated_at": "2026-07-24T13:40:00Z", "losses": 10, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-1ff96286ae16ecd4", "rated_matches": 62, "raw_elo_rating": 1499.79460936863, "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": 36.49095343062815, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-846809faa1345207", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-ccfb6c993d1622b0", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 46, "generated_at": "2026-07-24T13:40:00Z", "losses": 8, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-d109ab12db58a65f", "rated_matches": 62, "raw_elo_rating": 1478.0034412795826, "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": 32.15004550104347, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 24, "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": 32, "raw_elo_rating": 1517.6711255592445, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 36.22017754259853, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 41, "generated_at": "2026-07-02T16:51:45Z", "losses": 4, "model": "google/gemma-4-31b-it", "point_rating_method": "sequential_elo", "public_id": "E-ec0cf4b37c805eee", "rated_matches": 48, "raw_elo_rating": 1490.2406649219877, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 33.243606728345505, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 23, "generated_at": "2026-07-02T16:51:45Z", "losses": 9, "model": "gpt-4.1", "point_rating_method": "sequential_elo", "public_id": "E-ecb06954153be8d5", "rated_matches": 34, "raw_elo_rating": 1458.5374385455698, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 24.842595418716364, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 39, "generated_at": "2026-07-02T16:51:45Z", "losses": 7, "model": "gpt-5", "point_rating_method": "sequential_elo", "public_id": "E-6f1aae863396df76", "rated_matches": 60, "raw_elo_rating": 1548.729486332967, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 46.07577553411435, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 28, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 14, "draws": 21, "generated_at": "2026-07-02T16:51:45Z", "losses": 5, "model": "gpt-5", "point_rating_method": "sequential_elo", "public_id": "E-7e3da77777a95e31", "rated_matches": 28, "raw_elo_rating": 1469.1198423892715, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 25.622803197560856, "uncertainty": 49.09766908852594, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 40, "generated_at": "2026-07-02T16:51:45Z", "losses": 7, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-0b4132559ee98caf", "rated_matches": 58, "raw_elo_rating": 1513.1147492207922, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 38.809666551358085, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 49, "generated_at": "2026-07-02T16:51:45Z", "losses": 8, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-8d62bf1b340a70dc", "rated_matches": 68, "raw_elo_rating": 1494.2473590945217, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 35.83231653302763, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 27, "generated_at": "2026-07-02T16:51:45Z", "losses": 13, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-9279285adff8ed29", "rated_matches": 68, "raw_elo_rating": 1617.3769690127422, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 60.360340816834494, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 36, "generated_at": "2026-07-02T06:10:40Z", "losses": 12, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-040a4b654fceeb0c", "rated_matches": 56, "raw_elo_rating": 1477.865432695363, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 31.60740336660926, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 42, "generated_at": "2026-07-02T16:51:45Z", "losses": 12, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-0880cdf1a43cb90c", "rated_matches": 70, "raw_elo_rating": 1490.3720877432415, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 35.19641529069496, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 37, "generated_at": "2026-07-01T00:15:48Z", "losses": 5, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-6d633c9c2680eb32", "rated_matches": 54, "raw_elo_rating": 1554.4248661845468, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 46.66823942277007, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 31, "generated_at": "2026-07-02T16:51:45Z", "losses": 7, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-74f5bcc8ad3796a5", "rated_matches": 56, "raw_elo_rating": 1565.0718297202598, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 48.979346844304295, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 52, "generated_at": "2026-07-02T06:10:40Z", "losses": 4, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-c9bf6a0be0c43fd1", "rated_matches": 62, "raw_elo_rating": 1469.9760007329758, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 30.55093983673764, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 48, "generated_at": "2026-07-02T06:10:40Z", "losses": 6, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-f9e13a78abccfd1f", "rated_matches": 64, "raw_elo_rating": 1528.4438868136224, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 42.35368309302285, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 35, "generated_at": "2026-07-01T00:15:48Z", "losses": 7, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-ff4778924359442b", "rated_matches": 48, "raw_elo_rating": 1471.8616369261956, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 29.582413898343336, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 15, "generated_at": "2026-07-09T17:30:50Z", "losses": 21, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-3403c285ceec6345", "rated_matches": 66, "raw_elo_rating": 1532.0327204441571, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 43.21722641263964, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 30 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 41, "generated_at": "2026-07-01T00:15:48Z", "losses": 12, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-48f60c9100c65daa", "rated_matches": 58, "raw_elo_rating": 1472.887750806737, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 30.796250488236097, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 34, "generated_at": "2026-07-09T17:30:50Z", "losses": 8, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-a32cb67d48c62b3b", "rated_matches": 58, "raw_elo_rating": 1559.1494715097724, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 47.98000979334802, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 26, "generated_at": "2026-07-02T06:10:40Z", "losses": 22, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-bbf36865f2b7fe63", "rated_matches": 56, "raw_elo_rating": 1377.564471203454, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 11.626958201577812, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 46, "generated_at": "2026-07-02T06:10:40Z", "losses": 8, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-c8f4bd9fcf2e481e", "rated_matches": 60, "raw_elo_rating": 1501.6481606432203, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 36.69694374378444, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 43, "generated_at": "2026-07-01T00:15:48Z", "losses": 13, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-fd2be90162c92ecf", "rated_matches": 70, "raw_elo_rating": 1532.7044940450228, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 43.62923896691468, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 40, "generated_at": "2026-07-02T16:51:45Z", "losses": 13, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-64bf5daf186f8119", "rated_matches": 64, "raw_elo_rating": 1470.1339268004403, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 30.738052083219, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 40, "generated_at": "2026-07-02T16:51:45Z", "losses": 13, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-9e7bdad81107b7e4", "rated_matches": 62, "raw_elo_rating": 1454.5510147312568, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 27.47820671040979, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 46, "generated_at": "2026-07-02T16:51:45Z", "losses": 12, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-ba1aa87056709e9a", "rated_matches": 64, "raw_elo_rating": 1496.2226687102534, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 35.93505786860947, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 59, "generated_at": "2026-07-10T05:30:29Z", "losses": 1, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-5389e160269f5ceb", "rated_matches": 62, "raw_elo_rating": 1512.834046928935, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 39.08847356683884, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 42, "generated_at": "2026-07-10T05:30:29Z", "losses": 11, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-71a01107bf3f9fc1", "rated_matches": 60, "raw_elo_rating": 1496.0402265733064, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 35.57981567734945, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 33, "generated_at": "2026-07-10T05:30:29Z", "losses": 15, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-e348813cda8b38b7", "rated_matches": 60, "raw_elo_rating": 1515.0969212350349, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 39.376003042374144, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 26, "generated_at": "2026-07-10T05:30:29Z", "losses": 2, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-270a233119b6cc62", "rated_matches": 54, "raw_elo_rating": 1653.7320041970793, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 66.45071005956129, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 50, "generated_at": "2026-07-10T05:30:29Z", "losses": 4, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-c81bf4d15f3d48f1", "rated_matches": 58, "raw_elo_rating": 1489.7668442731074, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 34.15864897798004, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 45, "generated_at": "2026-07-10T10:07:13Z", "losses": 4, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-f0b7195272d6417e", "rated_matches": 52, "raw_elo_rating": 1480.2355614499472, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 31.688519104226355, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 37, "draws": 69, "generated_at": "2026-07-10T05:30:29Z", "losses": 1, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-50ee0aadbc66fe0e", "rated_matches": 74, "raw_elo_rating": 1520.6818659965604, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 41.48990096796995, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 49, "generated_at": "2026-07-10T05:30:29Z", "losses": 5, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-89c18d144e85d89f", "rated_matches": 62, "raw_elo_rating": 1510.4667796354577, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 38.61690227136209, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 27, "generated_at": "2026-07-10T05:30:29Z", "losses": 12, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-b85c80e7475ef9ec", "rated_matches": 58, "raw_elo_rating": 1560.7829388596697, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 48.305404528632984, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "inclusionai/ling-3.0-flash", "point_rating_method": "sequential_elo", "public_id": "E-20e94e7276184071", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 55, "generated_at": "2026-07-24T13:40:00Z", "losses": 4, "model": "inclusionai/ling-3.0-flash", "point_rating_method": "sequential_elo", "public_id": "E-f38039bb8cc277a1", "rated_matches": 60, "raw_elo_rating": 1477.6032838196008, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 31.907085942540736, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-46a1c9f4e3ff6058", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-4ccf296e55b59be3", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 34, "generated_at": "2026-07-24T13:40:00Z", "losses": 11, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-9e1d4bf411e97fa6", "rated_matches": 60, "raw_elo_rating": 1569.103382231883, "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": 50.13435586825387, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 20, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 10, "draws": 19, "generated_at": "2026-07-02T16:51:45Z", "losses": 1, "model": "minimax/minimax-m3", "point_rating_method": "sequential_elo", "public_id": "E-c60620c3c72a6064", "rated_matches": 20, "raw_elo_rating": 1485.2635116292065, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 26.247240589417363, "uncertainty": 65.3589451179962, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 22, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 11, "draws": 17, "generated_at": "2026-07-02T16:51:45Z", "losses": 3, "model": "moonshotai/kimi-k2.7-code", "point_rating_method": "sequential_elo", "public_id": "E-eb97811a38950c20", "rated_matches": 22, "raw_elo_rating": 1477.805603453178, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 25.53478066069057, "uncertainty": 60.5072070285374, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 20, "generated_at": "2026-07-21T14:43:57Z", "losses": 8, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-0f7ca9245c7db7c7", "rated_matches": 40, "raw_elo_rating": 1503.1676826710195, "reasoning": "high", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 34.7576378651005, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugin_count": 1, "attempted_matches": 30, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 15, "draws": 15, "generated_at": "2026-07-17T22:36:00Z", "losses": 7, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-2a7239d6b25916b0", "rated_matches": 30, "raw_elo_rating": 1533.727851065557, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "score": 38.97830256660651, "uncertainty": 46.05265101338746, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 27, "generated_at": "2026-07-24T14:00:00Z", "losses": 6, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-35e5c9532c697b2c", "rated_matches": 36, "raw_elo_rating": 1479.9223016926098, "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": 29.47164141744014, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 19, "generated_at": "2026-07-24T14:00:00Z", "losses": 6, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-3c06949f23d4a77f", "rated_matches": 32, "raw_elo_rating": 1514.4819621397323, "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": 35.584880493815724, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 11, "generated_at": "2026-07-24T14:00:00Z", "losses": 7, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-601725df2c678708", "rated_matches": 32, "raw_elo_rating": 1573.848549836008, "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": 47.41099693833408, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 8, "generated_at": "2026-07-17T22:36:00Z", "losses": 10, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-6f3da6d3b01bcfad", "rated_matches": 32, "raw_elo_rating": 1540.2303591629875, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "score": 40.71408790278068, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 28, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 14, "draws": 18, "generated_at": "2026-07-21T14:20:15Z", "losses": 5, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-818ed7ee27b56509", "rated_matches": 28, "raw_elo_rating": 1503.0402498423114, "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": 32.379915303068024, "uncertainty": 49.09766908852594, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 45, "generated_at": "2026-07-11T17:22:09Z", "losses": 3, "model": "nex-agi/nex-n2-pro", "point_rating_method": "sequential_elo", "public_id": "E-6f4b3b55e4ec7cf5", "rated_matches": 50, "raw_elo_rating": 1491.333286691229, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 33.686693364975824, "uncertainty": 26.26400420140049, "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, "generated_at": "2026-07-11T17:22:09Z", "losses": 5, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-958dea26b779a042", "rated_matches": 32, "raw_elo_rating": 1453.741817911068, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 23.485144828023245, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 27, "generated_at": "2026-07-02T16:51:45Z", "losses": 6, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-f36b99b3d76fbb35", "rated_matches": 38, "raw_elo_rating": 1495.9623564264125, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 33.00720768323213, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 44, "generated_at": "2026-07-02T16:51:45Z", "losses": 7, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-7e92e17a121661f4", "rated_matches": 54, "raw_elo_rating": 1460.2028298284708, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 27.89874606250913, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 28, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 14, "draws": 15, "generated_at": "2026-07-21T14:20:15Z", "losses": 8, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-a4643af0a1bcc24c", "rated_matches": 28, "raw_elo_rating": 1468.27005544933, "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": 25.45352145685857, "uncertainty": 49.09766908852594, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 21, "generated_at": "2026-07-02T16:51:45Z", "losses": 9, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-3a27113d21c73b01", "rated_matches": 34, "raw_elo_rating": 1458.9537932238363, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 24.925535319735957, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 36, "generated_at": "2026-07-02T16:51:45Z", "losses": 4, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-f1288f2abfdbbfe4", "rated_matches": 44, "raw_elo_rating": 1480.001540532111, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 30.70877457082836, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 22, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 11, "draws": 11, "generated_at": "2026-07-21T14:20:15Z", "losses": 10, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-f6de1ce39e48807c", "rated_matches": 22, "raw_elo_rating": 1422.0102326087713, "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": 14.420068188974202, "uncertainty": 60.5072070285374, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-e996fd38983e3b7f", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 24, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 12, "draws": 14, "generated_at": "2026-07-02T16:51:45Z", "losses": 6, "model": "qwen/qwen3.7-max", "point_rating_method": "sequential_elo", "public_id": "E-ea08328e287de1ad", "rated_matches": 24, "raw_elo_rating": 1494.484627206166, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "first_pass", "score": 29.53576955257776, "uncertainty": 56.25, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 34, "generated_at": "2026-07-02T16:51:45Z", "losses": 3, "model": "qwen/qwen3.7-plus", "point_rating_method": "sequential_elo", "public_id": "E-84b9a07f75f324e2", "rated_matches": 40, "raw_elo_rating": 1508.141304108455, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 35.74840773334668, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 42, "generated_at": "2026-07-02T16:51:45Z", "losses": 3, "model": "stepfun/step-3.7-flash", "point_rating_method": "sequential_elo", "public_id": "E-25e56c6bfae33c62", "rated_matches": 50, "raw_elo_rating": 1526.1505400202454, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 40.6224615828462, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 24, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 12, "draws": 13, "generated_at": "2026-07-21T14:20:15Z", "losses": 3, "model": "stepfun/step-3.7-flash", "point_rating_method": "sequential_elo", "public_id": "E-fa23ca0bdb2bc960", "rated_matches": 24, "raw_elo_rating": 1529.6913005047602, "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": 36.549112144936515, "uncertainty": 56.25, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 33, "generated_at": "2026-07-02T16:51:45Z", "losses": 6, "model": "tencent/hy3-preview", "point_rating_method": "sequential_elo", "public_id": "E-3fd10f7865cc280e", "rated_matches": 48, "raw_elo_rating": 1517.8546980180151, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 38.74445802482134, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 18, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 9, "draws": 11, "generated_at": "2026-07-02T16:51:45Z", "losses": 6, "model": "tencent/hy3-preview", "point_rating_method": "sequential_elo", "public_id": "E-51c104b34ef2a244", "rated_matches": 18, "raw_elo_rating": 1437.608554413027, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 15.86187235078222, "uncertainty": 70.95786693528086, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 28, "generated_at": "2026-07-24T13:40:00Z", "losses": 16, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-646ff33c7bab8b13", "rated_matches": 50, "raw_elo_rating": 1434.9202660770147, "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": 22.44894201932177, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 47, "generated_at": "2026-07-24T13:40:00Z", "losses": 5, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-7ca32267720b2e1a", "rated_matches": 56, "raw_elo_rating": 1499.9771522139858, "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": 36.0121667185741, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 40, "generated_at": "2026-07-24T13:40:00Z", "losses": 12, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-d9e91f86e4e39739", "rated_matches": 58, "raw_elo_rating": 1445.7739527166314, "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": 25.39504846686978, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 52, "generated_at": "2026-07-24T13:40:00Z", "losses": 6, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-ddc16fa197bfc7c5", "rated_matches": 62, "raw_elo_rating": 1510.686655827679, "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": 38.66070269098349, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 14, "generated_at": "2026-07-24T14:00:00Z", "losses": 12, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-07caaa12175b0b3c", "rated_matches": 34, "raw_elo_rating": 1490.9811128639078, "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": 31.30553501598018, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 47, "generated_at": "2026-07-17T22:36:00Z", "losses": 6, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-1a7064508fe2a12f", "rated_matches": 62, "raw_elo_rating": 1503.5559184005565, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 37.2402247012451, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 26, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 13, "draws": 19, "generated_at": "2026-07-21T14:20:15Z", "losses": 3, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-436af9e9ba989a11", "rated_matches": 26, "raw_elo_rating": 1528.1630099942583, "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": 36.846260866909006, "uncertainty": 52.475044864937615, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 35, "generated_at": "2026-07-24T14:00:00Z", "losses": 4, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-617354569710a53d", "rated_matches": 44, "raw_elo_rating": 1529.164083365473, "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": 40.50219505897332, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 24, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 12, "draws": 15, "generated_at": "2026-07-17T22:36:00Z", "losses": 9, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-70da8ff73f18e636", "rated_matches": 24, "raw_elo_rating": 1401.3535350181637, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 10.983597639729526, "uncertainty": 56.25, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 40, "generated_at": "2026-07-17T22:36:00Z", "losses": 9, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-83f4cc0ffc20bde5", "rated_matches": 56, "raw_elo_rating": 1504.184417188392, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 36.8502746077259, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 82, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 41, "draws": 58, "generated_at": "2026-07-24T14:00:00Z", "losses": 12, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-ba6a8e6d7fc9a48d", "rated_matches": 82, "raw_elo_rating": 1504.4453110108711, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 38.71014819221992, "uncertainty": 11.132129994845172, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugin_count": 1, "attempted_matches": 20, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 10, "draws": 11, "generated_at": "2026-07-17T22:36:00Z", "losses": 6, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-dac812d348a29158", "rated_matches": 20, "raw_elo_rating": 1465.4677734092577, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 22.30383211035796, "uncertainty": 65.3589451179962, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 22, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 11, "draws": 18, "generated_at": "2026-07-02T16:51:45Z", "losses": 3, "model": "x-ai/grok-build-0.1", "point_rating_method": "sequential_elo", "public_id": "E-85934b32572399da", "rated_matches": 22, "raw_elo_rating": 1479.2974345534708, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 25.831960757984973, "uncertainty": 60.5072070285374, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 30, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 15, "draws": 23, "generated_at": "2026-07-02T06:10:40Z", "losses": 5, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-00e6914e513b1656", "rated_matches": 30, "raw_elo_rating": 1468.7641962381597, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 26.03722280334275, "uncertainty": 46.05265101338746, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 30, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 15, "draws": 19, "generated_at": "2026-07-01T00:15:48Z", "losses": 10, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-23e877112cb95491", "rated_matches": 30, "raw_elo_rating": 1420.0369437120878, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 16.33051428671147, "uncertainty": 46.05265101338746, "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, "generated_at": "2026-07-02T16:51:45Z", "losses": 4, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-2f7e15b8aa123825", "rated_matches": 26, "raw_elo_rating": 1460.9897364084577, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 23.46501417222989, "uncertainty": 52.475044864937615, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 39, "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": 54, "raw_elo_rating": 1491.3499007385865, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 34.10339587956107, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 44, "generated_at": "2026-07-02T06:10:40Z", "losses": 2, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-d58c55e107783a21", "rated_matches": 48, "raw_elo_rating": 1507.84708305417, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 36.750891871081286, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 28, "generated_at": "2026-07-02T06:10:40Z", "losses": 6, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-f8929b12716a2221", "rated_matches": 38, "raw_elo_rating": 1495.7904116780787, "reasoning": "highest", "reasoning_bracket": "highest", "reasoning_setting": "highest", "repair_status": "repaired", "score": 32.97295544313002, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 30, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 15, "draws": 13, "generated_at": "2026-07-02T16:51:45Z", "losses": 8, "model": "xiaomi/mimo-v2.5-pro", "point_rating_method": "sequential_elo", "public_id": "E-ffdebde8a72ed049", "rated_matches": 30, "raw_elo_rating": 1489.28005979839, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 30.12408379431653, "uncertainty": 46.05265101338746, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 25, "generated_at": "2026-07-02T16:51:45Z", "losses": 5, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-1d5f5ff0402ff944", "rated_matches": 36, "raw_elo_rating": 1540.7272314478314, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 41.58428267896779, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 34, "generated_at": "2026-07-02T06:10:40Z", "losses": 1, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-3efc86009429a22c", "rated_matches": 36, "raw_elo_rating": 1496.826980032491, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 32.83913653990452, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 80, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 40, "draws": 57, "generated_at": "2026-07-11T15:43:48Z", "losses": 12, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-6d59400949b2dde9", "rated_matches": 80, "raw_elo_rating": 1514.0198533112462, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 40.51012439121856, "uncertainty": 11.805555555555554, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 24, "generated_at": "2026-07-11T17:22:09Z", "losses": 8, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-912f31ad14c4bf0a", "rated_matches": 38, "raw_elo_rating": 1467.1029555456405, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 27.2582729948998, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 11, "generated_at": "2026-07-01T00:15:48Z", "losses": 12, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-947248ef34168cde", "rated_matches": 34, "raw_elo_rating": 1520.0418361385473, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 37.09457411598848, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 28, "generated_at": "2026-07-01T00:15:48Z", "losses": 6, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-e6dc2409fc5fe917", "rated_matches": 38, "raw_elo_rating": 1486.5884066146955, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 31.139870746408565, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 16, "generated_at": "2026-07-11T14:00:45Z", "losses": 11, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-f776c26a98306f5d", "rated_matches": 38, "raw_elo_rating": 1506.0505372159496, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 35.01682294595854, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 25, "generated_at": "2026-07-02T06:10:40Z", "losses": 16, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-f9359f32abb5e3c8", "rated_matches": 50, "raw_elo_rating": 1438.9648484544537, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 23.25464273450773, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 9 } ], "GB2-05": [ { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 8, "model": "claude-fable-5", "point_rating_method": "sequential_elo", "public_id": "E-5aa4402ccce7b855", "rated_matches": 64, "raw_elo_rating": 1895.2246300132751, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 92.451262399467, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 56 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 24, "model": "claude-fable-5", "point_rating_method": "sequential_elo", "public_id": "E-ad7cf41c05ec3f64", "rated_matches": 54, "raw_elo_rating": 1564.6835482433685, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 52.452932914118634, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 30 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "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": "highest", "reasoning_policy_version": "legacy_reasoning_presets_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": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 24, "model": "claude-opus-4-5", "point_rating_method": "sequential_elo", "public_id": "E-934b5bc34a7e20b9", "rated_matches": 62, "raw_elo_rating": 1523.974286932912, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 48.01327090561448, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 38 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 0, "losses": 20, "model": "claude-opus-4-5", "point_rating_method": "sequential_elo", "public_id": "E-a75e9d71efa4a6bc", "rated_matches": 40, "raw_elo_rating": 1498.5786407549515, "reasoning": "legacy_shared_thinking_budget", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "legacy_shared_thinking_budget", "repair_status": "first_pass", "score": 43.53761331209199, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 0, "losses": 20, "model": "claude-opus-4-5", "point_rating_method": "sequential_elo", "public_id": "E-ccacc93776fb7c88", "rated_matches": 42, "raw_elo_rating": 1490.7358118120442, "reasoning": "legacy_shared_thinking_budget", "reasoning_bracket": "intensive", "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "legacy_shared_thinking_budget", "repair_status": "first_pass", "score": 42.776408543684546, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 22 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "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": "medium", "reasoning_policy_version": "legacy_reasoning_presets_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": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 28, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-233f9cae6335e53d", "rated_matches": 56, "raw_elo_rating": 1426.356743667632, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 36.044276212350354, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 35, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-6774d700e60de31a", "rated_matches": 64, "raw_elo_rating": 1538.3667950040874, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 49.82574174672981, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 28, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-924d7e6ee41b562e", "rated_matches": 60, "raw_elo_rating": 1525.7692733725237, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 48.12979094866205, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 0, "generated_at": "2026-07-25T10:50:00Z", "losses": 15, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-09963ffe0b0fa5fd", "rated_matches": 58, "raw_elo_rating": 1817.924552575232, "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": 82.92397813412782, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 43 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 0, "generated_at": "2026-07-25T10:50:00Z", "losses": 17, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-32c377b229530444", "rated_matches": 56, "raw_elo_rating": 1760.302528451473, "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": 75.93302615623676, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 39 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 0, "generated_at": "2026-07-25T10:50:00Z", "losses": 0, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-3f3686d02d1503fa", "rated_matches": 40, "raw_elo_rating": 1971.2777366099735, "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": 34.33688094430304, "unilateral_faults": 0, "wins": 40 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 0, "generated_at": "2026-07-25T10:50:00Z", "losses": 12, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-a35dfc1adc62e4eb", "rated_matches": 40, "raw_elo_rating": 1739.552877541597, "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": 72.32121086617754, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 0, "generated_at": "2026-07-25T10:50:00Z", "losses": 14, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-b53cb955b1d8baab", "rated_matches": 56, "raw_elo_rating": 1810.6684408918225, "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": 81.94907240856237, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 42 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 0, "generated_at": "2026-07-25T10:50:00Z", "losses": 11, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-d7111b534ebcaba2", "rated_matches": 56, "raw_elo_rating": 1820.5237005744175, "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": 83.1262514808048, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 45 }, { "admitted_plugin_count": 1, "attempted_matches": 76, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 38, "draws": 0, "generated_at": "2026-07-03T16:50:00Z", "losses": 38, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-c902807aab849f31", "rated_matches": 76, "raw_elo_rating": 1549.2728597100909, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 51.609766414462925, "uncertainty": 13.230288229818967, "unilateral_faults": 0, "wins": 38 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 27, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-e0a09b1ea3f11175", "rated_matches": 62, "raw_elo_rating": 1520.9036581003338, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 47.646494167430816, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 35 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 27, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-e619c51e7d5d70d2", "rated_matches": 46, "raw_elo_rating": 1435.9565657354813, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 36.55014764549661, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 16, "model": "cohere/north-mini-code", "point_rating_method": "sequential_elo", "public_id": "E-a0518a43c688d1e2", "rated_matches": 38, "raw_elo_rating": 1495.2464344570433, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "first_pass", "score": 42.950656228503576, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 22 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 0, "generated_at": "2026-07-01T00:15:48Z", "losses": 27, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-06a41d0e11b18b77", "rated_matches": 46, "raw_elo_rating": 1416.3172699890229, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 34.20429693319734, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 41, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-0dca18c79b6ac9d7", "rated_matches": 64, "raw_elo_rating": 1452.4159035831772, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 39.55918420487605, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 28, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-2c1cbd253f3a9d69", "rated_matches": 48, "raw_elo_rating": 1370.0003984534594, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 28.81560673275056, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 57, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-b306c8f5ffbbec38", "rated_matches": 70, "raw_elo_rating": 1284.9234124510494, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 19.808674799193287, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 29, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-b3d889b0631db85f", "rated_matches": 70, "raw_elo_rating": 1558.4723377992989, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 52.48321413406782, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 41 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 39, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-b8554f0ccf0845da", "rated_matches": 62, "raw_elo_rating": 1411.6622811428792, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 34.597963035941035, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 0, "generated_at": "2026-07-01T00:15:48Z", "losses": 38, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-efa8d9109b008ee9", "rated_matches": 68, "raw_elo_rating": 1439.1921009936452, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 38.15398238039824, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 30 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 23, "model": "deepseek/deepseek-v4-pro", "point_rating_method": "sequential_elo", "public_id": "E-0ca4798825ceaccb", "rated_matches": 72, "raw_elo_rating": 1758.883007674556, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 76.49983872640665, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 49 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 39, "model": "deepseek/deepseek-v4-pro", "point_rating_method": "sequential_elo", "public_id": "E-da5f3b1a4e370e1a", "rated_matches": 70, "raw_elo_rating": 1407.767805319223, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 34.48204243070537, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 31 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 37, "model": "google/gemini-3.1-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-7603462aff103041", "rated_matches": 64, "raw_elo_rating": 1321.2599404656255, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 23.893026239049423, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 27 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 34, "model": "google/gemini-3.1-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-a72dd193e1dc4331", "rated_matches": 38, "raw_elo_rating": 1230.2869285583215, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 11.30209542127282, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 30, "model": "google/gemini-3.1-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-d979b43c3aeea657", "rated_matches": 46, "raw_elo_rating": 1305.284761574915, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 20.941820909912263, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-21T14:20:15Z", "losses": 0, "model": "google/gemini-3.5-flash", "point_rating_method": "sequential_elo", "public_id": "E-84cd6ee956650b32", "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": 74, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 37, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 40, "model": "google/gemini-3.5-flash", "point_rating_method": "sequential_elo", "public_id": "E-a7ce764239377b3f", "rated_matches": 74, "raw_elo_rating": 1469.3980693923404, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 41.99685872000467, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 18, "model": "google/gemini-3.5-flash", "point_rating_method": "sequential_elo", "public_id": "E-b50da126631c1ea1", "rated_matches": 38, "raw_elo_rating": 1495.28311322599, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 42.95503738948669, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-214f636367cbdac4", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-27023858537764ac", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-2aebd7296279d5e5", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-a870d09d3e1a40d4", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 34, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-c311887ca24f8a76", "rated_matches": 68, "raw_elo_rating": 1371.5676509074417, "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": 30.076459313809973, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 33, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-e3c1bc55ae62b8db", "rated_matches": 64, "raw_elo_rating": 1367.3874948935063, "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": 29.40281425834644, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 31 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-68cd3c6f37a30f06", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-9bef179ce22a6c93", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 15, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-9e479871cca0aeaa", "rated_matches": 72, "raw_elo_rating": 1811.4294073860576, "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": 82.77633717030919, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 57 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 37, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 39, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-c7d3f2597dfefeb3", "rated_matches": 74, "raw_elo_rating": 1599.0133940880332, "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": 57.47899238139743, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 35 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-e23af86eb5787555", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 38, "model": "google/gemma-4-31b-it", "point_rating_method": "sequential_elo", "public_id": "E-e8e17fbbdd12faa4", "rated_matches": 60, "raw_elo_rating": 1306.4883081561472, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 21.93738491295836, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 22 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 18, "model": "google/gemma-4-31b-it", "point_rating_method": "sequential_elo", "public_id": "E-fd1bc1e2e6ac48fb", "rated_matches": 32, "raw_elo_rating": 1490.3861000662391, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 41.70361565070743, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 28, "model": "gpt-4.1", "point_rating_method": "sequential_elo", "public_id": "E-1b9f1f7b70f02927", "rated_matches": 46, "raw_elo_rating": 1343.9306693331305, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 25.5579502972611, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 31, "model": "gpt-5", "point_rating_method": "sequential_elo", "public_id": "E-9e5b308c41a36374", "rated_matches": 58, "raw_elo_rating": 1567.8741951513823, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 53.05626716087649, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 27 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 14, "model": "gpt-5", "point_rating_method": "sequential_elo", "public_id": "E-c5ad048b6fb4e93d", "rated_matches": 38, "raw_elo_rating": 1612.8618408113805, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 56.99943823859395, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "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": 80, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 40, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 25, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-6d3546010ef68f50", "rated_matches": 80, "raw_elo_rating": 1744.8030888257304, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 75.10136719944344, "uncertainty": 11.805555555555554, "unilateral_faults": 0, "wins": 55 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 32, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-cafab3c275850d3b", "rated_matches": 64, "raw_elo_rating": 1525.8350202224913, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 48.32886155421666, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 4, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-f6403f7a30e19e82", "rated_matches": 64, "raw_elo_rating": 1931.051509970191, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 96.73066798261004, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 60 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 30, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-0791f6b66243ec1a", "rated_matches": 58, "raw_elo_rating": 1473.506918125209, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 41.784399427558654, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 37, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-427bdffeacc6c394", "rated_matches": 58, "raw_elo_rating": 1333.6735560249267, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 25.081754061810127, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 34, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-481582e8f8e3217e", "rated_matches": 64, "raw_elo_rating": 1546.876053971512, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 50.84214536260139, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 30 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 33, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-539afc540807da47", "rated_matches": 58, "raw_elo_rating": 1388.3021280033795, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 31.606961286242058, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 0, "generated_at": "2026-07-01T00:15:48Z", "losses": 26, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-8ed627956c0a0292", "rated_matches": 60, "raw_elo_rating": 1411.9678598975274, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 34.53657812130674, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 80, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 40, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 43, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-95d1a872f51b78e7", "rated_matches": 80, "raw_elo_rating": 1439.7622455160515, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 38.66521954952476, "uncertainty": 11.805555555555554, "unilateral_faults": 0, "wins": 37 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 40, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-cdd304da89074d54", "rated_matches": 70, "raw_elo_rating": 1386.5322565424424, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 31.945524427861, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 30 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 0, "generated_at": "2026-07-01T00:15:48Z", "losses": 32, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-ce84b7a3c6105fb2", "rated_matches": 56, "raw_elo_rating": 1420.6809546650486, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 35.3663214706702, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 0, "generated_at": "2026-07-09T17:30:50Z", "losses": 49, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-3311575b341ee4a8", "rated_matches": 70, "raw_elo_rating": 1344.61500478334, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 26.938643521021447, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 0, "generated_at": "2026-07-01T00:15:48Z", "losses": 46, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-49b3c6006a3b9fcc", "rated_matches": 68, "raw_elo_rating": 1391.6284739987418, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 32.472660111719044, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 22 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 35, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-54b9ca4996a5589d", "rated_matches": 69, "raw_elo_rating": 1568.89177719822, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 53.68742421303622, "uncertainty": 16.01143046671968, "unilateral_faults": 1, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 41, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-6c37eeef15b82287", "rated_matches": 58, "raw_elo_rating": 1289.8416048261813, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 19.846168465030985, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 45, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-83cfa14483bf0d43", "rated_matches": 58, "raw_elo_rating": 1265.5935646074108, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 16.94981804832515, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 16, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-8e40431df091d53f", "rated_matches": 68, "raw_elo_rating": 1741.0650102044026, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 74.21173049102529, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 52 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 0, "generated_at": "2026-07-09T17:30:50Z", "losses": 40, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-a0d8c8fd6b01598c", "rated_matches": 66, "raw_elo_rating": 1407.2421202586966, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 34.25244224396947, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 0, "generated_at": "2026-07-09T17:30:50Z", "losses": 23, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-b05a7e0987de9967", "rated_matches": 64, "raw_elo_rating": 1670.4608946585429, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 65.60395710462083, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 41 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 0, "generated_at": "2026-07-01T00:15:48Z", "losses": 40, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-ff2b4db95370e3d6", "rated_matches": 62, "raw_elo_rating": 1328.4399839095454, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 24.6573272939897, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 22 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 25, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-6f42dbbf02274b56", "rated_matches": 60, "raw_elo_rating": 1578.3209032811378, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 54.40691412278813, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 35 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 15, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-762e9d80a60b41ed", "rated_matches": 68, "raw_elo_rating": 1819.332270454036, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 83.56050300184323, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 53 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 21, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-ffa82d1e96e897ab", "rated_matches": 58, "raw_elo_rating": 1652.109166288075, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 63.117863543585464, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 37 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 31, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-25a83ddaeb1268a4", "rated_matches": 66, "raw_elo_rating": 