{ "benchmark_line": "gamebench2", "generated_at": "2026-07-28T14:34:29Z", "public_release_id": "gb2-20260728-67bc5cf10e2e", "results_cut_id": "gb2-20260728-67bc5cf10e2e", "schema_version": 2, "snapshot_id": "20260728_143429", "tracks": { "full_freedom/balanced": { "GB2-01": [ { "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": 20, "model": "claude-fable-5", "point_rating_method": "sequential_elo", "public_id": "E-2dbc6efbd7db03b5", "rated_matches": 60, "raw_elo_rating": 1683.5740198568387, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 69.93910267106604, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 40 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 9, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 9, "generated_at": "2026-07-02T16:51:45Z", "losses": 26, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-13ec9509bc80f2bf", "rated_matches": 58, "raw_elo_rating": 1487.721422135228, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 45.78994213262309, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 5, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 5, "generated_at": "2026-07-25T15:48:00Z", "losses": 18, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-0437af9582860271", "rated_matches": 54, "raw_elo_rating": 1555.9230220837762, "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": 53.9341946903938, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 31 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 2, "coverage_status": "rated", "distinct_rated_opponents": 27, "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": 54, "raw_elo_rating": 1703.84709742756, "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": 72.09382214243796, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 8, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 8, "generated_at": "2026-07-02T16:51:45Z", "losses": 26, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-cd50a27a6bb44b58", "rated_matches": 66, "raw_elo_rating": 1453.4311708784803, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 41.974160447041655, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 26, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 26, "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": 48, "raw_elo_rating": 1352.8818752557147, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 28.61453589959575, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 8, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 8, "generated_at": "2026-07-01T00:15:48Z", "losses": 25, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-fd9da5310ad15cac", "rated_matches": 54, "raw_elo_rating": 1620.8077045088708, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 61.89964356979712, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 35, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 35, "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": 64, "raw_elo_rating": 1450.7657677567693, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 41.55535155576687, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "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": 60, "raw_elo_rating": 1844.99143016808, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 89.7552146103392, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 51 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 20, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 20, "generated_at": "2026-07-24T13:40:00Z", "losses": 25, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-77d8df8cd762fd09", "rated_matches": 72, "raw_elo_rating": 1489.7919739948888, "reasoning": "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": 46.68975405941891, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 27 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 13, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 13, "generated_at": "2026-07-24T13:40:00Z", "losses": 34, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-fc3c30006929710a", "rated_matches": 66, "raw_elo_rating": 1526.2127800710075, "reasoning": "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": 50.90906103861127, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 35, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 35, "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": 66, "raw_elo_rating": 1327.504805744083, "reasoning": "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": 26.5150414908058, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 2, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 2, "generated_at": "2026-07-24T13:40:00Z", "losses": 9, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-7484f4e7d8863a3b", "rated_matches": 66, "raw_elo_rating": 1856.4537079549752, "reasoning": "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": 91.45048207404956, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 55 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 19, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 19, "generated_at": "2026-07-02T16:51:45Z", "losses": 29, "model": "gpt-5", "point_rating_method": "sequential_elo", "public_id": "E-adee794ecd761044", "rated_matches": 64, "raw_elo_rating": 1357.5991262730408, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 30.11791991138669, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 26, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 26, "generated_at": "2026-07-02T16:51:45Z", "losses": 13, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-586de6c9939561c3", "rated_matches": 66, "raw_elo_rating": 1666.0791613055155, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 68.07950047101149, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 27 }, { "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": 1603.3998294781852, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 60.09666542640562, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 31 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 18, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 18, "generated_at": "2026-07-01T00:15:48Z", "losses": 36, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-aa899d4eca8a2891", "rated_matches": 62, "raw_elo_rating": 1304.5057479594527, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 23.50408546806865, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 84, "capped_draws": 11, "coverage_status": "rated", "distinct_rated_opponents": 42, "draws": 11, "generated_at": "2026-07-02T06:10:40Z", "losses": 33, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-c675a6c67536654d", "rated_matches": 84, "raw_elo_rating": 1502.2011058063451, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 48.634261080942416, "uncertainty": 10.482614454664043, "unilateral_faults": 0, "wins": 40 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 19, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 19, "generated_at": "2026-07-02T06:10:40Z", "losses": 25, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-22c14c8deb751cb3", "rated_matches": 60, "raw_elo_rating": 1378.65720566583, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 32.50654994627, "uncertainty": 20.268439966447993, "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": 1418.5035046960031, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 37.49881072082661, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 10, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 10, "generated_at": "2026-07-01T00:15:48Z", "losses": 49, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-98c36ba5e36ecf75", "rated_matches": 60, "raw_elo_rating": 1113.866457280888, "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": 20.268439966447993, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 10, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 10, "generated_at": "2026-07-09T17:30:50Z", "losses": 49, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-c48c1aed1cdecc72", "rated_matches": 60, "raw_elo_rating": 1150.5504577389338, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 4.503443947312286, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 39, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 39, "generated_at": "2026-07-02T16:51:45Z", "losses": 3, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-e4496be687faac9d", "rated_matches": 60, "raw_elo_rating": 1590.4682109147573, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 58.50913902194425, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 8, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 8, "generated_at": "2026-07-10T05:30:29Z", "losses": 26, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-4f775a5b7b265dae", "rated_matches": 68, "raw_elo_rating": 1645.9200434293616, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 65.69228710920916, "uncertainty": 16.4429265428846, "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": "2026-07-10T05:30:29Z", "losses": 29, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-bc834303cebba06a", "rated_matches": 62, "raw_elo_rating": 1603.5304016092489, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 60.21329792477527, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 33 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 22, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 22, "generated_at": "2026-07-10T05:30:29Z", "losses": 20, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-46de264ad4571b48", "rated_matches": 62, "raw_elo_rating": 1498.983410367778, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 47.378778542011254, "uncertainty": 19.244078834871203, "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": "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": 1459.2155603129977, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 40.38312858490863, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 16 }, { "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": 21, "model": "moonshotai/kimi-k2.7-code", "point_rating_method": "sequential_elo", "public_id": "E-4935e918b1e70ea1", "rated_matches": 42, "raw_elo_rating": 1497.308406643702, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 45.87134893587861, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 28, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 28, "generated_at": "2026-07-24T14:00:00Z", "losses": 12, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-6cc4477cf8936e55", "rated_matches": 48, "raw_elo_rating": 1482.4062234003072, "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": 44.51535463250467, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 14, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 14, "generated_at": "2026-07-21T14:43:57Z", "losses": 6, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-ee608da1db5fc482", "rated_matches": 34, "raw_elo_rating": 1589.456695453392, "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": 56.37194235700224, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 14, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 14, "generated_at": "2026-07-02T16:51:45Z", "losses": 29, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-b851008baae8f441", "rated_matches": 72, "raw_elo_rating": 1500.6871955211363, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 48.02728592138475, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 10, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 10, "generated_at": "2026-07-02T16:51:45Z", "losses": 24, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-428923c2eb87dc7a", "rated_matches": 68, "raw_elo_rating": 1526.8363065441854, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 51.07319084373484, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 20, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 20, "generated_at": "2026-07-02T16:51:45Z", "losses": 24, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-a3e0c8f8ea39b5ec", "rated_matches": 60, "raw_elo_rating": 1397.6747028116988, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 34.84119805839559, "uncertainty": 20.268439966447993, "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": 34, "capped_draws": 9, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 9, "generated_at": "2026-07-02T16:51:45Z", "losses": 16, "model": "qwen/qwen3.7-max", "point_rating_method": "sequential_elo", "public_id": "E-24581eb49b81bf8f", "rated_matches": 34, "raw_elo_rating": 1429.107788816565, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 36.6870033090479, "uncertainty": 40.76542547285167, "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": 1496.6188223697204, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 45.606222132078074, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 15, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 15, "generated_at": "2026-07-24T13:40:00Z", "losses": 24, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-7382cf954e1b755d", "rated_matches": 66, "raw_elo_rating": 1455.0498647650818, "reasoning": "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": 42.17287642935396, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 27 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 26, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 26, "generated_at": "2026-07-24T13:40:00Z", "losses": 27, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-c9890f6abafaf54f", "rated_matches": 66, "raw_elo_rating": 1294.0874891238236, "reasoning": "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": 22.412625985685597, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 82, "capped_draws": 7, "coverage_status": "rated", "distinct_rated_opponents": 41, "draws": 7, "generated_at": "2026-07-17T22:36:00Z", "losses": 42, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-abb31ae26e404d88", "rated_matches": 82, "raw_elo_rating": 1462.056816210286, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 43.642231826323574, "uncertainty": 11.132129994845172, "unilateral_faults": 0, "wins": 33 }, { "admitted_plugin_count": 1, "attempted_matches": 76, "capped_draws": 6, "coverage_status": "rated", "distinct_rated_opponents": 38, "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": 76, "raw_elo_rating": 1825.3784261046408, "reasoning": "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": 88.03868080320296, "uncertainty": 13.230288229818967, "unilateral_faults": 0, "wins": 60 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 12, "coverage_status": "rated", "distinct_rated_opponents": 33, "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": 66, "raw_elo_rating": 1646.142849491161, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 65.63205576348118, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 8, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 8, "generated_at": "2026-07-02T16:51:45Z", "losses": 17, "model": "x-ai/grok-build-0.1", "point_rating_method": "sequential_elo", "public_id": "E-f1ded648f3ab17dc", "rated_matches": 44, "raw_elo_rating": 1506.4490343059604, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 47.16178330789564, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 3, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 3, "generated_at": "2026-07-02T16:51:45Z", "losses": 18, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-1208f50b0908ecb4", "rated_matches": 42, "raw_elo_rating": 1492.9024648281463, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 45.33046158025427, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 4, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 4, "generated_at": "2026-07-02T06:10:40Z", "losses": 26, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-2a71bee21bd7c0b9", "rated_matches": 48, "raw_elo_rating": 1488.3764895552486, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 45.248283392825215, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 34, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 34, "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": 48, "raw_elo_rating": 1475.508755653665, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 43.66859967155317, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 4, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 4, "generated_at": "2026-07-11T17:22:09Z", "losses": 20, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-f889d782e3cce209", "rated_matches": 50, "raw_elo_rating": 1431.4781468541285, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 38.40218824126544, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 26 } ], "GB2-02": [ { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 31, "generated_at": "2026-07-02T16:51:45Z", "losses": 9, "model": "claude-fable-5", "point_rating_method": "sequential_elo", "public_id": "E-cd3608270e8c00fd", "rated_matches": 64, "raw_elo_rating": 1636.8022098052088, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 64.91511947130134, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 45, "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": 50, "raw_elo_rating": 1475.402260482471, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 25.370766045966345, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 23, "generated_at": "2026-07-25T10:50:00Z", "losses": 10, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-50b401cafe71e710", "rated_matches": 56, "raw_elo_rating": 1652.955076470378, "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": 67.92823779226067, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 27, "generated_at": "2026-07-25T10:50:00Z", "losses": 7, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-8a5bf2e23121edf6", "rated_matches": 54, "raw_elo_rating": 1631.9817217201396, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 62.76051011951749, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 20 }, { "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": 3, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-a1a16bb5799cfdbe", "rated_matches": 60, "raw_elo_rating": 1487.5573627493632, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 29.365695602250742, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 36, "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": 42, "raw_elo_rating": 1449.902229991137, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 18.185676434085963, "uncertainty": 32.49928516630233, "unilateral_faults": 1, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 41, "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": 42, "raw_elo_rating": 1497.5964351716725, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 29.425648522700747, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 53, "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": 62, "raw_elo_rating": 1491.9455099224035, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 30.592965958181995, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 61, "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": 68, "raw_elo_rating": 1489.7324730104383, "reasoning": "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": 30.599537526773265, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 67, "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": 68, "raw_elo_rating": 1481.4729062717392, "reasoning": "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": 28.653026430601027, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 66, "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": 70, "raw_elo_rating": 1470.6574745098255, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 26.26515964856663, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 65, "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": 66, "raw_elo_rating": 1481.321900682551, "reasoning": "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": 28.449305559055883, "uncertainty": 17.33472217815261, "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": 1459.0930765758949, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 23.37882885928049, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 53, "generated_at": "2026-07-02T06:10:40Z", "losses": 4, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-3082b8a32a9c1e1f", "rated_matches": 60, "raw_elo_rating": 1494.7479081869635, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 31.060273166015826, "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": 60, "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": 64, "raw_elo_rating": 1481.7298499274937, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 28.369610637610304, "uncertainty": 18.26736729460423, "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": "2026-07-02T16:51:45Z", "losses": 2, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-6724998b59176607", "rated_matches": 54, "raw_elo_rating": 1477.6874336305343, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 26.39836748614762, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 63, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 54, "generated_at": "2026-07-01T00:15:48Z", "losses": 7, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-6a4ccfcf11c5e3f3", "rated_matches": 63, "raw_elo_rating": 1474.8171470134807, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 26.64951885685805, "uncertainty": 18.75, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 49, "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": 52, "raw_elo_rating": 1474.6633957814352, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 25.448091621557595, "uncertainty": 24.930281974344517, "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": "2026-07-02T16:51:45Z", "losses": 3, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-d96eaa4f1d20c47b", "rated_matches": 66, "raw_elo_rating": 1483.123702192543, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 28.873931540448716, "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": 34, "generated_at": "2026-07-02T16:51:45Z", "losses": 12, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-8460841e3919c568", "rated_matches": 62, "raw_elo_rating": 1542.631132430455, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 42.53791776371207, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 59, "generated_at": "2026-07-10T05:30:29Z", "losses": 1, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-e2dda893ae4363f2", "rated_matches": 60, "raw_elo_rating": 1485.1956413229286, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 28.80911471755574, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 30, "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": 64, "raw_elo_rating": 1557.8041669293343, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 46.29785153237801, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 54, "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": 56, "raw_elo_rating": 1486.2662373624098, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 28.645102829320255, "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": "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": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 30, "generated_at": "2026-07-02T16:51:45Z", "losses": 2, "model": "minimax/minimax-m3", "point_rating_method": "sequential_elo", "public_id": "E-cad87bcb23d33fef", "rated_matches": 32, "raw_elo_rating": 1464.6310084541792, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 19.62257491103967, "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": 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": 1461.747653970409, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 18.943062089796843, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 38, "generated_at": "2026-07-24T14:00:00Z", "losses": 4, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-8825a1d540d89836", "rated_matches": 42, "raw_elo_rating": 1477.719665153068, "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": 24.741340662338175, "uncertainty": 32.49928516630233, "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": "2026-07-21T14:43:57Z", "losses": 3, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-be8e56a3b58c5bcc", "rated_matches": 32, "raw_elo_rating": 1517.4994211194166, "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": 32.0819393239128, "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": 58, "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": 60, "raw_elo_rating": 1477.573967254025, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 27.012934165249288, "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": 55, "generated_at": "2026-07-02T16:51:45Z", "losses": 4, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-8f0c6569aa132f8e", "rated_matches": 60, "raw_elo_rating": 1478.4308374646337, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 27.214870589482516, "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": "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": 36, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 32, "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": 36, "raw_elo_rating": 1501.7510369677718, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 29.282936560242895, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 38, "generated_at": "2026-07-02T16:51:45Z", "losses": 5, "model": "qwen/qwen3.7-plus", "point_rating_method": "sequential_elo", "public_id": "E-57293d5b71f14882", "rated_matches": 44, "raw_elo_rating": 1484.4653388827323, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 26.65416444437566, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 53, "generated_at": "2026-07-02T16:51:45Z", "losses": 6, "model": "stepfun/step-3.7-flash", "point_rating_method": "sequential_elo", "public_id": "E-0ccea44addccfff0", "rated_matches": 60, "raw_elo_rating": 1492.386996118362, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 30.503883020623825, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 65, "generated_at": "2026-07-24T13:40:00Z", "losses": 7, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-63e0985794df5d5b", "rated_matches": 72, "raw_elo_rating": 1474.1670464469105, "reasoning": "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": 27.24656835203928, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 31, "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": 60, "raw_elo_rating": 1591.688437333961, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 53.906001231790846, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 84, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 42, "draws": 56, "generated_at": "2026-07-24T14:00:00Z", "losses": 15, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-da5ea0258e71b6ab", "rated_matches": 84, "raw_elo_rating": 1506.3447777590582, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 35.638238433963316, "uncertainty": 10.482614454664043, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 33, "generated_at": "2026-07-02T16:51:45Z", "losses": 3, "model": "x-ai/grok-build-0.1", "point_rating_method": "sequential_elo", "public_id": "E-99592fa0331c6679", "rated_matches": 38, "raw_elo_rating": 1505.5724580315348, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 30.586119737224937, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 32, "generated_at": "2026-07-02T16:51:45Z", "losses": 4, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-5b213ae773e821cc", "rated_matches": 38, "raw_elo_rating": 1492.7593511110604, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 27.56648740223964, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 29, "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": 32, "raw_elo_rating": 1465.4021769870442, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 19.804314238746468, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 0 }, { "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-c37f25e181320efb", "rated_matches": 38, "raw_elo_rating": 1481.6528261727108, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 24.94904090457791, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 40, "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": 42, "raw_elo_rating": 1468.8623880163934, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 22.65396867615027, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 0 } ], "GB2-03": [ { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 5, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 25, "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": 42, "raw_elo_rating": 1456.992704704807, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 38.09391002162233, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "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": 42, "raw_elo_rating": 1770.1925604080766, "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": 90.45821307999611, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 33 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 22, "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": 44, "raw_elo_rating": 1806.7805996235456, "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": 96.80462707901296, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 38 }, { "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": 1444.616242265077, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 32.27852714847803, "uncertainty": 60.5072070285374, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 9, "generated_at": "2026-07-01T00:15:48Z", "losses": 10, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-32e04fe5ad231857", "rated_matches": 32, "raw_elo_rating": 1548.4644867532702, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 51.94406520454458, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 16, "generated_at": "2026-07-02T16:51:45Z", "losses": 15, "model": "google/gemini-3.5-flash", "point_rating_method": "sequential_elo", "public_id": "E-8ed795ea8fd1e0aa", "rated_matches": 54, "raw_elo_rating": 1584.4380808026062, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 60.58261886572101, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 3, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 21, "generated_at": "2026-07-24T13:40:00Z", "losses": 18, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-36e89f1dca2cd568", "rated_matches": 54, "raw_elo_rating": 1534.5721625266235, "reasoning": "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": 52.245469249146645, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 18, "generated_at": "2026-07-24T13:40:00Z", "losses": 19, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-e51f710b50e975e5", "rated_matches": 54, "raw_elo_rating": 1494.9601751869436, "reasoning": "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": 45.62268806956448, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 2, "coverage_status": "rated", "distinct_rated_opponents": 26, "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": 52, "raw_elo_rating": 1568.0269179489935, "reasoning": "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": 57.67024616007308, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 3, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 14, "generated_at": "2026-07-24T13:40:00Z", "losses": 19, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-f44c7c8e627e08cd", "rated_matches": 56, "raw_elo_rating": 1551.7329489848184, "reasoning": "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": 55.27422079196909, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 29, "generated_at": "2026-07-02T16:51:45Z", "losses": 12, "model": "gpt-5", "point_rating_method": "sequential_elo", "public_id": "E-e724ba162431d43a", "rated_matches": 46, "raw_elo_rating": 1431.7303930296262, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 34.31390109131504, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 2, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 25, "generated_at": "2026-07-02T16:51:45Z", "losses": 19, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-496f83ad0bd69447", "rated_matches": 56, "raw_elo_rating": 1400.8815780438904, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 30.053178186490474, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 8, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 21, "generated_at": "2026-07-01T00:15:48Z", "losses": 13, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-3e164d6fc6c16cbb", "rated_matches": 50, "raw_elo_rating": 1552.5018653012748, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 54.89620238599134, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 13, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 27, "generated_at": "2026-07-02T06:10:40Z", "losses": 11, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-7cbcc752e71e2d3b", "rated_matches": 44, "raw_elo_rating": 1461.2632800472154, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 39.037123982353414, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 9, "coverage_status": "rated", "distinct_rated_opponents": 27, "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": 54, "raw_elo_rating": 1537.3428421012582, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 52.70870287547778, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 13 }, { "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": 1408.753378227649, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 30.673497730348966, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 4, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 23, "generated_at": "2026-07-02T16:51:45Z", "losses": 14, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-c002b0ea38b845f8", "rated_matches": 46, "raw_elo_rating": 1468.040920087715, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 40.38470670777879, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 15, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 35, "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": 44, "raw_elo_rating": 1489.5459265778684, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 43.76573750900555, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 2, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 14, "generated_at": "2026-07-10T05:30:29Z", "losses": 12, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-b741de451c385e8e", "rated_matches": 50, "raw_elo_rating": 1582.5689592229082, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 59.92316006022683, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 25, "generated_at": "2026-07-10T05:30:29Z", "losses": 9, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-e44c62bb88a3042a", "rated_matches": 40, "raw_elo_rating": 1500.0753756097706, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 45.05117535357613, "uncertainty": 34.33688094430304, "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": 24, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 11, "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": 22, "raw_elo_rating": 1651.4966395310923, "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": 66.86713765389882, "uncertainty": 60.5072070285374, "unilateral_faults": 1, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 22, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 11, "draws": 6, "generated_at": "2026-07-24T14:00:00Z", "losses": 8, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-b97350a867368460", "rated_matches": 22, "raw_elo_rating": 1513.3940866178589, "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": 43.77758699735245, "uncertainty": 60.5072070285374, "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": 1477.2378787461882, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 38.806908566038985, "uncertainty": 52.475044864937615, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 4, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 28, "generated_at": "2026-07-02T16:51:45Z", "losses": 13, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-87b4bd61da369b42", "rated_matches": 48, "raw_elo_rating": 1426.7962430236144, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 33.69010844396414, "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": "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": 60, "capped_draws": 6, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 33, "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": 60, "raw_elo_rating": 1495.8404344667613, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 46.224827056787426, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 4, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 24, "generated_at": "2026-07-24T14:00:00Z", "losses": 17, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-cbed46472ce4dd05", "rated_matches": 64, "raw_elo_rating": 1535.107382073436, "reasoning": "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": 53.05757019618682, "uncertainty": 18.26736729460423, "unilateral_faults": 1, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 7, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 20, "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": 44, "raw_elo_rating": 1543.708942096389, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 52.82132456474889, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 22, "capped_draws": 1, "coverage_status": "under_covered", "distinct_rated_opponents": 11, "draws": 10, "generated_at": "2026-07-02T16:51:45Z", "losses": 7, "model": "x-ai/grok-build-0.1", "point_rating_method": "sequential_elo", "public_id": "E-2a93343a8a88fd59", "rated_matches": 22, "raw_elo_rating": 1512.2395415346, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 43.58455705965157, "uncertainty": 60.5072070285374, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 6, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 21, "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": 32, "raw_elo_rating": 1483.3794346590705, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 41.06240823577625, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 5 } ], "GB2-04": [ { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 25, "generated_at": "2026-07-02T16:51:45Z", "losses": 15, "model": "claude-fable-5", "point_rating_method": "sequential_elo", "public_id": "E-eb1f17ce19beffd0", "rated_matches": 62, "raw_elo_rating": 1581.0598602467503, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 51.78455451097985, "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": 47, "generated_at": "2026-07-02T16:51:45Z", "losses": 7, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-caf91ab5b69b1e64", "rated_matches": 58, "raw_elo_rating": 1466.485643264073, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 29.004017345869457, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 31, "generated_at": "2026-07-25T15:48:00Z", "losses": 13, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-048d3dcf802043b4", "rated_matches": 58, "raw_elo_rating": 1538.6551452561764, "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": 43.14591949521648, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 20, "generated_at": "2026-07-25T15:48:00Z", "losses": 14, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-d0f0a2b1c4bbddae", "rated_matches": 54, "raw_elo_rating": 1539.3499750795136, "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": 42.91751654259464, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 48, "generated_at": "2026-07-02T16:51:45Z", "losses": 8, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-b1fc5b99a5deb881", "rated_matches": 68, "raw_elo_rating": 1495.0551444554867, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 35.3707045451438, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugin_count": 1, "attempted_matches": 24, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 12, "draws": 18, "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": 24, "raw_elo_rating": 1480.403456405545, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 26.259363733302056, "uncertainty": 56.25, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 41, "generated_at": "2026-07-01T00:15:48Z", "losses": 5, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-5d143d6301429619", "rated_matches": 48, "raw_elo_rating": 1466.5672296334092, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 28.02704826832348, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 43, "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": 50, "raw_elo_rating": 1495.4259070579112, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 33.9037734449991, "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": 34, "generated_at": "2026-07-02T16:51:45Z", "losses": 9, "model": "google/gemini-3.5-flash", "point_rating_method": "sequential_elo", "public_id": "E-32cfa6c9dfb1d16f", "rated_matches": 56, "raw_elo_rating": 1533.857806977198, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 42.028380510266544, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 56, "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": 67, "raw_elo_rating": 1504.8720377502932, "reasoning": "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": 37.2252346041612, "uncertainty": 16.883906259083243, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 54, "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": 69, "raw_elo_rating": 1472.5821006203996, "reasoning": "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": 31.034664555308932, "uncertainty": 16.01143046671968, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 69, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 40, "generated_at": "2026-07-24T13:40:00Z", "losses": 13, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-1ff96286ae16ecd4", "rated_matches": 68, "raw_elo_rating": 1494.233632097183, "reasoning": "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": 35.20972591753903, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 50, "generated_at": "2026-07-24T13:40:00Z", "losses": 9, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-d109ab12db58a65f", "rated_matches": 68, "raw_elo_rating": 1476.497140927611, "reasoning": "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": 31.734189636018268, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 27, "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": 36, "raw_elo_rating": 1539.3989299517496, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 40.610226642627, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 78, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 39, "draws": 50, "generated_at": "2026-07-02T16:51:45Z", "losses": 12, "model": "gpt-5", "point_rating_method": "sequential_elo", "public_id": "E-6f1aae863396df76", "rated_matches": 78, "raw_elo_rating": 1548.0131095292184, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 46.365446088704815, "uncertainty": 12.5043950463012, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 43, "generated_at": "2026-07-02T16:51:45Z", "losses": 7, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-0b4132559ee98caf", "rated_matches": 66, "raw_elo_rating": 1521.843945614986, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 40.48027638959632, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 41, "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": 62, "raw_elo_rating": 1569.7783785164224, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 49.57390310940306, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 35, "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": 62, "raw_elo_rating": 1568.7055868234213, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 49.36368529259289, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 51, "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": 68, "raw_elo_rating": 1530.5831222317804, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 42.332553683738304, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 36, "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": 64, "raw_elo_rating": 1573.0644962351932, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 50.370943422371525, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 20 }, { "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": 1533.704734035738, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 43.078097240001945, "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": 41, "generated_at": "2026-07-02T16:51:45Z", "losses": 14, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-9e7bdad81107b7e4", "rated_matches": 64, "raw_elo_rating": 1449.039720517403, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 26.067793284414353, "uncertainty": 18.26736729460423, "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": 1512.2196063935532, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 38.29503183096133, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 59, "generated_at": "2026-07-10T05:30:29Z", "losses": 7, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-c81bf4d15f3d48f1", "rated_matches": 70, "raw_elo_rating": 1483.3945244178965, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 33.21961073407453, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 54, "generated_at": "2026-07-10T05:30:29Z", "losses": 7, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-89c18d144e85d89f", "rated_matches": 70, "raw_elo_rating": 1505.8676356462586, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 37.623306633454085, "uncertainty": 15.58908290969266, "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": "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": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 29, "generated_at": "2026-07-02T16:51:45Z", "losses": 3, "model": "minimax/minimax-m3", "point_rating_method": "sequential_elo", "public_id": "E-c60620c3c72a6064", "rated_matches": 32, "raw_elo_rating": 1462.166968986042, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 24.717685927847732, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 26, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 13, "draws": 20, "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": 26, "raw_elo_rating": 1483.3504319083952, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 27.428609381105517, "uncertainty": 52.475044864937615, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 25, "generated_at": "2026-07-21T14:43:57Z", "losses": 13, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-0f7ca9245c7db7c7", "rated_matches": 52, "raw_elo_rating": 1479.532620120741, "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": 30.99849895195425, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 29, "generated_at": "2026-07-24T14:00:00Z", "losses": 6, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-35e5c9532c697b2c", "rated_matches": 38, "raw_elo_rating": 1478.1778373322668, "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": 28.948463788698337, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 47, "generated_at": "2026-07-02T16:51:45Z", "losses": 8, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-7e92e17a121661f4", "rated_matches": 58, "raw_elo_rating": 1453.38347630081, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 26.43659540135972, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 42, "generated_at": "2026-07-02T16:51:45Z", "losses": 6, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-f1288f2abfdbbfe4", "rated_matches": 52, "raw_elo_rating": 1470.896254983829, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 29.306168711049935, "uncertainty": 24.930281974344517, "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": 28, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 14, "draws": 17, "generated_at": "2026-07-02T16:51:45Z", "losses": 7, "model": "qwen/qwen3.7-max", "point_rating_method": "sequential_elo", "public_id": "E-ea08328e287de1ad", "rated_matches": 28, "raw_elo_rating": 1483.2326201707826, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "first_pass", "score": 27.934971918287903, "uncertainty": 49.09766908852594, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 43, "generated_at": "2026-07-02T16:51:45Z", "losses": 4, "model": "stepfun/step-3.7-flash", "point_rating_method": "sequential_elo", "public_id": "E-25e56c6bfae33c62", "rated_matches": 52, "raw_elo_rating": 1525.7581685865202, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 40.05657979162075, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 52, "generated_at": "2026-07-24T13:40:00Z", "losses": 8, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-7ca32267720b2e1a", "rated_matches": 64, "raw_elo_rating": 1495.0703113780432, "reasoning": "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": 35.08767140272284, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 42, "generated_at": "2026-07-24T13:40:00Z", "losses": 12, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-d9e91f86e4e39739", "rated_matches": 60, "raw_elo_rating": 1444.4738152198197, "reasoning": "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": 24.859391360201073, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 37, "draws": 57, "generated_at": "2026-07-17T22:36:00Z", "losses": 7, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-1a7064508fe2a12f", "rated_matches": 74, "raw_elo_rating": 1501.568405879708, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 37.032312332420936, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 49, "generated_at": "2026-07-17T22:36:00Z", "losses": 12, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-83f4cc0ffc20bde5", "rated_matches": 70, "raw_elo_rating": 1496.784910839686, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 35.84351043258728, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 86, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 43, "draws": 61, "generated_at": "2026-07-24T14:00:00Z", "losses": 13, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-ba6a8e6d7fc9a48d", "rated_matches": 86, "raw_elo_rating": 1503.1775544812508, "reasoning": "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": 37.994969393101584, "uncertainty": 9.855626741889738, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugin_count": 1, "attempted_matches": 28, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 14, "draws": 23, "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": 28, "raw_elo_rating": 1486.6872720566844, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 28.61192475268359, "uncertainty": 49.09766908852594, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 28, "generated_at": "2026-07-02T06:10:40Z", "losses": 6, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-00e6914e513b1656", "rated_matches": 36, "raw_elo_rating": 1464.2307841980507, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 25.880728272069145, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 24, "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": 36, "raw_elo_rating": 1434.6389637716811, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 20.082092874300265, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 30, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 15, "draws": 24, "generated_at": "2026-07-02T16:51:45Z", "losses": 6, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-2f7e15b8aa123825", "rated_matches": 30, "raw_elo_rating": 1444.5321443660189, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 20.828805883070206, "uncertainty": 46.05265101338746, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 15, "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": 32, "raw_elo_rating": 1496.005201975642, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 31.34842282690637, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 27, "generated_at": "2026-07-11T17:22:09Z", "losses": 9, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-912f31ad14c4bf0a", "rated_matches": 44, "raw_elo_rating": 1469.2510998588752, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 28.065895749489687, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 12, "generated_at": "2026-07-01T00:15:48Z", "losses": 17, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-947248ef34168cde", "rated_matches": 42, "raw_elo_rating": 1515.6489399725556, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 36.889094946068, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 13 } ], "GB2-05": [ { "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": "claude-fable-5", "point_rating_method": "sequential_elo", "public_id": "E-ad7cf41c05ec3f64", "rated_matches": 60, "raw_elo_rating": 1576.0871543127037, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 55.065570137094625, "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": 30, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-924d7e6ee41b562e", "rated_matches": 70, "raw_elo_rating": 1537.236926140518, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 51.11193183106644, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 40 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 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": 62, "raw_elo_rating": 1783.7336347634437, "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": 78.54251452521142, "uncertainty": 19.244078834871203, "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": "2026-07-25T10:50:00Z", "losses": 11, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-d7111b534ebcaba2", "rated_matches": 62, "raw_elo_rating": 1844.431383861268, "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": 85.37815146132921, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 51 }, { "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": 31, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-e0a09b1ea3f11175", "rated_matches": 76, "raw_elo_rating": 1532.0402550957847, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 50.73920853170654, "uncertainty": 13.230288229818967, "unilateral_faults": 0, "wins": 45 }, { "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": 16, "model": "cohere/north-mini-code", "point_rating_method": "sequential_elo", "public_id": "E-a0518a43c688d1e2", "rated_matches": 42, "raw_elo_rating": 1507.503874989952, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "first_pass", "score": 46.23995635293639, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 0, "generated_at": "2026-07-01T00:15:48Z", "losses": 32, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-06a41d0e11b18b77", "rated_matches": 52, "raw_elo_rating": 1396.8569813632248, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 34.46108749309675, "uncertainty": 24.930281974344517, "unilateral_faults": 2, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 29, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-2c1cbd253f3a9d69", "rated_matches": 52, "raw_elo_rating": 1363.1128299523764, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 30.660900975633034, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 23 }, { "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": 43, "model": "google/gemini-3.1-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-7603462aff103041", "rated_matches": 70, "raw_elo_rating": 1292.0994540643576, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 23.50512954504209, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 27 }, { "admitted_plugin_count": 1, "attempted_matches": 82, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 41, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 46, "model": "google/gemini-3.5-flash", "point_rating_method": "sequential_elo", "public_id": "E-a7ce764239377b3f", "rated_matches": 82, "raw_elo_rating": 1474.9857181649531, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 44.502893226762005, "uncertainty": 11.132129994845172, "unilateral_faults": 0, "wins": 36 }, { "admitted_plugin_count": 1, "attempted_matches": 78, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 37, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 38, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-c311887ca24f8a76", "rated_matches": 74, "raw_elo_rating": 1366.5570300915422, "reasoning": "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": 32.03488163738203, "uncertainty": 13.985026918962571, "unilateral_faults": 2, "wins": 36 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 36, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-e3c1bc55ae62b8db", "rated_matches": 70, "raw_elo_rating": 1361.044656121879, "reasoning": "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": 31.26957512593088, "uncertainty": 15.58908290969266, "unilateral_faults": 2, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 78, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 39, "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": 78, "raw_elo_rating": 1828.180387590261, "reasoning": "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": 84.15520849708763, "uncertainty": 12.5043950463012, "unilateral_faults": 0, "wins": 63 }, { "admitted_plugin_count": 1, "attempted_matches": 80, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 40, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 42, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-c7d3f2597dfefeb3", "rated_matches": 80, "raw_elo_rating": 1600.666830764492, "reasoning": "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": 58.59613118143334, "uncertainty": 11.805555555555554, "unilateral_faults": 0, "wins": 38 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 26, "model": "google/gemma-4-31b-it", "point_rating_method": "sequential_elo", "public_id": "E-fd1bc1e2e6ac48fb", "rated_matches": 52, "raw_elo_rating": 1529.4989801817678, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 49.398915664339874, "uncertainty": 24.930281974344517, "unilateral_faults": 6, "wins": 26 }, { "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": 32, "model": "gpt-5", "point_rating_method": "sequential_elo", "public_id": "E-9e5b308c41a36374", "rated_matches": 66, "raw_elo_rating": 1594.6561013740363, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 57.42107172094892, "uncertainty": 17.33472217815261, "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": "2026-07-02T16:51:45Z", "losses": 34, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-cafab3c275850d3b", "rated_matches": 70, "raw_elo_rating": 1535.7359811804806, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 50.942898959824795, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 36 }, { "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-0791f6b66243ec1a", "rated_matches": 64, "raw_elo_rating": 1461.2661835118558, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 42.31498884641358, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 30 }, { "admitted_plugin_count": 1, "attempted_matches": 80, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 41, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-539afc540807da47", "rated_matches": 72, "raw_elo_rating": 1368.6051517630897, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 32.19476312847781, "uncertainty": 14.770573598065289, "unilateral_faults": 4, "wins": 31 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 0, "generated_at": "2026-07-01T00:15:48Z", "losses": 38, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-ce84b7a3c6105fb2", "rated_matches": 64, "raw_elo_rating": 1400.4932946391689, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 35.47088984657748, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 51, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-83cfa14483bf0d43", "rated_matches": 64, "raw_elo_rating": 1245.267602758152, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 17.98973957943594, "uncertainty": 18.26736729460423, "unilateral_faults": 2, "wins": 13 }, { "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": 17, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-8e40431df091d53f", "rated_matches": 74, "raw_elo_rating": 1754.4732503803718, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 75.72108883514751, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 57 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 0, "generated_at": "2026-07-09T17:30:50Z", "losses": 44, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-a0d8c8fd6b01598c", "rated_matches": 72, "raw_elo_rating": 1401.8017054794216, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 35.93328048880792, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "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-ff2b4db95370e3d6", "rated_matches": 68, "raw_elo_rating": 1303.70499708439, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 24.73519206926743, "uncertainty": 16.4429265428846, "unilateral_faults": 2, "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": 27, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-ffa82d1e96e897ab", "rated_matches": 70, "raw_elo_rating": 1666.0116361417768, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 65.61423508293475, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 43 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 33, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-e917387a1c57aa23", "rated_matches": 62, "raw_elo_rating": 1580.9116397569835, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 55.70118117875034, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 37, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 29, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-d61f8454991c5422", "rated_matches": 74, "raw_elo_rating": 1637.7720719272563, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 62.57847814892709, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 45 }, { "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-terra", "point_rating_method": "sequential_elo", "public_id": "E-9664e98d37ece097", "rated_matches": 66, "raw_elo_rating": 1556.1844675568093, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 53.08848731670678, "uncertainty": 17.33472217815261, "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": "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": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 34, "model": "minimax/minimax-m3", "point_rating_method": "sequential_elo", "public_id": "E-fb8ac45946e32e22", "rated_matches": 38, "raw_elo_rating": 1224.8792762545324, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 14.067752272340876, "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": 20, "model": "moonshotai/kimi-k2.7-code", "point_rating_method": "sequential_elo", "public_id": "E-952fba19b28982d5", "rated_matches": 38, "raw_elo_rating": 1549.3907801120831, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 50.61347027563539, "uncertainty": 36.31407690254356, "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": "2026-07-21T14:43:57Z", "losses": 19, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-4a1443311507f194", "rated_matches": 38, "raw_elo_rating": 1552.219483093816, "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": 50.93203211475854, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 30, "model": "nex-agi/nex-n2-pro", "point_rating_method": "sequential_elo", "public_id": "E-5f76f577111bee8d", "rated_matches": 38, "raw_elo_rating": 1286.863854304965, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 21.048308841388355, "uncertainty": 36.31407690254356, "unilateral_faults": 2, "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": 1511.7322847617274, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 48.16273316433884, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 36 }, { "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": 35, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-5ef540286ecbb63d", "rated_matches": 68, "raw_elo_rating": 1423.8445683656728, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 38.26502642302819, "uncertainty": 16.4429265428846, "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": 48, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 29, "model": "qwen/qwen3.7-max", "point_rating_method": "sequential_elo", "public_id": "E-435ec29661cdc285", "rated_matches": 48, "raw_elo_rating": 1509.8875319944243, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 46.94271606979717, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 19 }, { "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": 22, "model": "qwen/qwen3.7-plus", "point_rating_method": "sequential_elo", "public_id": "E-6cc7454f585005c4", "rated_matches": 50, "raw_elo_rating": 1498.8448079056152, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 45.82655477428856, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 28 }, { "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": 26, "model": "stepfun/step-3.7-flash", "point_rating_method": "sequential_elo", "public_id": "E-7b9b33921ba865f5", "rated_matches": 66, "raw_elo_rating": 1583.6391550622056, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 56.18036928549278, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 40 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 37, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-01a1df4eac0e6aef", "rated_matches": 70, "raw_elo_rating": 1348.1334066224467, "reasoning": "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": 29.815540746047837, "uncertainty": 15.58908290969266, "unilateral_faults": 2, "wins": 33 }, { "admitted_plugin_count": 1, "attempted_matches": 76, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 38, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 43, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-ae60ed096a69eeff", "rated_matches": 76, "raw_elo_rating": 1391.529556899853, "reasoning": "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": 34.91522604827307, "uncertainty": 13.230288229818967, "unilateral_faults": 0, "wins": 33 }, { "admitted_plugin_count": 1, "attempted_matches": 90, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 45, "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-824ec3caceabd338", "rated_matches": 90, "raw_elo_rating": 1651.5268455955904, "reasoning": "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": 64.60687961024074, "uncertainty": 8.664241836095918, "unilateral_faults": 0, "wins": 56 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "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": 70, "raw_elo_rating": 1777.9603866057128, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 78.22163856984506, "uncertainty": 15.58908290969266, "unilateral_faults": 2, "wins": 52 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 0, "generated_at": "2026-07-18T00:06:00Z", "losses": 27, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-c0bc4ff29a3cbf96", "rated_matches": 72, "raw_elo_rating": 1728.9654475477987, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 72.777687286115, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 45 }, { "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": 1590.3330337676452, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 55.224290042358746, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 21 }, { "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": 20, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-ad48cf51fe7da3cc", "rated_matches": 40, "raw_elo_rating": 1449.1737668928254, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 39.50540099410975, "uncertainty": 34.33688094430304, "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": "2026-07-02T06:10:40Z", "losses": 24, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-faaa866ee28d6401", "rated_matches": 38, "raw_elo_rating": 1396.9773694745934, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 33.44903247030231, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 14 }, { "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": "xiaomi/mimo-v2.5-pro", "point_rating_method": "sequential_elo", "public_id": "E-9c228ad72a159b33", "rated_matches": 38, "raw_elo_rating": 1439.2285062039607, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 38.20725555292037, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 16 }, { "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": 25, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-1a8c2012f200fd88", "rated_matches": 56, "raw_elo_rating": 1639.7406049749611, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 62.035127375812706, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 31 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 0, "generated_at": "2026-07-11T17:22:09Z", "losses": 27, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-3916ba303b2ff700", "rated_matches": 52, "raw_elo_rating": 1545.7295977101912, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 51.22676942040723, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 25 } ], "GB2-06": [ { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "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": 56, "raw_elo_rating": 1680.7525107491392, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 76.68664750233343, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 36 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "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": 64, "raw_elo_rating": 1707.1649512901192, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 80.54297967705504, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 42 }, { "admitted_plugin_count": 1, "attempted_matches": 76, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 38, "draws": 3, "generated_at": "2026-07-02T16:51:45Z", "losses": 33, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-01597b81edc004dd", "rated_matches": 76, "raw_elo_rating": 1485.0135108536388, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 52.29736118277051, "uncertainty": 13.230288229818967, "unilateral_faults": 0, "wins": 40 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 1, "generated_at": "2026-07-02T16:51:45Z", "losses": 29, "model": "cohere/north-mini-code", "point_rating_method": "sequential_elo", "public_id": "E-78dfcb6ce8b3efaa", "rated_matches": 36, "raw_elo_rating": 1259.9497701926696, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "first_pass", "score": 20.540191912025133, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 2, "generated_at": "2026-07-02T06:10:40Z", "losses": 26, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-6f20412107151172", "rated_matches": 46, "raw_elo_rating": 1368.8044629251704, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 35.5963217241142, "uncertainty": 29.182495748947275, "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": "2026-07-01T00:15:48Z", "losses": 34, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-d8ca2fcf88af96c7", "rated_matches": 48, "raw_elo_rating": 1254.222955779497, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 20.914421729563475, "uncertainty": 27.67857142857143, "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": "2026-07-02T16:51:45Z", "losses": 41, "model": "google/gemini-3.1-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-a10101fbca309818", "rated_matches": 64, "raw_elo_rating": 1393.3523465645424, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 39.905904249814974, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 12, "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": 56, "raw_elo_rating": 1754.720265023284, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 86.26508114189525, "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": 