1575.875340508706, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 54.39513803855472, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 35 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 53, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-59156a669808a24f", "rated_matches": 58, "raw_elo_rating": 1123.6908903432654, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 0.0, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 29, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-e917387a1c57aa23", "rated_matches": 54, "raw_elo_rating": 1566.3786416398286, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 52.65540636850494, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 25, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-471e9297eea18ffd", "rated_matches": 64, "raw_elo_rating": 1587.9373567546218, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 55.746785917192774, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 39 }, { "admitted_plugin_count": 1, "attempted_matches": 76, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 38, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 21, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-af9c2c2998294ad0", "rated_matches": 76, "raw_elo_rating": 1721.279849578368, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 72.15544813911, "uncertainty": 13.230288229818967, "unilateral_faults": 0, "wins": 55 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 20, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-d61f8454991c5422", "rated_matches": 60, "raw_elo_rating": 1639.493660691125, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 61.71380324937027, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 40 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 25, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-012ecb9ce0709c05", "rated_matches": 68, "raw_elo_rating": 1616.3524860198763, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 59.31522058212656, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 43 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 23, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-1f00b423eab1c19d", "rated_matches": 58, "raw_elo_rating": 1583.9989523111312, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 54.98231754257976, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 35 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 28, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-9664e98d37ece097", "rated_matches": 60, "raw_elo_rating": 1554.884848939414, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 51.6075528075571, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 56, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-067ab716d64e3e9a", "rated_matches": 72, "raw_elo_rating": 1252.5131973626942, "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": 16.015593489602008, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-52b991e608dc1672", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 42, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-8cc657b7db4428cb", "rated_matches": 68, "raw_elo_rating": 1350.9008543530088, "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": 27.60787693468351, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-9061c6162106c911", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 37, "model": "minimax/minimax-m3", "point_rating_method": "sequential_elo", "public_id": "E-33797d7b77c7800c", "rated_matches": 70, "raw_elo_rating": 1469.451876888559, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 41.85000638911461, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 33 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 28, "model": "minimax/minimax-m3", "point_rating_method": "sequential_elo", "public_id": "E-fb8ac45946e32e22", "rated_matches": 32, "raw_elo_rating": 1259.1865795370063, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 14.08757651577286, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 34, "model": "mistralai/mistral-medium-3-5", "point_rating_method": "sequential_elo", "public_id": "E-1954b83d439b455c", "rated_matches": 38, "raw_elo_rating": 1193.9561815045674, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 6.962504533968066, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 76, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 38, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 39, "model": "mistralai/mistral-medium-3-5", "point_rating_method": "sequential_elo", "public_id": "E-4a7d37b86196302f", "rated_matches": 76, "raw_elo_rating": 1441.2006518851858, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 38.70088877553203, "uncertainty": 13.230288229818967, "unilateral_faults": 0, "wins": 37 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 17, "model": "moonshotai/kimi-k2.7-code", "point_rating_method": "sequential_elo", "public_id": "E-952fba19b28982d5", "rated_matches": 32, "raw_elo_rating": 1544.771611656525, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 48.199790093512426, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 0, "generated_at": "2026-07-18T00:14:00Z", "losses": 27, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-288f9a63e6b6cae3", "rated_matches": 52, "raw_elo_rating": 1495.7378044213926, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "score": 44.09715494334264, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-24T14:00:00Z", "losses": 11, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-4419230379dcd41e", "rated_matches": 38, "raw_elo_rating": 1637.7681353062624, "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": 59.974415011480026, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 27 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 0, "generated_at": "2026-07-21T14:43:57Z", "losses": 18, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-4a1443311507f194", "rated_matches": 36, "raw_elo_rating": 1546.1994437538688, "reasoning": "high", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 48.832774381854, "uncertainty": 38.449493652678655, "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, "generated_at": "2026-07-21T14:20:15Z", "losses": 14, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-91be72471ad409b6", "rated_matches": 38, "raw_elo_rating": 1613.8418822581664, "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": 57.11650103736769, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 0, "generated_at": "2026-07-17T22:08:39Z", "losses": 20, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-95ac38f534c0080f", "rated_matches": 45, "raw_elo_rating": 1510.0302066011964, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "score": 45.32266046602105, "uncertainty": 29.97097807744857, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 24, "model": "nex-agi/nex-n2-pro", "point_rating_method": "sequential_elo", "public_id": "E-5f76f577111bee8d", "rated_matches": 32, "raw_elo_rating": 1336.8196578257846, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 23.360598031045697, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 76, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 38, "draws": 0, "generated_at": "2026-07-11T17:22:09Z", "losses": 42, "model": "nex-agi/nex-n2-pro", "point_rating_method": "sequential_elo", "public_id": "E-962a9da8812a74d4", "rated_matches": 76, "raw_elo_rating": 1459.739093474812, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 40.915245999404725, "uncertainty": 13.230288229818967, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 16, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-4477e0de2e04aad4", "rated_matches": 48, "raw_elo_rating": 1544.427991149785, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 49.650421679977455, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 30, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-48ed5c5e00ef38fb", "rated_matches": 38, "raw_elo_rating": 1302.325804098009, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 19.906907410444493, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-11T17:22:09Z", "losses": 25, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-da3b98638ff53ea9", "rated_matches": 38, "raw_elo_rating": 1359.3589379658868, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 26.719331818929053, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 32, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-343b92f3dda3dcb5", "rated_matches": 68, "raw_elo_rating": 1497.821508842899, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 45.157076581963906, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 36 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 0, "generated_at": "2026-07-03T16:00:00Z", "losses": 25, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-4fc62dc65156d576", "rated_matches": 46, "raw_elo_rating": 1463.867990376425, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 39.884077549121216, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-21T14:20:15Z", "losses": 12, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-b556333d605791f4", "rated_matches": 38, "raw_elo_rating": 1603.7314964969933, "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": 55.9088479755849, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-21T14:20:15Z", "losses": 19, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-172336d3fd38632a", "rated_matches": 38, "raw_elo_rating": 1430.2908983914597, "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": 35.1919263578203, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 29, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-5ef540286ecbb63d", "rated_matches": 62, "raw_elo_rating": 1447.33708487285, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 38.85920360288856, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 33 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 20, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-1ca53619662c7f6f", "rated_matches": 68, "raw_elo_rating": 1704.7305555195596, "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": 69.87169673911161, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 48 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 36, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-21623e96b2b104e9", "rated_matches": 64, "raw_elo_rating": 1390.6753030488358, "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": 32.1844680434074, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-53ce0020411c86d4", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-62e15a037ee860c1", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 19, "model": "qwen/qwen3.7-max", "point_rating_method": "sequential_elo", "public_id": "E-435ec29661cdc285", "rated_matches": 34, "raw_elo_rating": 1512.8093379384543, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 44.62312914680338, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 34, "model": "qwen/qwen3.7-max", "point_rating_method": "sequential_elo", "public_id": "E-c577c41440c17864", "rated_matches": 62, "raw_elo_rating": 1521.2856555640442, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 47.692122535876926, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 20, "model": "qwen/qwen3.7-plus", "point_rating_method": "sequential_elo", "public_id": "E-6cc7454f585005c4", "rated_matches": 44, "raw_elo_rating": 1491.7047630621466, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 43.055902071000624, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 37, "model": "qwen/qwen3.7-plus", "point_rating_method": "sequential_elo", "public_id": "E-94daaf1196d89c6c", "rated_matches": 70, "raw_elo_rating": 1416.7106818294349, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 35.55024026744643, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 33 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 22, "model": "stepfun/step-3.7-flash", "point_rating_method": "sequential_elo", "public_id": "E-358338a9fbdbcb6a", "rated_matches": 38, "raw_elo_rating": 1466.366711746241, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 39.50106623470973, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-21T14:20:15Z", "losses": 21, "model": "stepfun/step-3.7-flash", "point_rating_method": "sequential_elo", "public_id": "E-386b7a319dfe25ad", "rated_matches": 38, "raw_elo_rating": 1442.1903981687146, "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": 36.613283334610685, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 24, "model": "stepfun/step-3.7-flash", "point_rating_method": "sequential_elo", "public_id": "E-7b9b33921ba865f5", "rated_matches": 56, "raw_elo_rating": 1572.8040677708518, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 53.536938067285334, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 37, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 48, "model": "tencent/hy3-preview", "point_rating_method": "sequential_elo", "public_id": "E-1bb81f8a4ae78954", "rated_matches": 74, "raw_elo_rating": 1375.3160039220393, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 30.759058589728017, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 0, "generated_at": "2026-07-03T19:10:00Z", "losses": 20, "model": "tencent/hy3-preview", "point_rating_method": "sequential_elo", "public_id": "E-92dc0ac61d798488", "rated_matches": 46, "raw_elo_rating": 1502.7156411525352, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 44.52430449110435, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 36, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-01a1df4eac0e6aef", "rated_matches": 64, "raw_elo_rating": 1346.8039660609616, "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": 26.944177940790823, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 40, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-0f05573125dedc2b", "rated_matches": 72, "raw_elo_rating": 1434.6823288381802, "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": 37.77511034538186, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 42, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-ae60ed096a69eeff", "rated_matches": 68, "raw_elo_rating": 1386.8091340232932, "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": 31.897005451787702, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-e9202aa1565d1c4e", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 45, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-f7a1d86c7e241f8d", "rated_matches": 70, "raw_elo_rating": 1465.738774441627, "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": 41.40648824404333, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugin_count": 1, "attempted_matches": 84, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 42, "draws": 0, "generated_at": "2026-07-24T14:00:00Z", "losses": 31, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-824ec3caceabd338", "rated_matches": 84, "raw_elo_rating": 1646.441087627935, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 63.47875935949037, "uncertainty": 10.482614454664043, "unilateral_faults": 0, "wins": 53 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-18T00:06:00Z", "losses": 20, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-87d1c39ddc685d7b", "rated_matches": 38, "raw_elo_rating": 1525.5095353150684, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 46.56548629271222, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 0, "generated_at": "2026-07-18T00:06:00Z", "losses": 18, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-9f28818a3063ee74", "rated_matches": 64, "raw_elo_rating": 1747.574278013794, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 74.81490273154559, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 46 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 0, "generated_at": "2026-07-18T00:06:00Z", "losses": 23, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-bd7fcc801178eba2", "rated_matches": 48, "raw_elo_rating": 1508.4017122615546, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 45.34719853580299, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 0, "generated_at": "2026-07-18T00:06:00Z", "losses": 26, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-c0bc4ff29a3cbf96", "rated_matches": 66, "raw_elo_rating": 1704.3892195628102, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 69.74570756056913, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 40 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-24T14:00:00Z", "losses": 18, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-f1d32edccc2b8ba2", "rated_matches": 38, "raw_elo_rating": 1542.9348479566636, "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": 48.64688384382832, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-21T14:20:15Z", "losses": 3, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-fcfafa8fb4ccd299", "rated_matches": 38, "raw_elo_rating": 1809.7776787372047, "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": 80.52040175097464, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 35 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 17, "model": "x-ai/grok-build-0.1", "point_rating_method": "sequential_elo", "public_id": "E-4aac1b6621aeae38", "rated_matches": 38, "raw_elo_rating": 1585.890955890403, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 53.777852779521325, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 27, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-09d406abc15f7c9a", "rated_matches": 62, "raw_elo_rating": 1585.8100503760031, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 55.3993539704669, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 35 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 0, "generated_at": "2026-07-01T00:15:48Z", "losses": 39, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-9490f08c56c27d13", "rated_matches": 62, "raw_elo_rating": 1327.556766274441, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 24.55182978811308, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 18, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-ad48cf51fe7da3cc", "rated_matches": 38, "raw_elo_rating": 1473.798526608742, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 40.38877261756302, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 25, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-be8fc9653466bbe1", "rated_matches": 60, "raw_elo_rating": 1454.1567111139825, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 39.57590070979902, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 35 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 20, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-faaa866ee28d6401", "rated_matches": 34, "raw_elo_rating": 1432.3565317225514, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 35.01330019954669, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 22, "model": "xiaomi/mimo-v2.5-pro", "point_rating_method": "sequential_elo", "public_id": "E-9c228ad72a159b33", "rated_matches": 36, "raw_elo_rating": 1436.0176886705406, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 35.67191810770685, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 37, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 48, "model": "xiaomi/mimo-v2.5-pro", "point_rating_method": "sequential_elo", "public_id": "E-af55f57b03605914", "rated_matches": 74, "raw_elo_rating": 1340.6671312177457, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 26.62036218416104, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 0, "generated_at": "2026-07-01T00:15:48Z", "losses": 19, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-1a8c2012f200fd88", "rated_matches": 48, "raw_elo_rating": 1640.6299431856698, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 61.141435442457045, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 0, "generated_at": "2026-07-11T14:00:45Z", "losses": 40, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-235e4beedf22bc99", "rated_matches": 72, "raw_elo_rating": 1560.971808516761, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 52.859982516183955, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 0, "generated_at": "2026-07-11T14:00:45Z", "losses": 22, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-38e323f4ce233fa1", "rated_matches": 46, "raw_elo_rating": 1454.1707872831807, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 38.72577782812944, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 0, "generated_at": "2026-07-11T17:22:09Z", "losses": 25, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-3916ba303b2ff700", "rated_matches": 46, "raw_elo_rating": 1532.8948638592171, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 48.129115579907, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 39, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-503ecd021099d8f9", "rated_matches": 66, "raw_elo_rating": 1425.0310386049832, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 36.37727132706912, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 27 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 31, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-51c8f79c1671819e", "rated_matches": 72, "raw_elo_rating": 1572.3682314569317, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 54.22124858279859, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 41 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 0, "generated_at": "2026-07-01T00:15:48Z", "losses": 27, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-6370c4b68d38a97e", "rated_matches": 46, "raw_elo_rating": 1376.3332358443529, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 29.42833265271711, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 28, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-a6655b3c71893984", "rated_matches": 48, "raw_elo_rating": 1426.5839450762207, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 35.57432939078477, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 22, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-d8655d29a4806df8", "rated_matches": 46, "raw_elo_rating": 1579.0569863043886, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 53.64303263769047, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 24 } ], "GB2-06": [ { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 9, "generated_at": "2026-07-02T16:51:45Z", "losses": 11, "model": "claude-fable-5", "point_rating_method": "sequential_elo", "public_id": "E-499fbc92ee0778fb", "rated_matches": 58, "raw_elo_rating": 1703.812816431412, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 79.37424207225958, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 38 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 7, "generated_at": "2026-07-02T16:51:45Z", "losses": 13, "model": "claude-fable-5", "point_rating_method": "sequential_elo", "public_id": "E-e1ca3ac536f3eb1e", "rated_matches": 48, "raw_elo_rating": 1646.4648905020276, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 71.02490499954271, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 3, "losses": 17, "model": "claude-opus-4-5", "point_rating_method": "sequential_elo", "public_id": "E-1ff6d6f973c7157d", "rated_matches": 40, "raw_elo_rating": 1483.455953622267, "reasoning": "legacy_shared_thinking_budget", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "legacy_shared_thinking_budget", "repair_status": "first_pass", "score": 48.50651019158293, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 1, "generated_at": "2026-07-02T16:51:45Z", "losses": 34, "model": "claude-opus-4-5", "point_rating_method": "sequential_elo", "public_id": "E-40a259ca8a40b5b4", "rated_matches": 58, "raw_elo_rating": 1455.789381704686, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 46.195935526761325, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "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": "highest", "reasoning_policy_version": "legacy_reasoning_presets_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, "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": "medium", "reasoning_policy_version": "legacy_reasoning_presets_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": 46, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 6, "losses": 19, "model": "claude-opus-4-5", "point_rating_method": "sequential_elo", "public_id": "E-df9bde92610963b7", "rated_matches": 46, "raw_elo_rating": 1480.0600928572974, "reasoning": "legacy_shared_thinking_budget", "reasoning_bracket": "intensive", "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "legacy_shared_thinking_budget", "repair_status": "first_pass", "score": 48.60384820414883, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 1, "generated_at": "2026-07-02T16:51:45Z", "losses": 21, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-39e283268f14261d", "rated_matches": 58, "raw_elo_rating": 1681.0254506469776, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 76.32595670280091, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 36 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 3, "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": 60, "raw_elo_rating": 1494.5099950724373, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 51.49077663608371, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 3, "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": 56, "raw_elo_rating": 1701.9160659633524, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 78.99935188287517, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 37 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 11, "generated_at": "2026-07-25T10:50:00Z", "losses": 7, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-ca8985adf5006428", "rated_matches": 54, "raw_elo_rating": 1772.6067863963965, "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": 88.32799956129024, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 36 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 3, "generated_at": "2026-07-02T16:51:45Z", "losses": 32, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-01597b81edc004dd", "rated_matches": 68, "raw_elo_rating": 1480.3349355924784, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 50.00396058789727, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 33 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 1, "generated_at": "2026-07-02T16:51:45Z", "losses": 21, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-500304c7462c6005", "rated_matches": 40, "raw_elo_rating": 1508.2219156109704, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 51.81947406397143, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 82, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 41, "draws": 10, "generated_at": "2026-07-03T16:50:00Z", "losses": 33, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-51f3682dc3b76107", "rated_matches": 82, "raw_elo_rating": 1510.098396671887, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 54.55378800839192, "uncertainty": 11.132129994845172, "unilateral_faults": 0, "wins": 39 }, { "admitted_plugin_count": 1, "attempted_matches": 30, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 15, "draws": 1, "generated_at": "2026-07-02T16:51:45Z", "losses": 23, "model": "cohere/north-mini-code", "point_rating_method": "sequential_elo", "public_id": "E-78dfcb6ce8b3efaa", "rated_matches": 30, "raw_elo_rating": 1317.998444155539, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "first_pass", "score": 25.119335087150468, "uncertainty": 46.05265101338746, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 46, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-5f5fd61f4544b8d7", "rated_matches": 66, "raw_elo_rating": 1325.6338857012756, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 29.214032099678494, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 2, "generated_at": "2026-07-02T06:10:40Z", "losses": 23, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-6f20412107151172", "rated_matches": 40, "raw_elo_rating": 1383.6389637210625, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 35.153906261071285, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 0, "generated_at": "2026-07-01T00:15:48Z", "losses": 30, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-8daa317358045ed1", "rated_matches": 50, "raw_elo_rating": 1368.50660805525, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 33.993570618074976, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 0, "generated_at": "2026-07-01T00:15:48Z", "losses": 29, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-d8ca2fcf88af96c7", "rated_matches": 42, "raw_elo_rating": 1278.5777811236649, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 21.296435602250163, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 42, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-db0efb02339d9e80", "rated_matches": 56, "raw_elo_rating": 1217.0175055173588, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 14.134057602623102, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 41, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-f527097ad30176f4", "rated_matches": 58, "raw_elo_rating": 1343.8062559046955, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 31.215857213561456, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 6, "generated_at": "2026-07-02T16:51:45Z", "losses": 12, "model": "deepseek/deepseek-v4-pro", "point_rating_method": "sequential_elo", "public_id": "E-945bebaa34963e03", "rated_matches": 58, "raw_elo_rating": 1666.5668321788196, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 74.39181497022835, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 40 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 2, "generated_at": "2026-07-02T16:51:45Z", "losses": 34, "model": "deepseek/deepseek-v4-pro", "point_rating_method": "sequential_elo", "public_id": "E-c9778645f1bbd12c", "rated_matches": 62, "raw_elo_rating": 1417.6969290178033, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 41.325050962101, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 35, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 30, "model": "google/gemini-3.1-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-6238c7d8dc9e77d9", "rated_matches": 35, "raw_elo_rating": 1272.8334742113475, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 19.769903428463778, "uncertainty": 39.583333333333336, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 29, "model": "google/gemini-3.1-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-a10101fbca309818", "rated_matches": 52, "raw_elo_rating": 1429.7879988349669, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 42.33396509337835, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 1, "generated_at": "2026-07-02T16:51:45Z", "losses": 19, "model": "google/gemini-3.1-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-dc1c0f46738d1091", "rated_matches": 40, "raw_elo_rating": 1420.038975375964, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 40.02316688669191, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 11, "generated_at": "2026-07-02T16:51:45Z", "losses": 9, "model": "google/gemini-3.5-flash", "point_rating_method": "sequential_elo", "public_id": "E-35d6e87056063577", "rated_matches": 50, "raw_elo_rating": 1732.4144195081535, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 82.67382914279403, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 30 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 6, "generated_at": "2026-07-02T16:51:45Z", "losses": 11, "model": "google/gemini-3.5-flash", "point_rating_method": "sequential_elo", "public_id": "E-5dcb27eaa0273049", "rated_matches": 36, "raw_elo_rating": 1611.2604574466968, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 65.16290957666871, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-21T14:20:15Z", "losses": 0, "model": "google/gemini-3.5-flash", "point_rating_method": "sequential_elo", "public_id": "E-6537016fe84c175c", "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": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 1, "generated_at": "2026-07-24T13:40:00Z", "losses": 36, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-100ff33157ca87e5", "rated_matches": 60, "raw_elo_rating": 1333.6124881844505, "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": 29.96737981748139, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-3efea50fdbbd1829", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-46f1468c28505bfe", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-48cc2611d5aa8816", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 1, "generated_at": "2026-07-24T13:40:00Z", "losses": 33, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-92d447632fa55355", "rated_matches": 62, "raw_elo_rating": 1485.9208961239233, "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": 50.45142926942041, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-9c3a169358692b43", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-280a7de63c992141", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-5455742d003ec402", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-905531e52a8460f5", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 10, "generated_at": "2026-07-24T13:40:00Z", "losses": 24, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-aa5fab059f4d0186", "rated_matches": 64, "raw_elo_rating": 1553.219249586199, "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": 59.558511878686765, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 30 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-bb2e288b40b1a588", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 4, "generated_at": "2026-07-24T13:40:00Z", "losses": 12, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-dd9886be3d9e45b5", "rated_matches": 64, "raw_elo_rating": 1855.5383801769424, "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": 100.0, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 48 }, { "admitted_plugin_count": 1, "attempted_matches": 30, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 15, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 21, "model": "google/gemma-4-31b-it", "point_rating_method": "sequential_elo", "public_id": "E-41987f96551bf9d3", "rated_matches": 30, "raw_elo_rating": 1361.5388402568406, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 30.94377103431437, "uncertainty": 46.05265101338746, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 32, "model": "google/gemma-4-31b-it", "point_rating_method": "sequential_elo", "public_id": "E-da266f7bbd330107", "rated_matches": 56, "raw_elo_rating": 1400.355913354061, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 38.65939289391045, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 8, "generated_at": "2026-07-02T16:51:45Z", "losses": 16, "model": "gpt-4.1", "point_rating_method": "sequential_elo", "public_id": "E-4dcd6d3653c67437", "rated_matches": 42, "raw_elo_rating": 1498.497941533217, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 50.71534315686365, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 3, "generated_at": "2026-07-02T16:51:45Z", "losses": 15, "model": "gpt-5", "point_rating_method": "sequential_elo", "public_id": "E-1b082700b3692175", "rated_matches": 42, "raw_elo_rating": 1577.1374991955004, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 61.23502390233987, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 7, "generated_at": "2026-07-02T16:51:45Z", "losses": 25, "model": "gpt-5", "point_rating_method": "sequential_elo", "public_id": "E-816d262cd933cdb9", "rated_matches": 54, "raw_elo_rating": 1498.859087874097, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 51.70853629281069, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 22 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 6, "generated_at": "2026-07-02T16:51:45Z", "losses": 15, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-00a57c19a4229948", "rated_matches": 56, "raw_elo_rating": 1628.545670896392, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 69.18453151488029, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 35 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 11, "generated_at": "2026-07-02T16:51:45Z", "losses": 4, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-61f3ed920d3c145d", "rated_matches": 52, "raw_elo_rating": 1788.705954908835, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 90.34672640532096, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 37 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 8, "generated_at": "2026-07-02T16:51:45Z", "losses": 9, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-6e5bbab022d4d9fa", "rated_matches": 54, "raw_elo_rating": 1777.2678447386463, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 88.95151331383552, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 37 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 5, "generated_at": "2026-07-01T00:15:48Z", "losses": 37, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-050fceb6ddf16bc3", "rated_matches": 66, "raw_elo_rating": 1405.8139511588322, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 39.9397878877152, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 8, "generated_at": "2026-07-02T06:10:40Z", "losses": 16, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-0b7e07d12feb8fb5", "rated_matches": 56, "raw_elo_rating": 1629.298913714669, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 69.28529344955604, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 2, "generated_at": "2026-07-02T16:51:45Z", "losses": 33, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-144154b792c9e9a6", "rated_matches": 66, "raw_elo_rating": 1429.641609373582, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 43.127234063442, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 31 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 5, "generated_at": "2026-07-02T16:51:45Z", "losses": 19, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-3ccfe46cbdc271eb", "rated_matches": 54, "raw_elo_rating": 1503.7452804395457, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 52.36216644253991, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 30 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 0, "generated_at": "2026-07-01T00:15:48Z", "losses": 31, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-ac7c887de3c2e7af", "rated_matches": 66, "raw_elo_rating": 1575.0507387574512, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 62.5787374043566, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 35 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 1, "generated_at": "2026-07-02T06:10:40Z", "losses": 24, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-e726e4bfd20b0da9", "rated_matches": 54, "raw_elo_rating": 1371.968874884054, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 34.734324203353026, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 39, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-eca073d7ce610515", "rated_matches": 62, "raw_elo_rating": 1446.9959798754076, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 45.24441000136599, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 2, "generated_at": "2026-07-02T06:10:40Z", "losses": 21, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-3d7e23d6ea4c2792", "rated_matches": 58, "raw_elo_rating": 1603.5431286227667, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 65.96108035630274, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 35 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 2, "generated_at": "2026-07-02T16:51:45Z", "losses": 28, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-5ccde5c853d97bd9", "rated_matches": 56, "raw_elo_rating": 1576.3180575619283, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 62.19799910410298, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 5, "generated_at": "2026-07-02T06:10:40Z", "losses": 34, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-962a93f9cc008820", "rated_matches": 68, "raw_elo_rating": 1495.4760962529135, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 52.02940657206428, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 8, "generated_at": "2026-07-01T00:15:48Z", "losses": 29, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-9b6b064b63e4164b", "rated_matches": 56, "raw_elo_rating": 1506.4464307827188, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 52.85121195607604, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 2, "generated_at": "2026-07-09T17:30:50Z", "losses": 29, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-9c5263dcfd4c2ec7", "rated_matches": 62, "raw_elo_rating": 1488.9814231842397, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 50.860838586366015, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 31 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 0, "generated_at": "2026-07-09T17:30:50Z", "losses": 35, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-a1fb59d78d39d217", "rated_matches": 62, "raw_elo_rating": 1408.7464674466262, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 40.12774007871851, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 27 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 18, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-d5866895bf388f66", "rated_matches": 58, "raw_elo_rating": 1641.8873925366609, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 71.09042526598186, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 40 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 5, "generated_at": "2026-07-02T06:10:40Z", "losses": 19, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-f9bb09fb2842dd1f", "rated_matches": 56, "raw_elo_rating": 1691.0689393099397, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 77.54832249268348, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 32, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-1ea2c2c23d752166", "rated_matches": 58, "raw_elo_rating": 1448.0809451241314, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 45.16477138641322, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 7, "generated_at": "2026-07-02T16:51:45Z", "losses": 20, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-4175a77ccf4c269b", "rated_matches": 64, "raw_elo_rating": 1710.4157199319804, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 80.58681788029159, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 37 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 13, "generated_at": "2026-07-10T05:30:29Z", "losses": 15, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-9eafeacabdedfdba", "rated_matches": 56, "raw_elo_rating": 1674.3560486853933, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 75.31262484978316, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 45, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-ae522f9c5c491f57", "rated_matches": 54, "raw_elo_rating": 1184.250882263081, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 9.62312811760228, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 6, "generated_at": "2026-07-10T10:07:13Z", "losses": 24, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-f4c50b1a9cf2c2e6", "rated_matches": 58, "raw_elo_rating": 1591.7478127385095, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 64.38321088344401, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 84, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 42, "draws": 1, "generated_at": "2026-07-10T05:30:29Z", "losses": 49, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-992b9a5ebbb74c80", "rated_matches": 84, "raw_elo_rating": 1408.9987545376268, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 41.09911159247618, "uncertainty": 10.482614454664043, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 9, "generated_at": "2026-07-10T10:07:13Z", "losses": 13, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-acdece52463a2698", "rated_matches": 52, "raw_elo_rating": 1667.5084391584408, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 74.1340312841928, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 30 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 6, "generated_at": "2026-07-10T05:30:29Z", "losses": 21, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-eb315c759774ef38", "rated_matches": 56, "raw_elo_rating": 1674.4080128967423, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 75.31957614668558, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 1, "generated_at": "2026-07-10T05:30:29Z", "losses": 38, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-22ffdca36d9bac9c", "rated_matches": 62, "raw_elo_rating": 1357.4859927674747, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 33.27058263129217, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 9, "generated_at": "2026-07-10T05:30:29Z", "losses": 19, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-a3722334e358f0fe", "rated_matches": 56, "raw_elo_rating": 1496.011348653353, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 51.455302113536305, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 78, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 39, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 29, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-e6571a10c1120fab", "rated_matches": 78, "raw_elo_rating": 1632.355051545612, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 70.76130982029495, "uncertainty": 12.5043950463012, "unilateral_faults": 0, "wins": 49 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 3, "generated_at": "2026-07-24T13:40:00Z", "losses": 35, "model": "inclusionai/ling-3.0-flash", "point_rating_method": "sequential_elo", "public_id": "E-6807fffacebac165", "rated_matches": 64, "raw_elo_rating": 1385.9962675125475, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 37.18895084585539, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "inclusionai/ling-3.0-flash", "point_rating_method": "sequential_elo", "public_id": "E-6c37c8c2b8e19c4c", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "inclusionai/ling-3.0-flash", "point_rating_method": "sequential_elo", "public_id": "E-7f02a37922fd94e7", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 57, "model": "inclusionai/ling-3.0-flash", "point_rating_method": "sequential_elo", "public_id": "E-9bde0475193e2c4a", "rated_matches": 60, "raw_elo_rating": 1109.5922398363446, "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": 20.268439966447993, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 2, "generated_at": "2026-07-24T13:40:00Z", "losses": 38, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-3e8b2d11481a50d7", "rated_matches": 64, "raw_elo_rating": 1462.238800043231, "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": 47.38797949367356, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-9b849343b9780ba9", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-a9bdeb6a9326ac2d", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 10, "generated_at": "2026-07-24T13:40:00Z", "losses": 27, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-e3023ff7ecf82fc4", "rated_matches": 66, "raw_elo_rating": 1536.234820835545, "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": 57.38629893548021, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugin_count": 1, "attempted_matches": 30, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 15, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 21, "model": "minimax/minimax-m3", "point_rating_method": "sequential_elo", "public_id": "E-ef8c1a9fa3580f83", "rated_matches": 30, "raw_elo_rating": 1336.3094441421288, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 27.56881318335969, "uncertainty": 46.05265101338746, "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, "generated_at": "2026-07-02T16:51:45Z", "losses": 27, "model": "mistralai/mistral-medium-3-5", "point_rating_method": "sequential_elo", "public_id": "E-6c35f5ff426e7ada", "rated_matches": 34, "raw_elo_rating": 1300.921746746397, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 23.400792038637384, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 5, "generated_at": "2026-07-02T16:51:45Z", "losses": 32, "model": "mistralai/mistral-medium-3-5", "point_rating_method": "sequential_elo", "public_id": "E-cf0bc4a1e7a8d72a", "rated_matches": 60, "raw_elo_rating": 1331.884389148848, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 29.736210534597397, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 3, "generated_at": "2026-07-17T22:36:00Z", "losses": 8, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-026a38fa3b1622ee", "rated_matches": 36, "raw_elo_rating": 1660.204754074208, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "score": 71.71022990932427, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugin_count": 1, "attempted_matches": 30, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 15, "draws": 6, "generated_at": "2026-07-21T14:43:57Z", "losses": 2, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-13c9d1fee169a6f5", "rated_matches": 30, "raw_elo_rating": 1714.2525453020537, "reasoning": "high", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 78.12658439097301, "uncertainty": 46.05265101338746, "unilateral_faults": 0, "wins": 22 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 2, "generated_at": "2026-07-24T14:00:00Z", "losses": 13, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-1640f1438f9390d7", "rated_matches": 32, "raw_elo_rating": 1500.187292766553, "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": 49.786668032753, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 0, "generated_at": "2026-07-21T14:20:15Z", "losses": 5, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-2f8c760ee4329d00", "rated_matches": 34, "raw_elo_rating": 1749.2444896549302, "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": 83.37330799031281, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 3, "generated_at": "2026-07-17T22:36:00Z", "losses": 13, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-3f2124a8621f4c67", "rated_matches": 36, "raw_elo_rating": 1565.2453871015337, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "score": 59.00743434382783, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 2, "generated_at": "2026-07-24T14:00:00Z", "losses": 20, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-95a5c0e17cd4b70a", "rated_matches": 42, "raw_elo_rating": 1490.7850976149205, "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": 49.683589443184225, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 30, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 15, "draws": 3, "generated_at": "2026-07-02T16:51:45Z", "losses": 19, "model": "nex-agi/nex-n2-pro", "point_rating_method": "sequential_elo", "public_id": "E-209380b737b62580", "rated_matches": 30, "raw_elo_rating": 1350.0536939072658, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 29.40739320483244, "uncertainty": 46.05265101338746, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 2, "generated_at": "2026-07-11T17:22:09Z", "losses": 40, "model": "nex-agi/nex-n2-pro", "point_rating_method": "sequential_elo", "public_id": "E-973417dedd770061", "rated_matches": 62, "raw_elo_rating": 1338.9971736131567, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 30.7973175132515, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 4, "generated_at": "2026-07-02T16:51:45Z", "losses": 26, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-1ea0c8193f35ca72", "rated_matches": 62, "raw_elo_rating": 1555.945264596268, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 59.81864880409941, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 25, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-6e76a1c11ba24bc6", "rated_matches": 40, "raw_elo_rating": 1365.0587937088449, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 32.66842106080365, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 35, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 2, "generated_at": "2026-07-11T17:22:09Z", "losses": 19, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-ba2fb1c121873708", "rated_matches": 35, "raw_elo_rating": 1440.5408052205207, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 42.20425623178018, "uncertainty": 39.583333333333336, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 4, "generated_at": "2026-07-03T16:00:00Z", "losses": 15, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-4162fe183e6383e1", "rated_matches": 36, "raw_elo_rating": 1472.1905548712289, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 46.55941001629329, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 10, "generated_at": "2026-07-02T16:51:45Z", "losses": 24, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-69e964db7b91b1bb", "rated_matches": 60, "raw_elo_rating": 1533.5565018760735, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 56.714061176471255, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 1, "generated_at": "2026-07-21T14:20:15Z", "losses": 4, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-e4a4a86669325de4", "rated_matches": 34, "raw_elo_rating": 1750.2486128915534, "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": 83.5076304126712, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 2, "generated_at": "2026-07-02T16:51:45Z", "losses": 24, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-a97b527d9b41a80c", "rated_matches": 54, "raw_elo_rating": 1546.9530796525933, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 58.14211062009856, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 1, "generated_at": "2026-07-21T14:20:15Z", "losses": 29, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-b75de88bfc62ab22", "rated_matches": 48, "raw_elo_rating": 1467.99966969457, "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": 47.15146009630666, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 1, "generated_at": "2026-07-02T16:51:45Z", "losses": 34, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-f225b6990e542d31", "rated_matches": 54, "raw_elo_rating": 1369.2947045902554, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 34.37659816081083, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 2, "generated_at": "2026-07-24T13:40:00Z", "losses": 33, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-a29031412bc33c39", "rated_matches": 62, "raw_elo_rating": 1345.003199893997, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 31.60074877484011, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 27 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-b582570ce841ee30", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 32, "model": "qwen/qwen3.7-max", "point_rating_method": "sequential_elo", "public_id": "E-0c7e9f6c7d4cb892", "rated_matches": 52, "raw_elo_rating": 1354.7769806450185, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 32.299677169988506, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 2, "generated_at": "2026-07-02T16:51:45Z", "losses": 17, "model": "qwen/qwen3.7-max", "point_rating_method": "sequential_elo", "public_id": "E-8283efe6f68a787e", "rated_matches": 34, "raw_elo_rating": 1497.314614258339, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 49.67243354235248, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 44, "model": "qwen/qwen3.7-plus", "point_rating_method": "sequential_elo", "public_id": "E-2fb82a23fdec2792", "rated_matches": 60, "raw_elo_rating": 1347.1351283730276, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 31.776314936759203, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 5, "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": 32, "raw_elo_rating": 1547.6483336535148, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 56.1355719790718, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 24, "model": "stepfun/step-3.7-flash", "point_rating_method": "sequential_elo", "public_id": "E-2d684425ca56be18", "rated_matches": 36, "raw_elo_rating": 1376.6840179889298, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 33.78341906498985, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 1, "generated_at": "2026-07-02T16:51:45Z", "losses": 33, "model": "stepfun/step-3.7-flash", "point_rating_method": "sequential_elo", "public_id": "E-6526762dce98da7c", "rated_matches": 54, "raw_elo_rating": 1388.4103550666105, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 36.933715039786, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 0, "generated_at": "2026-07-21T14:20:15Z", "losses": 21, "model": "stepfun/step-3.7-flash", "point_rating_method": "sequential_elo", "public_id": "E-8a88dceef8a0239c", "rated_matches": 34, "raw_elo_rating": 1395.505080795559, "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": 36.05328535902041, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 29, "model": "tencent/hy3-preview", "point_rating_method": "sequential_elo", "public_id": "E-3627e3dbf7a48738", "rated_matches": 34, "raw_elo_rating": 1262.482587295157, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 18.2587528719364, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 39, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-02be9616e86c7055", "rated_matches": 64, "raw_elo_rating": 1418.0209855099072, "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": 41.47292470469752, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 35, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-0825a2443d50c563", "rated_matches": 62, "raw_elo_rating": 1356.7474097662753, "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": 33.17178175285869, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 27 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-56e54327930d2f64", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 12, "generated_at": "2026-07-17T22:36:00Z", "losses": 7, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-03c854e808265e3b", "rated_matches": 56, "raw_elo_rating": 1705.4947693431316, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 79.47807808832648, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 37 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 2, "generated_at": "2026-07-24T14:00:00Z", "losses": 16, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-14f0700d6ad1d367", "rated_matches": 34, "raw_elo_rating": 1539.4815378267888, "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": 55.31313889657064, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 80, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 40, "draws": 7, "generated_at": "2026-07-24T14:00:00Z", "losses": 41, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-3baaff3521870bef", "rated_matches": 80, "raw_elo_rating": 1483.7927030714934, "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": 50.96278515457614, "uncertainty": 11.805555555555554, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 4, "generated_at": "2026-07-24T14:00:00Z", "losses": 21, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-5a1e23bce371a184", "rated_matches": 44, "raw_elo_rating": 1506.7109073693723, "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": 51.99739158842913, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 2, "generated_at": "2026-07-17T22:36:00Z", "losses": 23, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-5bedcf6c046c3b54", "rated_matches": 52, "raw_elo_rating": 1561.0529470310196, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 59.89338924507642, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 27 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 3, "generated_at": "2026-07-17T22:36:00Z", "losses": 32, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-8cb8510a257ade6a", "rated_matches": 64, "raw_elo_rating": 1508.140720329728, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 53.52831854659575, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 1, "generated_at": "2026-07-21T14:20:15Z", "losses": 15, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-9eb453b88beb68a4", "rated_matches": 34, "raw_elo_rating": 1561.2596701251873, "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": 58.2264182412455, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 0, "generated_at": "2026-07-17T22:36:00Z", "losses": 21, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-cc9d4b5c56aea8b6", "rated_matches": 42, "raw_elo_rating": 1485.1406227167588, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 48.92852321863203, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 21, "model": "x-ai/grok-build-0.1", "point_rating_method": "sequential_elo", "public_id": "E-133675db0ee21fd5", "rated_matches": 36, "raw_elo_rating": 1406.828541437424, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 37.815877694328925, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 6, "generated_at": "2026-07-02T06:10:40Z", "losses": 18, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-51421c7ae2af8f7b", "rated_matches": 40, "raw_elo_rating": 1502.9248303375296, "reasoning": "highest", "reasoning_bracket": "highest", "reasoning_setting": "highest", "repair_status": "repaired", "score": 51.110878446006915, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 30, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 15, "draws": 3, "generated_at": "2026-07-02T16:51:45Z", "losses": 20, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-7b4c450b6850f156", "rated_matches": 30, "raw_elo_rating": 1351.5255739443542, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 29.60428785360836, "uncertainty": 46.05265101338746, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 28, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-d572bc902e0e416b", "rated_matches": 50, "raw_elo_rating": 1394.950915922396, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 37.53104825105106, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 22 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 34, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-d79ad8bc05d1b933", "rated_matches": 54, "raw_elo_rating": 1410.4158445729888, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 39.87740815221628, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 0, "generated_at": "2026-07-01T00:15:48Z", "losses": 22, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-ff7683792b6b3363", "rated_matches": 58, "raw_elo_rating": 1595.599320818678, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 64.89843040649872, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 36 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 0, "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": 34, "raw_elo_rating": 1534.1970432183366, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 54.6062275426075, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 32, "model": "xiaomi/mimo-v2.5-pro", "point_rating_method": "sequential_elo", "public_id": "E-6b662c734cdcff91", "rated_matches": 60, "raw_elo_rating": 1452.7547853739904, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 45.905146597643856, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 0, "generated_at": "2026-07-01T00:15:48Z", "losses": 33, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-18454080fac44f8c", "rated_matches": 40, "raw_elo_rating": 1201.0915329623122, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 10.734380648581704, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 4, "generated_at": "2026-07-11T14:00:45Z", "losses": 18, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-657c61c9039ce566", "rated_matches": 40, "raw_elo_rating": 1467.0377104482063, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 46.31022778960863, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 6, "generated_at": "2026-07-02T06:10:40Z", "losses": 19, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-6954e92d5890c32a", "rated_matches": 42, "raw_elo_rating": 1502.883231870553, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 51.30196718803007, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 3, "generated_at": "2026-07-02T06:10:40Z", "losses": 14, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-72584b5bdb2d01e3", "rated_matches": 40, "raw_elo_rating": 1673.3960713457311, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 73.91496184882483, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 7, "generated_at": "2026-07-11T17:22:09Z", "losses": 12, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-bc40affcf893e495", "rated_matches": 40, "raw_elo_rating": 1595.4337214549123, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 63.485871764918144, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 3, "generated_at": "2026-07-02T16:51:45Z", "losses": 16, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-ec1479c855f477b4", "rated_matches": 40, "raw_elo_rating": 1596.696441786834, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 63.65478694142105, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 6, "generated_at": "2026-07-11T14:00:45Z", "losses": 17, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-f94d63d03c820dac", "rated_matches": 54, "raw_elo_rating": 1623.151639774578, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 68.3352570412757, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 31 } ], "GB2-07": [ { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 25, "model": "claude-fable-5", "point_rating_method": "sequential_elo", "public_id": "E-babd82321b910e7b", "rated_matches": 62, "raw_elo_rating": 1604.4884389644276, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 61.59421983387494, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 37 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 15, "model": "claude-fable-5", "point_rating_method": "sequential_elo", "public_id": "E-bc12a8303ec2def7", "rated_matches": 56, "raw_elo_rating": 1721.3733595723618, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 76.52631679447857, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 41 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 31, "model": "claude-opus-4-5", "point_rating_method": "sequential_elo", "public_id": "E-ca22621c58b6f244", "rated_matches": 60, "raw_elo_rating": 1484.101949958685, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 45.759775387566016, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 0, "losses": 22, "model": "claude-opus-4-5", "point_rating_method": "sequential_elo", "public_id": "E-e7848fdc8b4ffd95", "rated_matches": 40, "raw_elo_rating": 1473.4992991593072, "reasoning": "legacy_shared_thinking_budget", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "legacy_shared_thinking_budget", "repair_status": "first_pass", "score": 42.90430696332293, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 0, "losses": 20, "model": "claude-opus-4-5", "point_rating_method": "sequential_elo", "public_id": "E-e8719bed57f17312", "rated_matches": 40, "raw_elo_rating": 1489.677650596856, "reasoning": "legacy_shared_thinking_budget", "reasoning_bracket": "intensive", "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "legacy_shared_thinking_budget", "repair_status": "first_pass", "score": 45.01785954122322, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "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": "medium", "reasoning_policy_version": "legacy_reasoning_presets_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, "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": "highest", "reasoning_policy_version": "legacy_reasoning_presets_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": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 19, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-0bf7b9ed307db853", "rated_matches": 56, "raw_elo_rating": 1655.5878327465305, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 67.93204374088673, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 37 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 0, "generated_at": "2026-07-03T17:20:00Z", "losses": 20, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-5e09cecd1172d99b", "rated_matches": 54, "raw_elo_rating": 1620.9004693099198, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 63.275737183469275, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 25, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-76804598cce96e62", "rated_matches": 62, "raw_elo_rating": 1585.6437673215585, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 59.132337083693706, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 37 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 0, "generated_at": "2026-07-25T10:50:00Z", "losses": 1, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-1e882072d8d97548", "rated_matches": 40, "raw_elo_rating": 1908.3795775583417, "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": 99.7174091533898, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 39 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 0, "generated_at": "2026-07-25T10:50:00Z", "losses": 4, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-54bca3ce32fa85ae", "rated_matches": 52, "raw_elo_rating": 1903.0174118422897, "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": 100.0, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 48 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 0, "generated_at": "2026-07-25T10:50:00Z", "losses": 18, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-914b104a64ab3110", "rated_matches": 52, "raw_elo_rating": 1741.5924576205412, "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": 78.91131680197287, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 0, "generated_at": "2026-07-25T10:50:00Z", "losses": 20, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-de5e72176c4f0dc9", "rated_matches": 54, "raw_elo_rating": 1759.1370608743762, "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": 81.3350744150181, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 0, "generated_at": "2026-07-03T16:50:00Z", "losses": 39, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-2146a36b46e938d6", "rated_matches": 66, "raw_elo_rating": 1412.1255644657329, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 36.6633342427911, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 27 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 30, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-9e40526fba9fa8b9", "rated_matches": 66, "raw_elo_rating": 1486.9450008445583, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 46.43780435774322, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 36 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 20, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-cd6f193a087d8c8d", "rated_matches": 44, "raw_elo_rating": 1563.6722330880127, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 55.05572388516481, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 18, "model": "cohere/north-mini-code", "point_rating_method": "sequential_elo", "public_id": "E-1c961fde1b53f0eb", "rated_matches": 36, "raw_elo_rating": 1490.616193888619, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 44.71065160481735, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 38, "model": "cohere/north-mini-code", "point_rating_method": "sequential_elo", "public_id": "E-3b908f26a42804a4", "rated_matches": 64, "raw_elo_rating": 1453.4820196031317, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 41.96870093034758, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 0, "generated_at": "2026-07-11T17:22:09Z", "losses": 52, "model": "cohere/north-mini-code", "point_rating_method": "sequential_elo", "public_id": "E-c7f5dc6d5d3c2a8d", "rated_matches": 66, "raw_elo_rating": 1225.971241468745, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 12.343986824956822, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 37, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-20285efe5ad468c1", "rated_matches": 64, "raw_elo_rating": 1415.1291155468884, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 36.958247328140686, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 27 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 0, "generated_at": "2026-07-01T00:15:48Z", "losses": 31, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-8f2f6c973751f183", "rated_matches": 42, "raw_elo_rating": 1396.5049366327746, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 33.03775475106972, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 0, "generated_at": "2026-07-01T00:15:48Z", "losses": 33, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-8f6a725b68dde85b", "rated_matches": 56, "raw_elo_rating": 1417.6779691835304, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 36.85131172795486, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 40, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-c394c0713cfcfaa4", "rated_matches": 72, "raw_elo_rating": 1435.8767573923717, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 40.03419471161385, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 36, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-c8fd55a5d257c569", "rated_matches": 68, "raw_elo_rating": 1430.6978152659915, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 39.18283162698061, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 25, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-ecf2a6ea6f9fe06c", "rated_matches": 60, "raw_elo_rating": 1614.4328114471043, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 62.78630181345937, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 35 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 26, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-edc2d085c4253ed3", "rated_matches": 44, "raw_elo_rating": 1483.83321482663, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 44.62549163840255, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 36, "model": "deepseek/deepseek-v4-pro", "point_rating_method": "sequential_elo", "public_id": "E-f398fd6ac8c8bada", "rated_matches": 70, "raw_elo_rating": 1591.3212202571904, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 60.25603724598094, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 30, "model": "deepseek/deepseek-v4-pro", "point_rating_method": "sequential_elo", "public_id": "E-f76d96b0f3163d4b", "rated_matches": 60, "raw_elo_rating": 1427.2591466449226, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 38.33378677910713, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 30 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 26, "model": "google/gemini-3.1-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-0d43f308cfa4da52", "rated_matches": 38, "raw_elo_rating": 1405.678612322642, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 33.83751705234364, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 46, "model": "google/gemini-3.1-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-1b3c52da51dfbdd4", "rated_matches": 56, "raw_elo_rating": 1176.6504298057089, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 5.363284090316728, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 38, "model": "google/gemini-3.1-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-3d6a15fe821fe6ad", "rated_matches": 42, "raw_elo_rating": 1143.6148913795123, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 0.0, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 26, "model": "google/gemini-3.5-flash", "point_rating_method": "sequential_elo", "public_id": "E-5447c508e2b0ab6c", "rated_matches": 54, "raw_elo_rating": 1476.3023229705768, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 44.38532142418434, "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, "generated_at": "2026-07-21T14:20:15Z", "losses": 0, "model": "google/gemini-3.5-flash", "point_rating_method": "sequential_elo", "public_id": "E-610847658aa43657", "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": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 20, "model": "google/gemini-3.5-flash", "point_rating_method": "sequential_elo", "public_id": "E-f7f306cca2bb9532", "rated_matches": 38, "raw_elo_rating": 1600.6146212924966, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 59.3041108443162, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 35, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-2950a4947ff48aa6", "rated_matches": 62, "raw_elo_rating": 1304.2873775939768, "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": 22.37571666331624, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 27 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-3e0523b11110a55d", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 42, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-42943e41c64d22d2", "rated_matches": 64, "raw_elo_rating": 1225.4888233208255, "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": 12.18349014380252, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 22 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-455ee67905f5f955", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-82a1dfc4206e9ddd", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-e2e240babaf0b862", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 30, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-5f208f03ea700603", "rated_matches": 66, "raw_elo_rating": 1496.1274992814167, "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": 47.63741318795713, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 36 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 26, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-65c6c8e09fe2c210", "rated_matches": 70, "raw_elo_rating": 1444.7694103173546, "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": 41.11039333473561, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 44 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-8e9b51be911dad38", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-a2d90fcdc2f4ef9d", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 36, "model": "google/gemma-4-31b-it", "point_rating_method": "sequential_elo", "public_id": "E-3f820f7e8ff15839", "rated_matches": 58, "raw_elo_rating": 1349.90531693581, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 28.115764310136107, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 22 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 17, "model": "google/gemma-4-31b-it", "point_rating_method": "sequential_elo", "public_id": "E-f417d302c870dfa6", "rated_matches": 36, "raw_elo_rating": 1459.431391791758, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 40.63664448996656, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 19, "model": "gpt-4.1", "point_rating_method": "sequential_elo", "public_id": "E-fcfa606d3cbb0ba0", "rated_matches": 44, "raw_elo_rating": 1507.216526715812, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 47.68030592612551, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 21, "model": "gpt-5", "point_rating_method": "sequential_elo", "public_id": "E-15dad0db253c0497", "rated_matches": 46, "raw_elo_rating": 1534.7241252046786, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 51.4414648280507, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 25, "model": "gpt-5", "point_rating_method": "sequential_elo", "public_id": "E-4d8b4cfcff519db6", "rated_matches": 66, "raw_elo_rating": 1571.1643984055847, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 57.44029280728862, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 41 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "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": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 24, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-22466ae84d7027e5", "rated_matches": 58, "raw_elo_rating": 1563.3796006203124, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 56.004212916192515, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 6, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-80aa3ec3ac4ad97f", "rated_matches": 64, "raw_elo_rating": 1839.8110785855636, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 92.43903356479711, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 58 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 32, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-c8176c382cf75e88", "rated_matches": 60, "raw_elo_rating": 1394.6909165849377, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 34.07904754522137, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 0, "generated_at": "2026-07-01T00:15:48Z", "losses": 38, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-022243613d51f0fb", "rated_matches": 64, "raw_elo_rating": 1355.2492138334867, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 29.135489791977815, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 21, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-1b33882368041bb3", "rated_matches": 62, "raw_elo_rating": 1624.3020252285476, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 64.18268235353479, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 41 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 45, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-6a87ebc54bdde781", "rated_matches": 60, "raw_elo_rating": 1251.8211628405084, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 15.414430356248433, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 69, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 0, "generated_at": "2026-07-01T00:15:48Z", "losses": 40, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-946bc9bcbefb4ad1", "rated_matches": 69, "raw_elo_rating": 1450.0764750092626, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 41.75957179317546, "uncertainty": 16.01143046671968, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 37, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-b96fbceba82aa188", "rated_matches": 64, "raw_elo_rating": 1489.954941342898, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 46.73355216158762, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 27 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 42, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-c2ab31787514c10c", "rated_matches": 58, "raw_elo_rating": 1284.705843848199, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 19.59805377862727, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 29, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-e453890c6dd35fa3", "rated_matches": 64, "raw_elo_rating": 1656.0079852411393, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 68.42685264118785, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 35 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 27, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-f4d7ac8a0f5d2974", "rated_matches": 56, "raw_elo_rating": 1506.1518610341518, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 48.40961066339226, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 42, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-4e14ae758717169e", "rated_matches": 66, "raw_elo_rating": 1422.57460456147, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 38.02840507316459, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 47, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-acb1779a65c941b4", "rated_matches": 54, "raw_elo_rating": 1182.0036362477724, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 5.937909127774502, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 0, "generated_at": "2026-07-09T17:30:50Z", "losses": 32, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-b9e3f57bc887c6ae", "rated_matches": 66, "raw_elo_rating": 1613.0301221781451, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 62.90966394480689, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 49, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-bea6d7d9558897f9", "rated_matches": 58, "raw_elo_rating": 1180.2311075914536, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 5.94939192372365, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 0, "generated_at": "2026-07-01T00:15:48Z", "losses": 51, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-c4ad375a0a870e69", "rated_matches": 66, "raw_elo_rating": 1287.0525736672737, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 20.323700186242597, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 55, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 0, "generated_at": "2026-07-09T17:30:50Z", "losses": 28, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-ce04fd14b6f43868", "rated_matches": 55, "raw_elo_rating": 1567.6900578052491, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 56.38748335772921, "uncertainty": 23.065310478106092, "unilateral_faults": 0, "wins": 27 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 34, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-ce2925d9379d2a5d", "rated_matches": 60, "raw_elo_rating": 1335.0448852215657, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 26.28684301584092, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 39, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-e0e874b71d913c12", "rated_matches": 62, "raw_elo_rating": 1375.04515939356, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 31.619569024065452, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 28, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-4edfe4117ad3e936", "rated_matches": 60, "raw_elo_rating": 1456.9711745696457, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 42.21538951578612, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 8, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-6201278165db862a", "rated_matches": 66, "raw_elo_rating": 1810.7420076245985, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 88.73890042665397, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 58 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 26, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-640b3078b8bce40e", "rated_matches": 58, "raw_elo_rating": 1637.762905975935, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 65.72170653066799, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 38, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-45c76cf9faaba10a", "rated_matches": 70, "raw_elo_rating": 1502.494574211802, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 48.65165422462213, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 21, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-73a7b73c1df452ad", "rated_matches": 54, "raw_elo_rating": 1626.8615300978795, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 64.05449486122448, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 33 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 46, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-ea529147555b5f2e", "rated_matches": 60, "raw_elo_rating": 1245.2596467020408, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 14.557228718434729, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 78, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 39, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 28, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-1b522c9c14f3860c", "rated_matches": 78, "raw_elo_rating": 1544.0623728482103, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 54.40449302982698, "uncertainty": 12.5043950463012, "unilateral_faults": 0, "wins": 50 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 31, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-bef852aad169a609", "rated_matches": 60, "raw_elo_rating": 1573.8998861000514, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 57.49104851229338, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 25, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-cc78d54d18d4c3f1", "rated_matches": 58, "raw_elo_rating": 1613.924246727442, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 62.60740530517968, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 33 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 24, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-65bf9818e3e1b632", "rated_matches": 66, "raw_elo_rating": 1690.141060653709, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 72.98349769903467, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 42 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 33, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-8ebe8776c7d44d46", "rated_matches": 60, "raw_elo_rating": 1496.914059374072, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 47.433559455600474, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 27 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 27, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-aca193dd2a8774fb", "rated_matches": 54, "raw_elo_rating": 1416.8015449056545, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 36.612092900151, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 27 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "inclusionai/ling-3.0-flash", "point_rating_method": "sequential_elo", "public_id": "E-57b2b1d3b488c246", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "inclusionai/ling-3.0-flash", "point_rating_method": "sequential_elo", "public_id": "E-5e20a850f6c14680", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-0ad780cd41873f27", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 32, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-c1f595f47c71e648", "rated_matches": 66, "raw_elo_rating": 1359.4019231798957, "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": 29.775476206938286, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 36, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-e2db910734ca5315", "rated_matches": 64, "raw_elo_rating": 1494.2969465629394, "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": 47.30079514437856, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 30, "model": "minimax/minimax-m3", "point_rating_method": "sequential_elo", "public_id": "E-24e15c4d7490cdf3", "rated_matches": 58, "raw_elo_rating": 1424.7213899013211, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 37.889795026123, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 18, "model": "minimax/minimax-m3", "point_rating_method": "sequential_elo", "public_id": "E-4547f4cedca403f9", "rated_matches": 34, "raw_elo_rating": 1528.3941973331473, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 49.40395561210127, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 38, "model": "mistralai/mistral-medium-3-5", "point_rating_method": "sequential_elo", "public_id": "E-d0d0df9d83b6e37e", "rated_matches": 38, "raw_elo_rating": 1159.7317422016708, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 1.7068241707303853, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 18, "model": "moonshotai/kimi-k2.7-code", "point_rating_method": "sequential_elo", "public_id": "E-d35e87ebfc251f60", "rated_matches": 34, "raw_elo_rating": 1499.4128100931498, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 45.6178043501094, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 0, "generated_at": "2026-07-24T14:00:00Z", "losses": 22, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-1d1372c78963efdf", "rated_matches": 46, "raw_elo_rating": 1558.078983518453, "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": 54.49256191826528, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 0, "generated_at": "2026-07-21T14:43:57Z", "losses": 12, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-3d2d4c8b0819b60b", "rated_matches": 32, "raw_elo_rating": 1611.7277808628844, "reasoning": "high", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 60.02699318566077, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 0, "generated_at": "2026-07-17T22:36:00Z", "losses": 26, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-49105fbc7f72e6fe", "rated_matches": 52, "raw_elo_rating": 1541.5326452995262, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "score": 52.7753453034211, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 0, "generated_at": "2026-07-24T14:00:00Z", "losses": 17, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-4cc8f48bf8bccc77", "rated_matches": 36, "raw_elo_rating": 1497.3704310336243, "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": 45.59303046676025, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 0, "generated_at": "2026-07-24T14:00:00Z", "losses": 23, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-4d8815930b656774", "rated_matches": 40, "raw_elo_rating": 1454.786214678421, "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": 40.459614863654, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 0, "generated_at": "2026-07-17T22:36:00Z", "losses": 15, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-77d9c422124dcbfe", "rated_matches": 42, "raw_elo_rating": 1514.214420946601, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "score": 48.41541451913415, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 27 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 0, "generated_at": "2026-07-21T14:20:15Z", "losses": 15, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-c00660d2a8eb25c9", "rated_matches": 36, "raw_elo_rating": 1542.0769976880406, "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": 51.43353155651955, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 0, "generated_at": "2026-07-11T17:22:09Z", "losses": 20, "model": "nex-agi/nex-n2-pro", "point_rating_method": "sequential_elo", "public_id": "E-1006c453b0c3a745", "rated_matches": 62, "raw_elo_rating": 1657.169899748788, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 68.47656737578293, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 42 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 15, "model": "nex-agi/nex-n2-pro", "point_rating_method": "sequential_elo", "public_id": "E-d1f432cda667f27f", "rated_matches": 34, "raw_elo_rating": 1480.9244522915517, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 43.20247072087337, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 0, "generated_at": "2026-07-03T18:15:00Z", "losses": 34, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-0e1c7f89e1c19b69", "rated_matches": 44, "raw_elo_rating": 1301.0437601099366, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 20.745733263714285, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 45, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-459f395cc0af6d2e", "rated_matches": 62, "raw_elo_rating": 1172.4066172061932, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 5.146710224123554, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-03T16:00:00Z", "losses": 27, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-312d25e3a9eeeee3", "rated_matches": 38, "raw_elo_rating": 1346.88960039813, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 26.15727421765783, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-21T14:20:15Z", "losses": 16, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-3fae70801895971d", "rated_matches": 40, "raw_elo_rating": 1458.0625092856346, "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": 40.88763257236601, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 30, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-f1e3e54a3d40556f", "rated_matches": 64, "raw_elo_rating": 1537.8619196179889, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 52.99215754691314, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 27, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-29bc7f4fdf0f7b14", "rated_matches": 38, "raw_elo_rating": 1341.589505961371, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 25.464865704765224, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 0, "generated_at": "2026-07-21T14:20:15Z", "losses": 23, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-759d747bb732d949", "rated_matches": 36, "raw_elo_rating": 1369.5464379088992, "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": 28.89400329893377, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 39, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-069a963abdd14cdf", "rated_matches": 66, "raw_elo_rating": 1497.5583703289335, "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": 47.82434330891513, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 27 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 28, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-d8e68d23876f6d21", "rated_matches": 68, "raw_elo_rating": 1585.8551435458874, "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": 59.45270723402088, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 40 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 22, "model": "qwen/qwen3.7-max", "point_rating_method": "sequential_elo", "public_id": "E-3142a09c7f192060", "rated_matches": 64, "raw_elo_rating": 1730.8896425336536, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 78.20945134532496, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 42 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 7, "model": "qwen/qwen3.7-max", "point_rating_method": "sequential_elo", "public_id": "E-59c7745eb1e91d63", "rated_matches": 32, "raw_elo_rating": 1700.82192229776, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 71.66632201544819, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 36, "model": "qwen/qwen3.7-plus", "point_rating_method": "sequential_elo", "public_id": "E-737a66790985a5e6", "rated_matches": 60, "raw_elo_rating": 1272.023445307137, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 18.05367245403799, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 19, "model": "qwen/qwen3.7-plus", "point_rating_method": "sequential_elo", "public_id": "E-9d091700cb41ece2", "rated_matches": 44, "raw_elo_rating": 1491.841528725517, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 45.67170407549571, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 0, "generated_at": "2026-07-21T14:20:15Z", "losses": 24, "model": "stepfun/step-3.7-flash", "point_rating_method": "sequential_elo", "public_id": "E-1140a7c92290e8f4", "rated_matches": 46, "raw_elo_rating": 1426.1484616915282, "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": 37.25705460545867, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 22 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 30, "model": "stepfun/step-3.7-flash", "point_rating_method": "sequential_elo", "public_id": "E-6a5e44fe2dde4257", "rated_matches": 38, "raw_elo_rating": 1290.3553975779018, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 18.771601420804853, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 27, "model": "tencent/hy3-preview", "point_rating_method": "sequential_elo", "public_id": "E-dfed1e345a939bcd", "rated_matches": 38, "raw_elo_rating": 1342.3629390250549, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 25.565907609553385, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 42, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-062d41f517db2ccb", "rated_matches": 66, "raw_elo_rating": 1358.1292477360432, "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": 29.609212884277255, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-38e756fc6f3a2db6", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 31, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-6df2b00898e4ba3c", "rated_matches": 68, "raw_elo_rating": 1640.3004589168615, "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": 66.56548612877529, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 37 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 32, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-8ad2285ad59d87bf", "rated_matches": 62, "raw_elo_rating": 1440.3656332366938, "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": 40.15308718960612, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 30 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-17T22:36:00Z", "losses": 17, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-0929811cef80813b", "rated_matches": 38, "raw_elo_rating": 1479.193023754416, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 43.44149768005027, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 0, "generated_at": "2026-07-17T22:36:00Z", "losses": 24, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-3cfeaacb3dbbab07", "rated_matches": 58, "raw_elo_rating": 1573.6891886176236, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 57.35106561456042, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 0, "generated_at": "2026-07-24T14:00:00Z", "losses": 25, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-436a3933a93e10cd", "rated_matches": 42, "raw_elo_rating": 1540.3467918300798, "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": 51.829368039715575, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 0, "generated_at": "2026-07-21T14:20:15Z", "losses": 7, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-7e2507a947914c49", "rated_matches": 36, "raw_elo_rating": 1675.633825922066, "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": 68.88150081963373, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-17T22:36:00Z", "losses": 13, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-8e7f3829f3e45642", "rated_matches": 38, "raw_elo_rating": 1680.1891759395735, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 69.69979335614812, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 0, "generated_at": "2026-07-17T22:36:00Z", "losses": 18, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-a1728c5ac67e11f3", "rated_matches": 66, "raw_elo_rating": 1688.6107752565024, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 72.7835800091097, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 48 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-24T14:00:00Z", "losses": 5, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-ca54791ad3682b4f", "rated_matches": 38, "raw_elo_rating": 1735.6551782099175, "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": 76.94591559158341, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 33 }, { "admitted_plugin_count": 1, "attempted_matches": 82, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 41, "draws": 0, "generated_at": "2026-07-24T14:00:00Z", "losses": 34, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-e58f3df122cf1d29", "rated_matches": 82, "raw_elo_rating": 1654.3079800618857, "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": 68.95048504308706, "uncertainty": 11.132129994845172, "unilateral_faults": 0, "wins": 48 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 21, "model": "x-ai/grok-build-0.1", "point_rating_method": "sequential_elo", "public_id": "E-37ae0129627ee16f", "rated_matches": 32, "raw_elo_rating": 1338.4379390913737, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 24.324192945486605, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 32, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-0984b025e9005f5b", "rated_matches": 56, "raw_elo_rating": 1353.1217849238958, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 28.41764095574733, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 0, "generated_at": "2026-07-01T00:15:48Z", "losses": 14, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-345a5b25cbac7f3b", "rated_matches": 32, "raw_elo_rating": 1497.9774514768028, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "first_pass", "score": 45.16656053657338, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 76, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 38, "draws": 0, "generated_at": "2026-07-01T00:15:48Z", "losses": 44, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-47d67dcf0077af42", "rated_matches": 76, "raw_elo_rating": 1451.0459115638023, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 42.17688423878943, "uncertainty": 13.230288229818967, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 19, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-fa1a93f7e4d57000", "rated_matches": 32, "raw_elo_rating": 1398.4187741474352, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 32.16013649305479, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 21, "model": "xiaomi/mimo-v2.5-pro", "point_rating_method": "sequential_elo", "public_id": "E-3b160130ae038271", "rated_matches": 36, "raw_elo_rating": 1493.5745054280833, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 45.09712775503596, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 21, "model": "xiaomi/mimo-v2.5-pro", "point_rating_method": "sequential_elo", "public_id": "E-83580d03385c6759", "rated_matches": 54, "raw_elo_rating": 1636.5407743062012, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 65.31899895038302, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 33 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 16, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-1d66fd51bbcbb370", "rated_matches": 42, "raw_elo_rating": 1664.0248249736765, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 67.98676372921676, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 0, "generated_at": "2026-07-11T14:00:45Z", "losses": 20, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-62e8714f035ebc68", "rated_matches": 46, "raw_elo_rating": 1538.4426521126998, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 51.927256112952506, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 76, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 38, "draws": 0, "generated_at": "2026-07-11T14:00:45Z", "losses": 28, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-c81741d135c9dc9c", "rated_matches": 76, "raw_elo_rating": 1580.6857304668326, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 59.113132316890294, "uncertainty": 13.230288229818967, "unilateral_faults": 0, "wins": 48 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 27, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-cb438d112c0ea172", "rated_matches": 60, "raw_elo_rating": 1542.4399698356713, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 53.38110026584942, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 33 }, { "admitted_plugin_count": 1, "attempted_matches": 78, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 39, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 37, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-d96269dd04d644e0", "rated_matches": 78, "raw_elo_rating": 1584.028671851824, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 59.62572181907002, "uncertainty": 12.5043950463012, "unilateral_faults": 0, "wins": 41 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 0, "generated_at": "2026-07-01T00:15:48Z", "losses": 17, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-e10fd023695e8b0a", "rated_matches": 42, "raw_elo_rating": 1663.8404021886329, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 67.96267059128135, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 23, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-e31f275ab7ef3741", "rated_matches": 44, "raw_elo_rating": 1531.359555833092, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 50.834370271069695, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 0, "generated_at": "2026-07-11T17:22:09Z", "losses": 18, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-ecd98326faa92bf4", "rated_matches": 44, "raw_elo_rating": 1517.4039789444332, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 49.01120271144721, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 0, "generated_at": "2026-07-01T00:15:48Z", "losses": 18, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-f7579fbfcb1dcbb9", "rated_matches": 44, "raw_elo_rating": 1583.7592130000278, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 57.67990276637863, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 26 } ], "GB2-08": [ { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 1, "generated_at": "2026-07-02T16:51:45Z", "losses": 4, "model": "claude-fable-5", "point_rating_method": "sequential_elo", "public_id": "E-12891afa894223fd", "rated_matches": 66, "raw_elo_rating": 1910.1404215986424, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 100.0, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 61 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 12, "model": "claude-fable-5", "point_rating_method": "sequential_elo", "public_id": "E-9ccf296d44d35675", "rated_matches": 60, "raw_elo_rating": 1742.3401615411974, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 73.64139541154456, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 48 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 6, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 6, "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": 70, "raw_elo_rating": 1636.0494722351684, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 57.75514722037097, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 45 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "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": "medium", "reasoning_policy_version": "legacy_reasoning_presets_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, "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": "highest", "reasoning_policy_version": "legacy_reasoning_presets_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": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 0, "losses": 11, "model": "claude-opus-4-5", "point_rating_method": "sequential_elo", "public_id": "E-72233463ddce5549", "rated_matches": 32, "raw_elo_rating": 1625.8450002114848, "reasoning": "legacy_shared_thinking_budget", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "legacy_shared_thinking_budget", "repair_status": "first_pass", "score": 52.74138987875058, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 28, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 28, "losses": 24, "model": "claude-opus-4-5", "point_rating_method": "sequential_elo", "public_id": "E-877eec51affacb3a", "rated_matches": 64, "raw_elo_rating": 1441.6905108373974, "reasoning": "legacy_shared_thinking_budget", "reasoning_bracket": "intensive", "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "legacy_shared_thinking_budget", "repair_status": "first_pass", "score": 27.3138197157522, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 0, "generated_at": "2026-07-03T17:20:00Z", "losses": 20, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-22dc6fe5ae5fb8b1", "rated_matches": 66, "raw_elo_rating": 1683.6684140637717, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 64.91576179922941, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 46 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 49, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 49, "generated_at": "2026-07-02T16:51:45Z", "losses": 7, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-c2dade0b97891d8a", "rated_matches": 60, "raw_elo_rating": 1451.714886192373, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 28.618761053818325, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 21, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-c9d7578e8375d994", "rated_matches": 70, "raw_elo_rating": 1649.3609751746642, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 59.81731792757247, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 49 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 0, "generated_at": "2026-07-25T10:50:00Z", "losses": 24, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-35a5bf9b35d5e1e8", "rated_matches": 58, "raw_elo_rating": 1686.7468791495075, "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": 64.89572776231789, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 0, "generated_at": "2026-07-25T10:50:00Z", "losses": 25, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-5a7942274854aaa6", "rated_matches": 56, "raw_elo_rating": 1564.7574379284083, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 45.85724479955294, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 31 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 0, "generated_at": "2026-07-25T15:48:01Z", "losses": 10, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-a40851c4f03704e5", "rated_matches": 40, "raw_elo_rating": 1794.374151033846, "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": 79.95876977478349, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 30 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 0, "generated_at": "2026-07-25T10:50:00Z", "losses": 16, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-e73b6fb78880341d", "rated_matches": 58, "raw_elo_rating": 1773.600323016276, "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": 78.35075448437216, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 42 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 0, "generated_at": "2026-07-25T15:48:01Z", "losses": 16, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-f5914ca845403384", "rated_matches": 40, "raw_elo_rating": 1577.758866326647, "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": 46.401500029537175, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 45, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 45, "generated_at": "2026-07-02T16:51:45Z", "losses": 9, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-130fb40b1c7a4d39", "rated_matches": 60, "raw_elo_rating": 1443.826362619811, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 27.396699029090957, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 78, "capped_draws": 42, "coverage_status": "rated", "distinct_rated_opponents": 39, "draws": 42, "generated_at": "2026-07-03T16:50:00Z", "losses": 26, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-b5805acb90227d50", "rated_matches": 78, "raw_elo_rating": 1466.4677843586585, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 31.86645017234374, "uncertainty": 12.5043950463012, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 42, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 42, "generated_at": "2026-07-02T16:51:45Z", "losses": 2, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-cf0ed4bbe4aaadd7", "rated_matches": 44, "raw_elo_rating": 1446.1686024506469, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 26.45612575749886, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 49, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 49, "generated_at": "2026-07-11T17:22:09Z", "losses": 9, "model": "cohere/north-mini-code", "point_rating_method": "sequential_elo", "public_id": "E-c36a98e057c264eb", "rated_matches": 62, "raw_elo_rating": 1450.883258777918, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 28.6168805991318, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 24, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 24, "generated_at": "2026-07-02T16:51:45Z", "losses": 8, "model": "cohere/north-mini-code", "point_rating_method": "sequential_elo", "public_id": "E-efd7b75d5cd3b538", "rated_matches": 32, "raw_elo_rating": 1430.5543856985234, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "first_pass", "score": 22.487662221514032, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 44, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 44, "generated_at": "2026-07-02T16:51:45Z", "losses": 14, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-4375cf96eeb624e2", "rated_matches": 64, "raw_elo_rating": 1442.4688068125326, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 27.434390561039304, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 40, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 40, "generated_at": "2026-07-02T06:10:40Z", "losses": 4, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-43aba68125a9abc5", "rated_matches": 44, "raw_elo_rating": 1444.850116717791, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 26.251870635555328, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 55, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 55, "generated_at": "2026-07-02T06:10:40Z", "losses": 7, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-95b070e1c29e44f0", "rated_matches": 62, "raw_elo_rating": 1422.4165040540342, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 24.206912169007527, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 48, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 48, "generated_at": "2026-07-02T16:51:45Z", "losses": 14, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-a7310645c3b96434", "rated_matches": 66, "raw_elo_rating": 1432.8957272786026, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 26.06694876849134, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 56, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 56, "generated_at": "2026-07-01T00:15:48Z", "losses": 10, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-b53fd6f34eb6127d", "rated_matches": 70, "raw_elo_rating": 1445.3812885112827, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 28.217510106225216, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 39, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 39, "generated_at": "2026-07-01T00:15:48Z", "losses": 4, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-d28ef17ff6995c62", "rated_matches": 44, "raw_elo_rating": 1443.8493725610651, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 26.096838908876283, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 54, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 54, "generated_at": "2026-07-02T16:51:45Z", "losses": 10, "model": "deepseek/deepseek-v4-pro", "point_rating_method": "sequential_elo", "public_id": "E-3a5b5c4507a989d3", "rated_matches": 70, "raw_elo_rating": 1442.2170907590032, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 27.727323840541924, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 57, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 57, "generated_at": "2026-07-02T16:51:45Z", "losses": 8, "model": "deepseek/deepseek-v4-pro", "point_rating_method": "sequential_elo", "public_id": "E-c296a7abab6975d7", "rated_matches": 68, "raw_elo_rating": 1446.802549177008, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 28.33186721946456, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 29, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 29, "generated_at": "2026-07-02T16:51:45Z", "losses": 6, "model": "google/gemini-3.1-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-b335c9f92035f80b", "rated_matches": 38, "raw_elo_rating": 1424.7057372534773, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 22.446013309546696, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 25, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 25, "generated_at": "2026-07-02T16:51:45Z", "losses": 24, "model": "google/gemini-3.1-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-cc6fb78c96472032", "rated_matches": 72, "raw_elo_rating": 1457.7343014406704, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 30.232635390830257, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "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": 62, "capped_draws": 57, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 57, "generated_at": "2026-07-02T16:51:45Z", "losses": 5, "model": "google/gemini-3.5-flash", "point_rating_method": "sequential_elo", "public_id": "E-bd0bbefbbd252fc5", "rated_matches": 62, "raw_elo_rating": 1402.0511352404135, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 21.05198164014908, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 25, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 25, "generated_at": "2026-07-02T16:51:45Z", "losses": 13, "model": "google/gemini-3.5-flash", "point_rating_method": "sequential_elo", "public_id": "E-fa332e578ae97122", "rated_matches": 38, "raw_elo_rating": 1374.610482889811, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 14.685434613954731, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-0d09401e4a31ea61", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-284d554eca16e6f6", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 2, "attempted_matches": 70, "capped_draws": 55, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 55, "generated_at": "2026-07-24T13:40:00Z", "losses": 12, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-94d4c9bacc61b6b0", "rated_matches": 70, "raw_elo_rating": 1429.1142665897733, "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": 25.697480906486177, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-96566b3cf3a15c23", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-af119b49b8f1d63d", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 50, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 50, "generated_at": "2026-07-24T13:40:00Z", "losses": 20, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-10fc8582228643cf", "rated_matches": 70, "raw_elo_rating": 1377.8172524718702, "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": 17.750729862546706, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-37e04d4125f1d7fa", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-657c523bc9e9f80c", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 39, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 39, "generated_at": "2026-07-24T13:40:00Z", "losses": 16, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-679bf377de51ec1e", "rated_matches": 68, "raw_elo_rating": 1435.6060844881897, "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": 26.5973507181767, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-c694a36a5e4e3f09", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-ee7ca879a02fdaf7", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 43, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 43, "generated_at": "2026-07-02T16:51:45Z", "losses": 10, "model": "google/gemma-4-31b-it", "point_rating_method": "sequential_elo", "public_id": "E-8546650b7690a81a", "rated_matches": 54, "raw_elo_rating": 1439.4942097257222, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 26.304012940866215, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 27, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 27, "generated_at": "2026-07-02T16:51:45Z", "losses": 14, "model": "gpt-4.1", "point_rating_method": "sequential_elo", "public_id": "E-eabc996d553eebe0", "rated_matches": 48, "raw_elo_rating": 1418.016037894468, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 22.47989431367969, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 49, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 49, "generated_at": "2026-07-02T16:51:45Z", "losses": 11, "model": "gpt-5", "point_rating_method": "sequential_elo", "public_id": "E-04ae9f2b42e0e036", "rated_matches": 68, "raw_elo_rating": 1439.8208523917242, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 27.25028757645839, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "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": 42, "capped_draws": 27, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 27, "generated_at": "2026-07-02T16:51:45Z", "losses": 10, "model": "gpt-5", "point_rating_method": "sequential_elo", "public_id": "E-ebca8ea756b4a4ad", "rated_matches": 42, "raw_elo_rating": 1423.6771246206629, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 22.759443475663716, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 49, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 49, "generated_at": "2026-07-02T16:51:45Z", "losses": 11, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-95f891d54f35bb4a", "rated_matches": 70, "raw_elo_rating": 1454.9766570016957, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 29.70399047704974, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 21, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 21, "generated_at": "2026-07-02T16:51:45Z", "losses": 26, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-b13a2be40d59c1ea", "rated_matches": 66, "raw_elo_rating": 1456.5400400197243, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 29.72984163252576, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 15, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 15, "generated_at": "2026-07-02T16:51:45Z", "losses": 28, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-ddc1f3e68bf1e74a", "rated_matches": 68, "raw_elo_rating": 1524.6754320667146, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 40.39565736475438, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 34, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 34, "generated_at": "2026-07-02T06:10:40Z", "losses": 25, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-00b5df785d927901", "rated_matches": 70, "raw_elo_rating": 1437.1119892602044, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 26.93645966720522, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 4, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 4, "generated_at": "2026-07-02T16:51:45Z", "losses": 30, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-1e5d07fc67fd8710", "rated_matches": 64, "raw_elo_rating": 1539.952499256562, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 42.53621759752361, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 30 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 44, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 44, "generated_at": "2026-07-01T00:15:48Z", "losses": 9, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-7ff0b78720f446ad", "rated_matches": 56, "raw_elo_rating": 1443.119426246869, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 27.01351650590875, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 47, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 47, "generated_at": "2026-07-02T06:10:40Z", "losses": 7, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-8cc872d6760c46c1", "rated_matches": 56, "raw_elo_rating": 1433.1644338510025, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 25.471324478270816, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 39, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 39, "generated_at": "2026-07-01T00:15:48Z", "losses": 13, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-acdb5996d6e8fdfc", "rated_matches": 58, "raw_elo_rating": 1449.3936251532014, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 28.12580554730766, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 25, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 25, "generated_at": "2026-07-02T16:51:45Z", "losses": 21, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-b5171a15f0048555", "rated_matches": 60, "raw_elo_rating": 1453.6580457764076, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 28.91978842779916, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 80, "capped_draws": 48, "coverage_status": "rated", "distinct_rated_opponents": 40, "draws": 48, "generated_at": "2026-07-02T06:10:40Z", "losses": 20, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-b63acb1096519102", "rated_matches": 80, "raw_elo_rating": 1437.1977394594303, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 27.418648267683565, "uncertainty": 11.805555555555554, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 53, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 53, "generated_at": "2026-07-02T16:51:45Z", "losses": 5, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-bb8ac98c284a38ce", "rated_matches": 58, "raw_elo_rating": 1444.9709152618298, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 27.44065505559449, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 63, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 63, "generated_at": "2026-07-09T17:30:50Z", "losses": 9, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-024aff0a983df40d", "rated_matches": 72, "raw_elo_rating": 1409.60538534671, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 22.776674828792995, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 45, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 45, "generated_at": "2026-07-02T16:51:45Z", "losses": 18, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-26fa12e871bd8f3a", "rated_matches": 68, "raw_elo_rating": 1394.8874477441384, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 20.2893642862598, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 58, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 58, "generated_at": "2026-07-02T06:10:40Z", "losses": 4, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-814593575d73a7cd", "rated_matches": 62, "raw_elo_rating": 1433.2979485120743, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 25.892626856177163, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 15, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-98e55f26cfe52488", "rated_matches": 70, "raw_elo_rating": 1747.046912507192, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 74.95047602311436, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 55 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 56, "coverage_status": "rated", "distinct_rated_opponents": 37, "draws": 56, "generated_at": "2026-07-02T06:10:40Z", "losses": 15, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-ba371b627387f273", "rated_matches": 74, "raw_elo_rating": 1434.4993035373657, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 26.73050740503117, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 47, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 47, "generated_at": "2026-07-09T17:30:50Z", "losses": 14, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-bb4437fab8180bfc", "rated_matches": 68, "raw_elo_rating": 1431.8775736806174, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 26.0197430803459, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 48, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 48, "generated_at": "2026-07-01T00:15:48Z", "losses": 10, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-c320ceaf4558afab", "rated_matches": 62, "raw_elo_rating": 1459.2786323344658, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 29.91746202130612, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 0, "generated_at": "2026-07-09T17:30:50Z", "losses": 23, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-e361d8cbba2abd67", "rated_matches": 60, "raw_elo_rating": 1675.169994435442, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 63.23563194269277, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 37 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 48, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 48, "generated_at": "2026-07-02T06:10:40Z", "losses": 7, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-f26c38927e48d019", "rated_matches": 60, "raw_elo_rating": 1463.8982068741182, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 30.506157776827983, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 3, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 3, "generated_at": "2026-07-02T16:51:45Z", "losses": 23, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-fd5a36e5fd795426", "rated_matches": 66, "raw_elo_rating": 1592.0368931255489, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 50.72053236540851, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 40 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 25, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 25, "generated_at": "2026-07-02T16:51:45Z", "losses": 22, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-0d83a3c5c5e66085", "rated_matches": 62, "raw_elo_rating": 1541.4688058948389, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 42.65007148744865, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 9, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 9, "generated_at": "2026-07-02T16:51:45Z", "losses": 16, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-3e859a6b27767128", "rated_matches": 68, "raw_elo_rating": 1686.9133200163933, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 65.52897413963234, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 43 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 45, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 45, "generated_at": "2026-07-02T16:51:45Z", "losses": 8, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-c42fbee03a029c83", "rated_matches": 56, "raw_elo_rating": 1448.3295730196996, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 27.82065391961682, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 5, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 5, "generated_at": "2026-07-10T05:30:29Z", "losses": 28, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-0fb7de4e8156a229", "rated_matches": 64, "raw_elo_rating": 1548.0692879399865, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 43.793641641644086, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 31 