1, "generated_at": "2026-07-24T13:40:00Z", "losses": 39, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-100ff33157ca87e5", "rated_matches": 66, "raw_elo_rating": 1322.0096348955046, "reasoning": "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": 30.76401786245334, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 1, "generated_at": "2026-07-24T13:40:00Z", "losses": 37, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-92d447632fa55355", "rated_matches": 68, "raw_elo_rating": 1478.9003989696714, "reasoning": "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": 51.17292971070997, "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": 10, "generated_at": "2026-07-24T13:40:00Z", "losses": 29, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-aa5fab059f4d0186", "rated_matches": 70, "raw_elo_rating": 1538.8753432667752, "reasoning": "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": 59.02782293210099, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 31 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 6, "generated_at": "2026-07-24T13:40:00Z", "losses": 15, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-dd9886be3d9e45b5", "rated_matches": 70, "raw_elo_rating": 1855.2757109550505, "reasoning": "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": 15.58908290969266, "unilateral_faults": 0, "wins": 49 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 29, "model": "google/gemma-4-31b-it", "point_rating_method": "sequential_elo", "public_id": "E-41987f96551bf9d3", "rated_matches": 38, "raw_elo_rating": 1306.0485900110548, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 26.73096583903303, "uncertainty": 36.31407690254356, "unilateral_faults": 1, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 78, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 39, "draws": 8, "generated_at": "2026-07-02T16:51:45Z", "losses": 36, "model": "gpt-5", "point_rating_method": "sequential_elo", "public_id": "E-816d262cd933cdb9", "rated_matches": 78, "raw_elo_rating": 1505.6333421063478, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 55.04271992802316, "uncertainty": 12.5043950463012, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "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": 58, "raw_elo_rating": 1815.6398626593548, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 94.2711346278566, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 43 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 7, "generated_at": "2026-07-02T16:51:45Z", "losses": 23, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-3ccfe46cbdc271eb", "rated_matches": 66, "raw_elo_rating": 1495.052182852292, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 53.17211418347611, "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": "2026-07-01T00:15:48Z", "losses": 33, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-ac7c887de3c2e7af", "rated_matches": 70, "raw_elo_rating": 1591.0072908848572, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 65.77863489957281, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 37 }, { "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": 1583.9245150143784, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 64.14793329235812, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 5, "generated_at": "2026-07-02T06:10:40Z", "losses": 36, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-962a93f9cc008820", "rated_matches": 72, "raw_elo_rating": 1495.5982818808066, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 53.50846608657866, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 31 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 10, "generated_at": "2026-07-01T00:15:48Z", "losses": 35, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-9b6b064b63e4164b", "rated_matches": 68, "raw_elo_rating": 1513.2031076340502, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 55.61494936945502, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 88, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 41, "draws": 2, "generated_at": "2026-07-09T17:30:50Z", "losses": 39, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-9c5263dcfd4c2ec7", "rated_matches": 82, "raw_elo_rating": 1493.0082221112164, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 53.54999441048698, "uncertainty": 11.132129994845172, "unilateral_faults": 3, "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": 38, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-1ea2c2c23d752166", "rated_matches": 64, "raw_elo_rating": 1439.3647361655196, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 45.864265764444326, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "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": 64, "raw_elo_rating": 1618.383682351255, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 69.04627410160604, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 10, "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": 60, "raw_elo_rating": 1699.206178915541, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 79.30505799919712, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 37 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 12, "generated_at": "2026-07-10T05:30:29Z", "losses": 20, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-a3722334e358f0fe", "rated_matches": 66, "raw_elo_rating": 1504.8244147827002, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 54.43756662250657, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 34 }, { "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": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 28, "model": "minimax/minimax-m3", "point_rating_method": "sequential_elo", "public_id": "E-ef8c1a9fa3580f83", "rated_matches": 38, "raw_elo_rating": 1304.7191377341055, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 26.55880878848199, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "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": 36, "raw_elo_rating": 1761.865034837106, "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": 85.53556864418464, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 3, "generated_at": "2026-07-24T14:00:00Z", "losses": 25, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-1640f1438f9390d7", "rated_matches": 54, "raw_elo_rating": 1495.0343771699572, "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": 52.51350184357782, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 3, "generated_at": "2026-07-02T16:51:45Z", "losses": 27, "model": "nex-agi/nex-n2-pro", "point_rating_method": "sequential_elo", "public_id": "E-209380b737b62580", "rated_matches": 38, "raw_elo_rating": 1288.6932218313036, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 24.483537293564577, "uncertainty": 36.31407690254356, "unilateral_faults": 1, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 5, "generated_at": "2026-07-02T16:51:45Z", "losses": 28, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-1ea0c8193f35ca72", "rated_matches": 70, "raw_elo_rating": 1566.120201385086, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 62.55588820955038, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 37 }, { "admitted_plugin_count": 1, "attempted_matches": 76, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 38, "draws": 12, "generated_at": "2026-07-02T16:51:45Z", "losses": 30, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-69e964db7b91b1bb", "rated_matches": 76, "raw_elo_rating": 1538.5869987807794, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 59.23484500914308, "uncertainty": 13.230288229818967, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 1, "generated_at": "2026-07-02T16:51:45Z", "losses": 44, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-f225b6990e542d31", "rated_matches": 66, "raw_elo_rating": 1349.1726611844706, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 34.28148635006266, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 21 }, { "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": 44, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 4, "generated_at": "2026-07-02T16:51:45Z", "losses": 23, "model": "qwen/qwen3.7-max", "point_rating_method": "sequential_elo", "public_id": "E-8283efe6f68a787e", "rated_matches": 44, "raw_elo_rating": 1497.2982048390093, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 52.06950812237848, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 6, "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": 38, "raw_elo_rating": 1586.5622739195126, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 63.05600683389494, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 1, "generated_at": "2026-07-02T16:51:45Z", "losses": 43, "model": "stepfun/step-3.7-flash", "point_rating_method": "sequential_elo", "public_id": "E-6526762dce98da7c", "rated_matches": 66, "raw_elo_rating": 1358.4283980930004, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 35.48005541077814, "uncertainty": 17.33472217815261, "unilateral_faults": 1, "wins": 22 }, { "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": 39, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-0825a2443d50c563", "rated_matches": 68, "raw_elo_rating": 1343.2749498156031, "reasoning": "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": 33.61015012782225, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "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": 62, "raw_elo_rating": 1738.0636778057162, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 84.44301843000522, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 43 }, { "admitted_plugin_count": 1, "attempted_matches": 94, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 47, "draws": 9, "generated_at": "2026-07-24T14:00:00Z", "losses": 46, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-3baaff3521870bef", "rated_matches": 94, "raw_elo_rating": 1479.471903029175, "reasoning": "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": 52.16831822774484, "uncertainty": 7.54891760425771, "unilateral_faults": 0, "wins": 39 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 5, "generated_at": "2026-07-17T22:36:00Z", "losses": 35, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-8cb8510a257ade6a", "rated_matches": 72, "raw_elo_rating": 1520.051662375247, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 56.67504975033097, "uncertainty": 14.770573598065289, "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": 23, "model": "x-ai/grok-build-0.1", "point_rating_method": "sequential_elo", "public_id": "E-133675db0ee21fd5", "rated_matches": 38, "raw_elo_rating": 1373.8468233302583, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 35.51047908909959, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 4, "generated_at": "2026-07-02T16:51:45Z", "losses": 27, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-7b4c450b6850f156", "rated_matches": 38, "raw_elo_rating": 1291.006145934247, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 24.783048752994254, "uncertainty": 36.31407690254356, "unilateral_faults": 1, "wins": 7 }, { "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": "xiaomi/mimo-v2.5-pro", "point_rating_method": "sequential_elo", "public_id": "E-530f82d65699c577", "rated_matches": 38, "raw_elo_rating": 1577.5838949262898, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 61.893354158802424, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 7, "generated_at": "2026-07-02T06:10:40Z", "losses": 16, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-72584b5bdb2d01e3", "rated_matches": 46, "raw_elo_rating": 1684.8010698527362, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 76.51621390529917, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 23, "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": 46, "raw_elo_rating": 1621.1969574486914, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 68.27981716939979, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 27 } ], "GB2-07": [ { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 16, "model": "claude-fable-5", "point_rating_method": "sequential_elo", "public_id": "E-bc12a8303ec2def7", "rated_matches": 62, "raw_elo_rating": 1732.9026765072072, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 76.98200491889094, "uncertainty": 19.244078834871203, "unilateral_faults": 2, "wins": 46 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 21, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-0bf7b9ed307db853", "rated_matches": 64, "raw_elo_rating": 1663.2800319802798, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 68.53036352739291, "uncertainty": 18.26736729460423, "unilateral_faults": 1, "wins": 43 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 0, "generated_at": "2026-07-25T10:50:00Z", "losses": 4, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-54bca3ce32fa85ae", "rated_matches": 58, "raw_elo_rating": 1922.0717818058629, "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": 21.344455490411935, "unilateral_faults": 0, "wins": 54 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 0, "generated_at": "2026-07-25T10:50:00Z", "losses": 21, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-de5e72176c4f0dc9", "rated_matches": 60, "raw_elo_rating": 1775.6096922481513, "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": 82.12453538591619, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 39 }, { "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": 33, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-9e40526fba9fa8b9", "rated_matches": 78, "raw_elo_rating": 1495.9673153967922, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 48.555402065964, "uncertainty": 12.5043950463012, "unilateral_faults": 0, "wins": 45 }, { "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": 23, "model": "cohere/north-mini-code", "point_rating_method": "sequential_elo", "public_id": "E-1c961fde1b53f0eb", "rated_matches": 48, "raw_elo_rating": 1483.908738760916, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 45.58462439953901, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 0, "generated_at": "2026-07-01T00:15:48Z", "losses": 37, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-8f2f6c973751f183", "rated_matches": 48, "raw_elo_rating": 1368.9649637776126, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 31.4729804448763, "uncertainty": 27.67857142857143, "unilateral_faults": 1, "wins": 11 }, { "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": 29, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-edc2d085c4253ed3", "rated_matches": 48, "raw_elo_rating": 1475.8883667633174, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 44.59996355965882, "uncertainty": 27.67857142857143, "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": 52, "model": "google/gemini-3.1-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-1b3c52da51dfbdd4", "rated_matches": 62, "raw_elo_rating": 1146.8224295367877, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 5.028949824704899, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugin_count": 1, "attempted_matches": 88, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 42, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 41, "model": "google/gemini-3.5-flash", "point_rating_method": "sequential_elo", "public_id": "E-5447c508e2b0ab6c", "rated_matches": 84, "raw_elo_rating": 1491.1934866603465, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 48.1678904051992, "uncertainty": 10.482614454664043, "unilateral_faults": 2, "wins": 43 }, { "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": 39, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-2950a4947ff48aa6", "rated_matches": 68, "raw_elo_rating": 1296.472599345917, "reasoning": "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": 23.676614784886056, "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": 45, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-42943e41c64d22d2", "rated_matches": 70, "raw_elo_rating": 1215.7211439442203, "reasoning": "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": 13.846622010261695, "uncertainty": 15.58908290969266, "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": "2026-07-24T13:40:00Z", "losses": 33, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-5f208f03ea700603", "rated_matches": 72, "raw_elo_rating": 1497.5221396698407, "reasoning": "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": 48.52371285673669, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 39 }, { "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": 29, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-65c6c8e09fe2c210", "rated_matches": 74, "raw_elo_rating": 1437.6843580559512, "reasoning": "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": 41.25458336053536, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 45 }, { "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": "google/gemma-4-31b-it", "point_rating_method": "sequential_elo", "public_id": "E-f417d302c870dfa6", "rated_matches": 38, "raw_elo_rating": 1465.5446251098992, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 42.481918086546386, "uncertainty": 36.31407690254356, "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": "2026-07-02T16:51:45Z", "losses": 27, "model": "gpt-5", "point_rating_method": "sequential_elo", "public_id": "E-4d8b4cfcff519db6", "rated_matches": 68, "raw_elo_rating": 1569.3972507863089, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 57.18356640655226, "uncertainty": 16.4429265428846, "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": 24, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-22466ae84d7027e5", "rated_matches": 60, "raw_elo_rating": 1590.5823542815288, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 