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 50, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 50, "generated_at": "2026-07-10T05:30:29Z", "losses": 7, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-8feb37d0677409f2", "rated_matches": 58, "raw_elo_rating": 1441.8619859707171, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 26.959030783411738, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 49, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 49, "generated_at": "2026-07-10T05:30:29Z", "losses": 6, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-e6198d88365e0492", "rated_matches": 62, "raw_elo_rating": 1466.5807611762505, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 31.048681859229955, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 5, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 5, "generated_at": "2026-07-10T05:30:29Z", "losses": 15, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-0385f0602a8e29e2", "rated_matches": 58, "raw_elo_rating": 1672.1128256209613, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 62.628672220103525, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 38 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 12, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 12, "generated_at": "2026-07-10T05:30:29Z", "losses": 32, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-3ae62f195160add3", "rated_matches": 64, "raw_elo_rating": 1370.0658232755432, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 16.21797777560009, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 5, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 5, "generated_at": "2026-07-10T05:30:29Z", "losses": 21, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-994624d0bc2e266d", "rated_matches": 58, "raw_elo_rating": 1522.545055470742, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 39.45816504693588, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 53, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 53, "generated_at": "2026-07-10T05:30:29Z", "losses": 9, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-44cace55a6126cdf", "rated_matches": 66, "raw_elo_rating": 1449.6896851314627, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 28.668609009228703, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 9, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 9, "generated_at": "2026-07-10T05:30:29Z", "losses": 31, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-b061663dc342c859", "rated_matches": 66, "raw_elo_rating": 1541.4118035776828, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 42.877873486874975, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 33, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 33, "generated_at": "2026-07-10T05:30:29Z", "losses": 14, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-d004e78844cdd202", "rated_matches": 60, "raw_elo_rating": 1488.7884995268803, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 34.36207341877303, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 54, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 54, "generated_at": "2026-07-24T13:40:00Z", "losses": 12, "model": "inclusionai/ling-3.0-flash", "point_rating_method": "sequential_elo", "public_id": "E-11d1ae7d9526f835", "rated_matches": 66, "raw_elo_rating": 1417.6213892585145, "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": 23.700702629337265, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 57, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 57, "generated_at": "2026-07-24T13:40:00Z", "losses": 11, "model": "inclusionai/ling-3.0-flash", "point_rating_method": "sequential_elo", "public_id": "E-28bcc8394e411616", "rated_matches": 72, "raw_elo_rating": 1423.9891223360928, "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": 25.00495222274436, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-4289b162cf8180f0", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 55, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 55, "generated_at": "2026-07-24T13:40:00Z", "losses": 7, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-87d69837bf65e78b", "rated_matches": 66, "raw_elo_rating": 1421.9008639632525, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 24.36366363520058, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 56, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 56, "generated_at": "2026-07-24T13:40:00Z", "losses": 8, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-df8e0fab4bf8bb33", "rated_matches": 70, "raw_elo_rating": 1432.31833577945, "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": 26.193843913490717, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-fffc7436e4cd7fbe", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 29, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 29, "generated_at": "2026-07-02T16:51:45Z", "losses": 6, "model": "minimax/minimax-m3", "point_rating_method": "sequential_elo", "public_id": "E-d169e7b29be70652", "rated_matches": 38, "raw_elo_rating": 1461.5536447992083, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 28.154360136186384, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 7, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 7, "generated_at": "2026-07-02T16:51:45Z", "losses": 33, "model": "minimax/minimax-m3", "point_rating_method": "sequential_elo", "public_id": "E-e67e41d4491d7ad3", "rated_matches": 66, "raw_elo_rating": 1499.683273236858, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 36.413437929557105, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 47, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 47, "generated_at": "2026-07-02T16:51:45Z", "losses": 5, "model": "mistralai/mistral-medium-3-5", "point_rating_method": "sequential_elo", "public_id": "E-ba85be2fa53925f5", "rated_matches": 52, "raw_elo_rating": 1438.2888976809872, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 25.961097857676517, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 30, "capped_draws": 2, "coverage_status": "under_covered", "distinct_rated_opponents": 15, "draws": 2, "generated_at": "2026-07-02T16:51:45Z", "losses": 14, "model": "moonshotai/kimi-k2.7-code", "point_rating_method": "sequential_elo", "public_id": "E-251b5d53a5f89562", "rated_matches": 30, "raw_elo_rating": 1564.582882005904, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 42.90835102937155, "uncertainty": 46.05265101338746, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 25, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 25, "generated_at": "2026-07-18T00:14:00Z", "losses": 11, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-134262cb96978830", "rated_matches": 38, "raw_elo_rating": 1389.414900625589, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "score": 16.978882373434576, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 37, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 37, "generated_at": "2026-07-24T14:00:00Z", "losses": 3, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-151c4ee6a2d1838e", "rated_matches": 42, "raw_elo_rating": 1466.675965925635, "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": 29.420671091039058, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 0, "generated_at": "2026-07-24T14:00:00Z", "losses": 1, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-3e1be56b9d966ded", "rated_matches": 36, "raw_elo_rating": 1792.9886993624134, "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": 79.23445145680559, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 35 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 13, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 13, "generated_at": "2026-07-21T14:43:57Z", "losses": 17, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-66c86eb2913b72e2", "rated_matches": 46, "raw_elo_rating": 1507.2816043430432, "reasoning": "high", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 36.12221240307626, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 33, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 33, "generated_at": "2026-07-17T22:36:00Z", "losses": 14, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-b06cbc77b01de3b3", "rated_matches": 50, "raw_elo_rating": 1429.093839088688, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "score": 24.371339668629737, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 11, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 11, "generated_at": "2026-07-21T14:20:15Z", "losses": 15, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-b88e77144afeb8fd", "rated_matches": 36, "raw_elo_rating": 1491.071352291259, "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": 32.46248949608453, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 48, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 48, "generated_at": "2026-07-11T17:22:09Z", "losses": 7, "model": "nex-agi/nex-n2-pro", "point_rating_method": "sequential_elo", "public_id": "E-506d972b5c69a00d", "rated_matches": 56, "raw_elo_rating": 1440.8610223975368, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 26.6636526111786, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 30, "capped_draws": 8, "coverage_status": "under_covered", "distinct_rated_opponents": 15, "draws": 8, "generated_at": "2026-07-02T16:51:45Z", "losses": 19, "model": "nex-agi/nex-n2-pro", "point_rating_method": "sequential_elo", "public_id": "E-92332f4d765b2297", "rated_matches": 30, "raw_elo_rating": 1332.1817748180883, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 6.905597790895916, "uncertainty": 46.05265101338746, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 42, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 42, "generated_at": "2026-07-02T16:51:45Z", "losses": 11, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-15cf0dede27b7e1b", "rated_matches": 56, "raw_elo_rating": 1436.2781128307956, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 25.953684555336736, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 28, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 28, "generated_at": "2026-07-11T17:22:09Z", "losses": 10, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-2e3c01d0103fc439", "rated_matches": 42, "raw_elo_rating": 1438.8528329749015, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 25.11041025765575, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 28, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 28, "generated_at": "2026-07-02T16:51:45Z", "losses": 8, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-8c24e8bcbe9b1228", "rated_matches": 42, "raw_elo_rating": 1429.6542352216024, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 23.685396198732267, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 38, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 38, "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": 44, "raw_elo_rating": 1452.3898563879034, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 27.41990029819383, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 1, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 1, "generated_at": "2026-07-03T16:00:00Z", "losses": 15, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-1b6fc7dfefb8cea4", "rated_matches": 38, "raw_elo_rating": 1612.4707931407108, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 51.533908181121, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 22 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 38, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 38, "generated_at": "2026-07-02T16:51:45Z", "losses": 18, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-35de956c8305ff90", "rated_matches": 66, "raw_elo_rating": 1462.0021926743475, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 30.576018901450553, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 15, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 15, "generated_at": "2026-07-21T14:20:15Z", "losses": 13, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-cbb72b5e25b55cee", "rated_matches": 36, "raw_elo_rating": 1491.6615321357433, "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": 32.55391805924589, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 32, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 32, "generated_at": "2026-07-02T16:51:45Z", "losses": 7, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-24a75273941e6ea3", "rated_matches": 44, "raw_elo_rating": 1439.7393158406376, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 25.460123534787694, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 45, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 45, "generated_at": "2026-07-02T16:51:45Z", "losses": 10, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-6e65dec497ff2de3", "rated_matches": 58, "raw_elo_rating": 1464.2474413129037, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 30.42690593498895, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 30, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 30, "generated_at": "2026-07-21T14:20:15Z", "losses": 4, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-f6e9da46c61ad315", "rated_matches": 36, "raw_elo_rating": 1440.4422887134535, "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": 24.61921497496216, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-0fab95afbec0dd98", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 60, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 60, "generated_at": "2026-07-24T13:40:00Z", "losses": 9, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-4030acdbccf3ca03", "rated_matches": 70, "raw_elo_rating": 1418.1879120868175, "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": 24.00480891483295, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 53, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 53, "generated_at": "2026-07-24T13:40:00Z", "losses": 14, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-e90a3ce84847ba43", "rated_matches": 70, "raw_elo_rating": 1414.5541574282531, "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": 23.441880562707087, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-f72c72b8f264c57a", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 20, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 20, "generated_at": "2026-07-02T16:51:45Z", "losses": 9, "model": "qwen/qwen3.7-max", "point_rating_method": "sequential_elo", "public_id": "E-64624689e7cbd439", "rated_matches": 32, "raw_elo_rating": 1476.2232335533376, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 29.56251775855583, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 47, "coverage_status": "rated", "distinct_rated_opponents": 37, "draws": 47, "generated_at": "2026-07-02T16:51:45Z", "losses": 22, "model": "qwen/qwen3.7-max", "point_rating_method": "sequential_elo", "public_id": "E-a667eb7d15f7f43e", "rated_matches": 74, "raw_elo_rating": 1456.5863157614344, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 30.15214880984472, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 29, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 29, "generated_at": "2026-07-02T16:51:45Z", "losses": 3, "model": "qwen/qwen3.7-plus", "point_rating_method": "sequential_elo", "public_id": "E-6c2a9942e92223c8", "rated_matches": 32, "raw_elo_rating": 1459.9075340300603, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "first_pass", "score": 27.03494759782097, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 28, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 28, "generated_at": "2026-07-02T16:51:45Z", "losses": 13, "model": "stepfun/step-3.7-flash", "point_rating_method": "sequential_elo", "public_id": "E-8b265019ada47f24", "rated_matches": 44, "raw_elo_rating": 1426.3919506761963, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 23.39239717920349, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 28, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 28, "generated_at": "2026-07-21T14:20:15Z", "losses": 8, "model": "stepfun/step-3.7-flash", "point_rating_method": "sequential_elo", "public_id": "E-c38fe2712e69333b", "rated_matches": 36, "raw_elo_rating": 1405.73919833146, "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": 19.24313559757037, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 80, "capped_draws": 65, "coverage_status": "rated", "distinct_rated_opponents": 40, "draws": 65, "generated_at": "2026-07-02T16:51:45Z", "losses": 14, "model": "tencent/hy3-preview", "point_rating_method": "sequential_elo", "public_id": "E-56487337fad4192f", "rated_matches": 80, "raw_elo_rating": 1450.2389966102576, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 29.438953458145875, "uncertainty": 11.805555555555554, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 9, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 9, "generated_at": "2026-07-02T16:51:45Z", "losses": 22, "model": "tencent/hy3-preview", "point_rating_method": "sequential_elo", "public_id": "E-81a5e5ef15f371dc", "rated_matches": 46, "raw_elo_rating": 1431.9083099217262, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 24.445649616184685, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 1, "generated_at": "2026-07-24T13:40:00Z", "losses": 38, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-68669040dc891a7d", "rated_matches": 68, "raw_elo_rating": 1637.7826189897944, "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": 57.91782061761204, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 38, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-9c877cdf80f00ddf", "rated_matches": 70, "raw_elo_rating": 1602.2012432700476, "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": 52.51149993427681, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-d21921560d198b28", "rated_matches": 0, "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", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-17T22:36:00Z", "losses": 13, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-1c7222840add0cf9", "rated_matches": 38, "raw_elo_rating": 1634.9673614218534, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 55.018996554146426, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 0, "generated_at": "2026-07-17T22:36:00Z", "losses": 13, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-34ecad20175c262b", "rated_matches": 56, "raw_elo_rating": 1786.330960585913, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 80.18262713936724, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 43 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-17T22:36:00Z", "losses": 10, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-60939cc4ea338b18", "rated_matches": 38, "raw_elo_rating": 1670.2667139146774, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 60.4874467377768, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-24T14:00:00Z", "losses": 4, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-707dd709e358a173", "rated_matches": 38, "raw_elo_rating": 1782.8058796629582, "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": 77.92161416979704, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 1, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 1, "generated_at": "2026-07-21T14:20:15Z", "losses": 7, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-71860dfe49537041", "rated_matches": 36, "raw_elo_rating": 1693.453686427907, "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": 63.81484114327353, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 0, "generated_at": "2026-07-17T22:36:00Z", "losses": 7, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-72b02fc86c46f3d7", "rated_matches": 58, "raw_elo_rating": 1840.5719390163315, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 88.72575912186454, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 51 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 1, "generated_at": "2026-07-24T14:00:00Z", "losses": 12, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-73422318071a105c", "rated_matches": 72, "raw_elo_rating": 1815.553575169084, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 85.66472507362005, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 59 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 0, "generated_at": "2026-07-24T14:00:00Z", "losses": 7, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-b914d026c7631fcb", "rated_matches": 36, "raw_elo_rating": 1723.196572871152, "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": 68.42250336215771, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 24, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 24, "generated_at": "2026-07-02T16:51:45Z", "losses": 5, "model": "x-ai/grok-build-0.1", "point_rating_method": "sequential_elo", "public_id": "E-3e2fe948d2bcebb0", "rated_matches": 32, "raw_elo_rating": 1459.4782493754258, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 26.968444345418725, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 37, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 37, "generated_at": "2026-07-02T06:10:40Z", "losses": 5, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-5f664f9580459829", "rated_matches": 44, "raw_elo_rating": 1438.8587143860132, "reasoning": "highest", "reasoning_bracket": "highest", "reasoning_setting": "highest", "repair_status": "repaired", "score": 25.32370388835863, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 17, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 17, "generated_at": "2026-07-03T19:35:00Z", "losses": 10, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-650d06103e7fa176", "rated_matches": 34, "raw_elo_rating": 1470.498222600706, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 28.988352652103423, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 21, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 21, "generated_at": "2026-07-02T06:10:40Z", "losses": 10, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-b5eb7da0f5021b69", "rated_matches": 32, "raw_elo_rating": 1394.7295192115866, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 16.937801278346626, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 45, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 45, "generated_at": "2026-07-02T16:51:45Z", "losses": 15, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-cabbf604f15eb575", "rated_matches": 62, "raw_elo_rating": 1374.319686659771, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 16.755924223402463, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 52, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 52, "generated_at": "2026-07-01T00:15:48Z", "losses": 6, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-d51fce0298267f96", "rated_matches": 58, "raw_elo_rating": 1444.0676433143008, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 27.30072337700811, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 27, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 27, "generated_at": "2026-07-02T16:51:45Z", "losses": 3, "model": "xiaomi/mimo-v2.5-pro", "point_rating_method": "sequential_elo", "public_id": "E-bd1bb7ac29877b8f", "rated_matches": 32, "raw_elo_rating": 1453.6706238024155, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 26.068747640283966, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 30, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 30, "generated_at": "2026-07-02T06:10:40Z", "losses": 10, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-1549af3bdbe8e3c4", "rated_matches": 44, "raw_elo_rating": 1457.469347598416, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 28.20679701672494, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 40, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 40, "generated_at": "2026-07-01T00:15:48Z", "losses": 3, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-18e15798a90b1d2f", "rated_matches": 44, "raw_elo_rating": 1460.632560055503, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 28.696830643980192, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 37, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 37, "generated_at": "2026-07-11T14:00:45Z", "losses": 5, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-6a361d88d8c1fb48", "rated_matches": 44, "raw_elo_rating": 1467.5919279050256, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 29.77495116764729, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 0, "generated_at": "2026-07-11T14:00:45Z", "losses": 23, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-907d60010bf80864", "rated_matches": 64, "raw_elo_rating": 1691.9955525601144, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 66.09018683609693, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 41 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 15, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-97efd9455394f6d7", "rated_matches": 44, "raw_elo_rating": 1607.1365868151802, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 51.39271358402592, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 58, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 58, "generated_at": "2026-07-02T06:10:40Z", "losses": 14, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-9e8f3e43bfd2810e", "rated_matches": 72, "raw_elo_rating": 1402.0577696393814, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 21.607425038471657, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 3, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 3, "generated_at": "2026-07-02T06:10:40Z", "losses": 17, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-b87c8a15936f0f63", "rated_matches": 44, "raw_elo_rating": 1535.0704831205398, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 40.22848902600901, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 30, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 30, "generated_at": "2026-07-02T16:51:45Z", "losses": 30, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-bc28f817090c9f60", "rated_matches": 62, "raw_elo_rating": 1308.0570686179608, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 6.490755028805242, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 38, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 38, "generated_at": "2026-07-11T17:22:09Z", "losses": 5, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-da1e9a6be31e371f", "rated_matches": 44, "raw_elo_rating": 1452.9805821593848, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 27.511413434424572, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 1 } ] } } }