59.4087344158915, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 36 }, { "admitted_plugin_count": 1, "attempted_matches": 71, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 36, "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": 71, "raw_elo_rating": 1456.3300135701293, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 43.42678008215959, "uncertainty": 15.175565098878964, "unilateral_faults": 0, "wins": 31 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 37, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 43, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-b96fbceba82aa188", "rated_matches": 74, "raw_elo_rating": 1467.8534887025785, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 44.958446663865594, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 31 }, { "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": 34, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-f4d7ac8a0f5d2974", "rated_matches": 68, "raw_elo_rating": 1497.7232695380007, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 48.38415378645852, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 34 }, { "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": 53, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-acb1779a65c941b4", "rated_matches": 60, "raw_elo_rating": 1156.9962119959694, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 6.177376175757823, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 7 }, { "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": 55, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-bea6d7d9558897f9", "rated_matches": 64, "raw_elo_rating": 1157.3137747604587, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 6.412900654814086, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 76, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 0, "generated_at": "2026-07-01T00:15:48Z", "losses": 57, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-c4ad375a0a870e69", "rated_matches": 72, "raw_elo_rating": 1263.1233843711118, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 19.74658439830341, "uncertainty": 14.770573598065289, "unilateral_faults": 2, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 65, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 0, "generated_at": "2026-07-09T17:30:50Z", "losses": 31, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-ce04fd14b6f43868", "rated_matches": 65, "raw_elo_rating": 1588.4151682571646, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 59.38552715383896, "uncertainty": 17.79574548966636, "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": 29, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-640b3078b8bce40e", "rated_matches": 66, "raw_elo_rating": 1671.308501921656, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 69.6076192029346, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 37 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 40, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-45c76cf9faaba10a", "rated_matches": 72, "raw_elo_rating": 1495.1492778934935, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 48.232396684579456, "uncertainty": 14.770573598065289, "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": 25, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-cc78d54d18d4c3f1", "rated_matches": 60, "raw_elo_rating": 1620.732869774357, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 63.110312337324274, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 35 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 30, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-aca193dd2a8774fb", "rated_matches": 62, "raw_elo_rating": 1415.0011967486844, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 37.95324937589321, "uncertainty": 19.244078834871203, "unilateral_faults": 1, "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": "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": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 22, "model": "minimax/minimax-m3", "point_rating_method": "sequential_elo", "public_id": "E-4547f4cedca403f9", "rated_matches": 40, "raw_elo_rating": 1491.106649402965, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 45.81435930794232, "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, "generated_at": "2026-07-02T16:51:45Z", "losses": 21, "model": "moonshotai/kimi-k2.7-code", "point_rating_method": "sequential_elo", "public_id": "E-d35e87ebfc251f60", "rated_matches": 40, "raw_elo_rating": 1513.8720710304185, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 48.609269467549154, "uncertainty": 34.33688094430304, "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": "2026-07-21T14:43:57Z", "losses": 14, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-3d2d4c8b0819b60b", "rated_matches": 38, "raw_elo_rating": 1630.5068984993, "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": 62.73433165449384, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 24 }, { "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": 17, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-4cc8f48bf8bccc77", "rated_matches": 38, "raw_elo_rating": 1512.5751169614134, "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": 48.25585022091068, "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": "nex-agi/nex-n2-pro", "point_rating_method": "sequential_elo", "public_id": "E-d1f432cda667f27f", "rated_matches": 38, "raw_elo_rating": 1459.0637934091908, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 41.68626656471518, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 20 }, { "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": 51, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-459f395cc0af6d2e", "rated_matches": 68, "raw_elo_rating": 1139.144947953933, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 4.361503540371355, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 17 }, { "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": "o3", "point_rating_method": "sequential_elo", "public_id": "E-f1e3e54a3d40556f", "rated_matches": 66, "raw_elo_rating": 1570.054537336516, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 57.17667287781976, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 36 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 8, "model": "qwen/qwen3.7-max", "point_rating_method": "sequential_elo", "public_id": "E-59c7745eb1e91d63", "rated_matches": 38, "raw_elo_rating": 1713.3149966509693, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 72.90067948715259, "uncertainty": 36.31407690254356, "unilateral_faults": 2, "wins": 30 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 25, "model": "qwen/qwen3.7-plus", "point_rating_method": "sequential_elo", "public_id": "E-9d091700cb41ece2", "rated_matches": 52, "raw_elo_rating": 1469.7323982620346, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 44.11412141740787, "uncertainty": 24.930281974344517, "unilateral_faults": 6, "wins": 27 }, { "admitted_plugin_count": 1, "attempted_matches": 76, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 37, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 36, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-6df2b00898e4ba3c", "rated_matches": 74, "raw_elo_rating": 1636.4932548974812, "reasoning": "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": 65.66234591796368, "uncertainty": 13.985026918962571, "unilateral_faults": 1, "wins": 38 }, { "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": 34, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-8ad2285ad59d87bf", "rated_matches": 66, "raw_elo_rating": 1437.950468340537, "reasoning": "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": 40.9582601198932, "uncertainty": 17.33472217815261, "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": "2026-07-17T22:36:00Z", "losses": 27, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-3cfeaacb3dbbab07", "rated_matches": 64, "raw_elo_rating": 1571.2333001327654, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 57.22978890113659, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 37 }, { "admitted_plugin_count": 1, "attempted_matches": 76, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 0, "generated_at": "2026-07-17T22:36:00Z", "losses": 19, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-a1728c5ac67e11f3", "rated_matches": 72, "raw_elo_rating": 1707.131329228841, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 74.25742704101226, "uncertainty": 14.770573598065289, "unilateral_faults": 2, "wins": 53 }, { "admitted_plugin_count": 1, "attempted_matches": 86, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 43, "draws": 0, "generated_at": "2026-07-24T14:00:00Z", "losses": 35, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-e58f3df122cf1d29", "rated_matches": 86, "raw_elo_rating": 1660.323910306573, "reasoning": "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": 68.9936078713067, "uncertainty": 9.855626741889738, "unilateral_faults": 0, "wins": 51 }, { "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": "x-ai/grok-build-0.1", "point_rating_method": "sequential_elo", "public_id": "E-37ae0129627ee16f", "rated_matches": 38, "raw_elo_rating": 1294.048013413273, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 21.42728399222184, "uncertainty": 36.31407690254356, "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": "2026-07-01T00:15:48Z", "losses": 18, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-345a5b25cbac7f3b", "rated_matches": 40, "raw_elo_rating": 1490.6626325299442, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "first_pass", "score": 45.75984736918924, "uncertainty": 34.33688094430304, "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": 23, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-fa1a93f7e4d57000", "rated_matches": 38, "raw_elo_rating": 1388.9895983217118, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 33.08325964565655, "uncertainty": 36.31407690254356, "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": 24, "model": "xiaomi/mimo-v2.5-pro", "point_rating_method": "sequential_elo", "public_id": "E-3b160130ae038271", "rated_matches": 44, "raw_elo_rating": 1493.8041478238345, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 46.49432371294967, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 20, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-1d66fd51bbcbb370", "rated_matches": 50, "raw_elo_rating": 1671.561473858593, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 68.76167840226208, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 30 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 0, "generated_at": "2026-07-01T00:15:48Z", "losses": 21, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-e10fd023695e8b0a", "rated_matches": 48, "raw_elo_rating": 1666.6515999245044, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 68.01996021804254, "uncertainty": 27.67857142857143, "unilateral_faults": 1, "wins": 27 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 0, "generated_at": "2026-07-11T17:22:09Z", "losses": 20, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-ecd98326faa92bf4", "rated_matches": 48, "raw_elo_rating": 1505.709024570307, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 48.261044862471415, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 28 } ], "GB2-08": [ { "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": 12, "model": "claude-fable-5", "point_rating_method": "sequential_elo", "public_id": "E-9ccf296d44d35675", "rated_matches": 66, "raw_elo_rating": 1763.0396484548678, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 75.70490277082847, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 54 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 51, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 51, "generated_at": "2026-07-02T16:51:45Z", "losses": 9, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-c2dade0b97891d8a", "rated_matches": 64, "raw_elo_rating": 1443.6592609728195, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 28.724237840417203, "uncertainty": 18.26736729460423, "unilateral_faults": 1, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 0, "generated_at": "2026-07-25T10:50:00Z", "losses": 25, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-35a5bf9b35d5e1e8", "rated_matches": 62, "raw_elo_rating": 1698.3996599576496, "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": 65.99439182520574, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 37 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "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": 64, "raw_elo_rating": 1799.0191312173206, "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": 80.8756305155602, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 48 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 55, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 55, "generated_at": "2026-07-02T16:51:45Z", "losses": 10, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-130fb40b1c7a4d39", "rated_matches": 72, "raw_elo_rating": 1438.7650526278594, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 28.416522587653844, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 30, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 30, "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": 38, "raw_elo_rating": 1428.7402146058764, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "first_pass", "score": 24.415991454087557, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 46, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 46, "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": 50, "raw_elo_rating": 1436.914374262004, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 26.79553430937692, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 43, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 43, "generated_at": "2026-07-01T00:15:48Z", "losses": 6, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-d28ef17ff6995c62", "rated_matches": 50, "raw_elo_rating": 1432.6903506163824, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 26.175631123177716, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 78, "capped_draws": 26, "coverage_status": "rated", "distinct_rated_opponents": 39, "draws": 26, "generated_at": "2026-07-02T16:51:45Z", "losses": 28, "model": "google/gemini-3.1-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-cc6fb78c96472032", "rated_matches": 78, "raw_elo_rating": 1451.3559728598718, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 30.530384005557536, "uncertainty": 12.5043950463012, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 61, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 61, "generated_at": "2026-07-02T16:51:45Z", "losses": 7, "model": "google/gemini-3.5-flash", "point_rating_method": "sequential_elo", "public_id": "E-bd0bbefbbd252fc5", "rated_matches": 68, "raw_elo_rating": 1390.2358564476272, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 21.098201606423295, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 2, "attempted_matches": 78, "capped_draws": 63, "coverage_status": "rated", "distinct_rated_opponents": 39, "draws": 63, "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": 78, "raw_elo_rating": 1426.8485145766456, "reasoning": "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": 26.93375369522216, "uncertainty": 12.5043950463012, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 76, "capped_draws": 56, "coverage_status": "rated", "distinct_rated_opponents": 38, "draws": 56, "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": 76, "raw_elo_rating": 1375.119567341035, "reasoning": "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": 19.25696759542373, "uncertainty": 13.230288229818967, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 76, "capped_draws": 45, "coverage_status": "rated", "distinct_rated_opponents": 38, "draws": 45, "generated_at": "2026-07-24T13:40:00Z", "losses": 17, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-679bf377de51ec1e", "rated_matches": 76, "raw_elo_rating": 1435.125394659315, "reasoning": "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": 28.063216486496604, "uncertainty": 13.230288229818967, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 50, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 50, "generated_at": "2026-07-02T16:51:45Z", "losses": 12, "model": "gpt-5", "point_rating_method": "sequential_elo", "public_id": "E-04ae9f2b42e0e036", "rated_matches": 70, "raw_elo_rating": 1431.2215797734218, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 27.21337115953385, "uncertainty": 15.58908290969266, "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": 1454.5300578111446, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 30.42909603823807, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 80, "capped_draws": 63, "coverage_status": "rated", "distinct_rated_opponents": 40, "draws": 63, "generated_at": "2026-07-02T06:10:40Z", "losses": 13, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-8cc872d6760c46c1", "rated_matches": 80, "raw_elo_rating": 1421.5989567986887, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 26.24539407059221, "uncertainty": 11.805555555555554, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 44, "coverage_status": "rated", "distinct_rated_opponents": 37, "draws": 44, "generated_at": "2026-07-01T00:15:48Z", "losses": 21, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-acdb5996d6e8fdfc", "rated_matches": 74, "raw_elo_rating": 1435.4514740395327, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 28.022460491215703, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 82, "capped_draws": 29, "coverage_status": "rated", "distinct_rated_opponents": 40, "draws": 29, "generated_at": "2026-07-02T16:51:45Z", "losses": 30, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-b5171a15f0048555", "rated_matches": 80, "raw_elo_rating": 1456.7268808782455, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 31.40064742341202, "uncertainty": 11.805555555555554, "unilateral_faults": 1, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 49, "coverage_status": "rated", "distinct_rated_opponents": 37, "draws": 49, "generated_at": "2026-07-02T16:51:45Z", "losses": 20, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-26fa12e871bd8f3a", "rated_matches": 74, "raw_elo_rating": 1386.3428002249889, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 20.815440379193305, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "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": 68, "raw_elo_rating": 1705.185174352874, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 67.31908056932906, "uncertainty": 16.4429265428846, "unilateral_faults": 1, "wins": 45 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 56, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 56, "generated_at": "2026-07-02T06:10:40Z", "losses": 9, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-f26c38927e48d019", "rated_matches": 70, "raw_elo_rating": 1457.613496954871, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 31.08655817818232, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 26, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 26, "generated_at": "2026-07-02T16:51:45Z", "losses": 23, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-0d83a3c5c5e66085", "rated_matches": 68, "raw_elo_rating": 1551.251508726565, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 44.7283050929694, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 19 }, { "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": 6, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-e6198d88365e0492", "rated_matches": 66, "raw_elo_rating": 1457.9749247725908, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 30.93465286854758, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 5, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 5, "generated_at": "2026-07-10T05:30:29Z", "losses": 19, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-0385f0602a8e29e2", "rated_matches": 68, "raw_elo_rating": 1669.960028561512, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 62.149559292375265, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 44 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 35, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 35, "generated_at": "2026-07-10T05:30:29Z", "losses": 21, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-d004e78844cdd202", "rated_matches": 72, "raw_elo_rating": 1488.8573843513443, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 35.7679009521483, "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-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": 52, "capped_draws": 33, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 33, "generated_at": "2026-07-02T16:51:45Z", "losses": 12, "model": "minimax/minimax-m3", "point_rating_method": "sequential_elo", "public_id": "E-d169e7b29be70652", "rated_matches": 50, "raw_elo_rating": 1453.3282140108763, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 29.204372992994628, "uncertainty": 26.26400420140049, "unilateral_faults": 1, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 2, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "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": 38, "raw_elo_rating": 1631.2691306737945, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 54.13843879363069, "uncertainty": 36.31407690254356, "unilateral_faults": 1, "wins": 22 }, { "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": 1459.348117952713, "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": 29.355778680609212, "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": 1510.291605381818, "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": 37.221478218076655, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 8, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 8, "generated_at": "2026-07-02T16:51:45Z", "losses": 27, "model": "nex-agi/nex-n2-pro", "point_rating_method": "sequential_elo", "public_id": "E-92332f4d765b2297", "rated_matches": 38, "raw_elo_rating": 1262.3695174883117, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 0.0, "uncertainty": 36.31407690254356, "unilateral_faults": 1, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 51, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 51, "generated_at": "2026-07-02T16:51:45Z", "losses": 14, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-15cf0dede27b7e1b", "rated_matches": 68, "raw_elo_rating": 1428.1113342083331, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 26.65667649020289, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 39, "coverage_status": "rated", "distinct_rated_opponents": 37, "draws": 39, "generated_at": "2026-07-02T16:51:45Z", "losses": 23, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-35de956c8305ff90", "rated_matches": 74, "raw_elo_rating": 1452.1756101546605, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 30.47683720261099, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 54, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 54, "generated_at": "2026-07-02T16:51:45Z", "losses": 11, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-6e65dec497ff2de3", "rated_matches": 68, "raw_elo_rating": 1452.621919774562, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 30.253765749838735, "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": "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": 42, "capped_draws": 26, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 26, "generated_at": "2026-07-02T16:51:45Z", "losses": 13, "model": "qwen/qwen3.7-max", "point_rating_method": "sequential_elo", "public_id": "E-64624689e7cbd439", "rated_matches": 42, "raw_elo_rating": 1462.4364586987772, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 29.8090129494416, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 35, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 35, "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": 38, "raw_elo_rating": 1452.4213354706649, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "first_pass", "score": 27.89135132620079, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 76, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 38, "draws": 1, "generated_at": "2026-07-24T13:40:00Z", "losses": 40, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-9c877cdf80f00ddf", "rated_matches": 76, "raw_elo_rating": 1614.2416876518455, "reasoning": "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": 54.34970776628676, "uncertainty": 13.230288229818967, "unilateral_faults": 0, "wins": 35 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "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": 64, "raw_elo_rating": 1814.8608889517905, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 83.2005124098112, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 51 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "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": 64, "raw_elo_rating": 1864.1808157412113, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 90.43853528204684, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 57 }, { "admitted_plugin_count": 1, "attempted_matches": 78, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 39, "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": 78, "raw_elo_rating": 1830.6394574386093, "reasoning": "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": 86.19272406059183, "uncertainty": 12.5043950463012, "unilateral_faults": 0, "wins": 65 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 32, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 32, "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": 40, "raw_elo_rating": 1451.1013700464266, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 27.92977092345208, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 19, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 19, "generated_at": "2026-07-03T19:35:00Z", "losses": 15, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-650d06103e7fa176", "rated_matches": 42, "raw_elo_rating": 1457.764628429521, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 29.12339120291192, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 25, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 25, "generated_at": "2026-07-02T06:10:40Z", "losses": 12, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-b5eb7da0f5021b69", "rated_matches": 38, "raw_elo_rating": 1378.9010503799364, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 17.101767081032705, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 33, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 33, "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": 38, "raw_elo_rating": 1447.3428035769923, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 27.14604344768903, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 35, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 35, "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": 50, "raw_elo_rating": 1458.0937473201427, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 29.903746275484338, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 45, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 45, "generated_at": "2026-07-01T00:15:48Z", "losses": 4, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-18e15798a90b1d2f", "rated_matches": 50, "raw_elo_rating": 1454.5042225310565, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 29.376959959786937, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 43, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 43, "generated_at": "2026-07-11T17:22:09Z", "losses": 6, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-da1e9a6be31e371f", "rated_matches": 50, "raw_elo_rating": 1445.4605497899704, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 28.049741644389226, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 1 } ] }, "full_freedom/baseline": { "GB2-01": [ { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 42, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 42, "generated_at": "2026-07-02T16:51:45Z", "losses": 15, "model": "claude-opus-4-5", "point_rating_method": "sequential_elo", "public_id": "E-2e3eca63f7980fac", "rated_matches": 68, "raw_elo_rating": 1424.8775888544635, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 38.55641611027493, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 17, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 17, "generated_at": "2026-07-02T16:51:45Z", "losses": 20, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-757a6149e87d8b53", "rated_matches": 66, "raw_elo_rating": 1588.3444361805764, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 58.53653969822832, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 38, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 38, "generated_at": "2026-07-25T15:48:00Z", "losses": 5, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-6c30dc38efb07e9e", "rated_matches": 54, "raw_elo_rating": 1538.9118776023718, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 51.845852778522705, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 12, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 12, "generated_at": "2026-07-25T15:48:00Z", "losses": 9, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-865d68ab219fd7ee", "rated_matches": 56, "raw_elo_rating": 1808.7368464219276, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 85.08762089462937, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 35 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 12, "coverage_status": "rated", "distinct_rated_opponents": 25, "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": 50, "raw_elo_rating": 1596.8207633735929, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 58.70017091218334, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugin_count": 1, "attempted_matches": 86, "capped_draws": 49, "coverage_status": "rated", "distinct_rated_opponents": 43, "draws": 49, "generated_at": "2026-07-02T16:51:45Z", "losses": 20, "model": "cohere/north-mini-code", "point_rating_method": "sequential_elo", "public_id": "E-194759b182ce3244", "rated_matches": 86, "raw_elo_rating": 1466.6454782536298, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 44.33091655722825, "uncertainty": 9.855626741889738, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 18, "coverage_status": "rated", "distinct_rated_opponents": 37, "draws": 18, "generated_at": "2026-07-11T17:22:09Z", "losses": 53, "model": "cohere/north-mini-code", "point_rating_method": "sequential_elo", "public_id": "E-c309b463b29efb71", "rated_matches": 74, "raw_elo_rating": 1192.0965559736162, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 10.220871729896173, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 78, "capped_draws": 26, "coverage_status": "rated", "distinct_rated_opponents": 39, "draws": 26, "generated_at": "2026-07-02T06:10:40Z", "losses": 23, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-c4c43ee3f29394f8", "rated_matches": 78, "raw_elo_rating": 1489.855662825924, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 46.92013530031653, "uncertainty": 12.5043950463012, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugin_count": 1, "attempted_matches": 94, "capped_draws": 31, "coverage_status": "rated", "distinct_rated_opponents": 47, "draws": 31, "generated_at": "2026-07-02T16:51:45Z", "losses": 35, "model": "deepseek/deepseek-v4-pro", "point_rating_method": "sequential_elo", "public_id": "E-e121525dd1846069", "rated_matches": 94, "raw_elo_rating": 1489.9089544458643, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 47.413357618255546, "uncertainty": 7.54891760425771, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 23, "coverage_status": "rated", "distinct_rated_opponents": 24, "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": 48, "raw_elo_rating": 1331.1073977123126, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 25.94143215206774, "uncertainty": 27.67857142857143, "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": "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": 86, "capped_draws": 22, "coverage_status": "rated", "distinct_rated_opponents": 43, "draws": 22, "generated_at": "2026-07-02T16:51:45Z", "losses": 30, "model": "google/gemma-4-31b-it", "point_rating_method": "sequential_elo", "public_id": "E-caaa54d3c88e6570", "rated_matches": 86, "raw_elo_rating": 1462.3109351147084, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 43.79879432901968, "uncertainty": 9.855626741889738, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 1, "generated_at": "2026-07-02T16:51:45Z", "losses": 24, "model": "gpt-4.1", "point_rating_method": "sequential_elo", "public_id": "E-f50ec6b60d5b85da", "rated_matches": 48, "raw_elo_rating": 1595.6478858053922, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 58.41725935320175, "uncertainty": 27.67857142857143, "unilateral_faults": 1, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 2, "coverage_status": "rated", "distinct_rated_opponents": 35, "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": 70, "raw_elo_rating": 1868.06073882597, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 93.0468380621979, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 62 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 23, "coverage_status": "rated", "distinct_rated_opponents": 37, "draws": 23, "generated_at": "2026-07-01T00:15:48Z", "losses": 42, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-3834aa9e894c458b", "rated_matches": 74, "raw_elo_rating": 1278.8833780426032, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 20.875096560147092, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 84, "capped_draws": 19, "coverage_status": "rated", "distinct_rated_opponents": 42, "draws": 19, "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": 84, "raw_elo_rating": 1498.51458551136, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 48.18169218709777, "uncertainty": 10.482614454664043, "unilateral_faults": 0, "wins": 33 }, { "admitted_plugin_count": 1, "attempted_matches": 86, "capped_draws": 36, "coverage_status": "rated", "distinct_rated_opponents": 43, "draws": 36, "generated_at": "2026-07-02T16:51:45Z", "losses": 30, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-ea1cb793f92b3cff", "rated_matches": 86, "raw_elo_rating": 1427.498691380369, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 39.52513315847563, "uncertainty": 9.855626741889738, "unilateral_faults": 0, "wins": 20 }, { "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": 1396.023730456296, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 35.17846784359503, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 86, "capped_draws": 21, "coverage_status": "rated", "distinct_rated_opponents": 43, "draws": 21, "generated_at": "2026-07-09T17:30:50Z", "losses": 23, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-9eb27042bf28d67c", "rated_matches": 86, "raw_elo_rating": 1503.5208554870655, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 48.85785452291434, "uncertainty": 9.855626741889738, "unilateral_faults": 0, "wins": 42 }, { "admitted_plugin_count": 1, "attempted_matches": 84, "capped_draws": 30, "coverage_status": "rated", "distinct_rated_opponents": 42, "draws": 30, "generated_at": "2026-07-02T16:51:45Z", "losses": 30, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-a8887794a1195b75", "rated_matches": 84, "raw_elo_rating": 1525.463439796922, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 51.49001879281006, "uncertainty": 10.482614454664043, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 19, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 19, "generated_at": "2026-07-01T00:15:48Z", "losses": 43, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-f491ad1b583dbcac", "rated_matches": 68, "raw_elo_rating": 1197.38613783015, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 10.628845905590964, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 88, "capped_draws": 62, "coverage_status": "rated", "distinct_rated_opponents": 44, "draws": 62, "generated_at": "2026-07-02T16:51:45Z", "losses": 13, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-58178b9b32a94ca0", "rated_matches": 88, "raw_elo_rating": 1492.6269870813733, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 47.579978108397675, "uncertainty": 9.249894000318006, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 76, "capped_draws": 22, "coverage_status": "rated", "distinct_rated_opponents": 38, "draws": 22, "generated_at": "2026-07-10T05:30:29Z", "losses": 40, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-959ed218b1c5605b", "rated_matches": 75, "raw_elo_rating": 1345.106968705622, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 29.04234144066881, "uncertainty": 13.603933467640434, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 15, "coverage_status": "rated", "distinct_rated_opponents": 36, "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": 72, "raw_elo_rating": 1581.1565667843893, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 57.90596050525336, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 38 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 23, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 23, "generated_at": "2026-07-10T05:30:29Z", "losses": 26, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-40742129939a44b5", "rated_matches": 72, "raw_elo_rating": 1574.221591188411, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 57.05460096205999, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 24, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 24, "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": 64, "raw_elo_rating": 1410.8433809053547, "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": 36.654353050059186, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 15, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 15, "generated_at": "2026-07-24T13:40:00Z", "losses": 35, "model": "inclusionai/ling-3.0-flash", "point_rating_method": "sequential_elo", "public_id": "E-f9af396559c3a1cd", "rated_matches": 68, "raw_elo_rating": 1531.0496105208936, "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": 51.59042936884591, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 19, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 19, "generated_at": "2026-07-24T13:40:00Z", "losses": 26, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-9f5585b5fd96f2c3", "rated_matches": 66, "raw_elo_rating": 1499.6187640615335, "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": 47.64429550221449, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 26, "coverage_status": "rated", "distinct_rated_opponents": 37, "draws": 26, "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": 74, "raw_elo_rating": 1459.8055386885103, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 43.08567335444458, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 86, "capped_draws": 17, "coverage_status": "rated", "distinct_rated_opponents": 43, "draws": 17, "generated_at": "2026-07-02T16:51:45Z", "losses": 24, "model": "minimax/minimax-m3", "point_rating_method": "sequential_elo", "public_id": "E-444510032bc433fc", "rated_matches": 86, "raw_elo_rating": 1508.925857944881, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 49.52138972354479, "uncertainty": 9.855626741889738, "unilateral_faults": 0, "wins": 45 }, { "admitted_plugin_count": 1, "attempted_matches": 78, "capped_draws": 6, "coverage_status": "rated", "distinct_rated_opponents": 37, "draws": 6, "generated_at": "2026-07-02T16:51:45Z", "losses": 46, "model": "mistralai/mistral-medium-3-5", "point_rating_method": "sequential_elo", "public_id": "E-a0a38f5e77e983bc", "rated_matches": 73, "raw_elo_rating": 1392.3613831959185, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 34.7678319511097, "uncertainty": 14.373819371909642, "unilateral_faults": 4, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 7, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 7, "generated_at": "2026-07-21T14:20:15Z", "losses": 18, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-2292c77f8fb54ff1", "rated_matches": 48, "raw_elo_rating": 1568.536622820786, "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": 55.08899494180933, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 32, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 32, "generated_at": "2026-07-24T14:00:00Z", "losses": 5, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-fb8801908d28001f", "rated_matches": 48, "raw_elo_rating": 1584.356578397868, "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": 57.03110273541922, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 12, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 12, "generated_at": "2026-07-02T16:51:45Z", "losses": 19, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-0ce5e196701b51f3", "rated_matches": 48, "raw_elo_rating": 1548.045412820271, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 52.573429177506654, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 14, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 14, "generated_at": "2026-07-21T14:20:15Z", "losses": 20, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-fbf1a1af436a64a7", "rated_matches": 52, "raw_elo_rating": 1442.2859213259474, "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": 39.85997039408309, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 11, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 11, "generated_at": "2026-07-21T14:20:15Z", "losses": 24, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-55f6c0e3dc8a8065", "rated_matches": 48, "raw_elo_rating": 1363.6774166386915, "reasoning": "low", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "low", "repair_status": "first_pass", "score": 29.93983071183216, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 8, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 8, "generated_at": "2026-07-24T13:40:00Z", "losses": 34, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-8461eb1b16e40129", "rated_matches": 72, "raw_elo_rating": 1643.3068833166908, "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": 65.53572997739795, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 30 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 22, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 22, "generated_at": "2026-07-24T13:40:00Z", "losses": 27, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-c58ec61528547516", "rated_matches": 72, "raw_elo_rating": 1516.95537959453, "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": 50.02441966318795, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 76, "capped_draws": 21, "coverage_status": "rated", "distinct_rated_opponents": 38, "draws": 21, "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": 76, "raw_elo_rating": 1600.9936984199935, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 60.49250178392132, "uncertainty": 13.230288229818967, "unilateral_faults": 0, "wins": 37 }, { "admitted_plugin_count": 1, "attempted_matches": 78, "capped_draws": 19, "coverage_status": "rated", "distinct_rated_opponents": 39, "draws": 19, "generated_at": "2026-07-03T18:55:00Z", "losses": 42, "model": "qwen/qwen3.7-plus", "point_rating_method": "sequential_elo", "public_id": "E-5e09f0c994a59f3c", "rated_matches": 78, "raw_elo_rating": 1363.2762547082637, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 31.3808467215317, "uncertainty": 12.5043950463012, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 18, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 18, "generated_at": "2026-07-21T14:20:15Z", "losses": 28, "model": "stepfun/step-3.7-flash", "point_rating_method": "sequential_elo", "public_id": "E-09ecaa63c419b917", "rated_matches": 66, "raw_elo_rating": 1469.4983722127108, "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": 43.94662091196941, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 82, "capped_draws": 15, "coverage_status": "rated", "distinct_rated_opponents": 41, "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": 82, "raw_elo_rating": 1704.653117005999, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 73.42412117365035, "uncertainty": 11.132129994845172, "unilateral_faults": 0, "wins": 52 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 34, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 34, "generated_at": "2026-07-24T13:40:00Z", "losses": 26, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-9e638fc0ac98df4f", "rated_matches": 68, "raw_elo_rating": 1355.6784914065313, "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": 30.061315993869457, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 26, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 26, "generated_at": "2026-07-24T13:40:00Z", "losses": 30, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-bc7c657b08ebac66", "rated_matches": 66, "raw_elo_rating": 1291.467544227601, "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": 22.09099326194052, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 31, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 31, "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": 52, "raw_elo_rating": 1567.42228168583, "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": 55.2221058649925, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 17, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 17, "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": 48, "raw_elo_rating": 1661.320192160666, "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": 66.47939943794896, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 5, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 5, "generated_at": "2026-07-02T06:10:40Z", "losses": 29, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-2cdd8ae895784956", "rated_matches": 72, "raw_elo_rating": 1621.9825868393657, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 62.91789188170463, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 38 }, { "admitted_plugin_count": 1, "attempted_matches": 92, "capped_draws": 27, "coverage_status": "rated", "distinct_rated_opponents": 46, "draws": 27, "generated_at": "2026-07-02T16:51:45Z", "losses": 36, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-912a4a40bbdcbd45", "rated_matches": 92, "raw_elo_rating": 1462.887330767872, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 44.04221272141304, "uncertainty": 8.09758473652126, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugin_count": 1, "attempted_matches": 82, "capped_draws": 29, "coverage_status": "rated", "distinct_rated_opponents": 41, "draws": 29, "generated_at": "2026-07-01T00:15:48Z", "losses": 36, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-a168350bd057f924", "rated_matches": 82, "raw_elo_rating": 1416.5999005346357, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 38.061797053482614, "uncertainty": 11.132129994845172, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugin_count": 1, "attempted_matches": 94, "capped_draws": 29, "coverage_status": "rated", "distinct_rated_opponents": 47, "draws": 29, "generated_at": "2026-07-02T16:51:45Z", "losses": 40, "model": "xiaomi/mimo-v2.5-pro", "point_rating_method": "sequential_elo", "public_id": "E-9ce4191c7f1f3b3e", "rated_matches": 94, "raw_elo_rating": 1427.9370306043306, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 39.80548819718096, "uncertainty": 7.54891760425771, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 2, "coverage_status": "rated", "distinct_rated_opponents": 24, "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": 48, "raw_elo_rating": 1529.881929087823, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 50.34362245371306, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 13, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 13, "generated_at": "2026-07-11T14:00:45Z", "losses": 24, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-5c3b7f5666a38043", "rated_matches": 50, "raw_elo_rating": 1449.7679989041592, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 40.64750833949597, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 8, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 8, "generated_at": "2026-07-02T06:10:40Z", "losses": 15, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-6a7eb114b16dc845", "rated_matches": 48, "raw_elo_rating": 1567.659706257965, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 54.98134189040207, "uncertainty": 27.67857142857143, "unilateral_faults": 1, "wins": 25 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 3, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 3, "generated_at": "2026-07-02T16:51:45Z", "losses": 29, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-c8076ea61de8da45", "rated_matches": 50, "raw_elo_rating": 1347.818567378608, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 28.131873604926756, "uncertainty": 26.26400420140049, "unilateral_faults": 1, "wins": 18 } ], "GB2-02": [ { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 37, "draws": 65, "generated_at": "2026-07-02T16:51:45Z", "losses": 6, "model": "claude-opus-4-5", "point_rating_method": "sequential_elo", "public_id": "E-16462f3d1f3a7b19", "rated_matches": 74, "raw_elo_rating": 1500.9638007338544, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 33.709793544320256, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 56, "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": 66, "raw_elo_rating": 1478.1224509695917, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 27.69529937871457, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 19, "generated_at": "2026-07-25T10:50:00Z", "losses": 11, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-51ddad48e10b006f", "rated_matches": 56, "raw_elo_rating": 1657.241211986099, "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": 68.93834045321007, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 34, "generated_at": "2026-07-25T10:50:00Z", "losses": 4, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-772d1a710082ddb3", "rated_matches": 56, "raw_elo_rating": 1594.1213833662362, "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": 54.06305090304598, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 38, "generated_at": "2026-07-02T16:51:45Z", "losses": 3, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-e501d6808bd19ccc", "rated_matches": 42, "raw_elo_rating": 1483.9542755106384, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 26.21063543593213, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 69, "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": 72, "raw_elo_rating": 1497.792219534097, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 32.814252834535765, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 63, "generated_at": "2026-07-02T06:10:40Z", "losses": 1, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-bc9a8c3886a48505", "rated_matches": 64, "raw_elo_rating": 1488.2384450412742, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 29.903474702187335, "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": 55, "generated_at": "2026-07-02T16:51:45Z", "losses": 2, "model": "deepseek/deepseek-v4-pro", "point_rating_method": "sequential_elo", "public_id": "E-6c3b019c1b20a09b", "rated_matches": 58, "raw_elo_rating": 1492.0797054118812, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 30.228599126505976, "uncertainty": 21.344455490411935, "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": "2026-07-02T16:51:45Z", "losses": 3, "model": "google/gemini-3.1-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-20b3484be872df52", "rated_matches": 42, "raw_elo_rating": 1494.771862796145, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 28.759988731473964, "uncertainty": 32.49928516630233, "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": 48, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 35, "generated_at": "2026-07-02T16:51:45Z", "losses": 10, "model": "gpt-4.1", "point_rating_method": "sequential_elo", "public_id": "E-e4707b8e4c581ede", "rated_matches": 48, "raw_elo_rating": 1464.639645646619, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 22.567673997988543, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 68, "generated_at": "2026-07-02T16:51:45Z", "losses": 1, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-98ddce22d3eb5886", "rated_matches": 70, "raw_elo_rating": 1486.4639803433008, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 29.99023869568103, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 63, "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": 64, "raw_elo_rating": 1483.909003509502, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 28.883166222526008, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 57, "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": 60, "raw_elo_rating": 1498.8962495460976, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 32.03790222837709, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 65, "generated_at": "2026-07-01T00:15:48Z", "losses": 5, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-dd45dfa7984ab9fa", "rated_matches": 72, "raw_elo_rating": 1498.893600981965, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 33.073812600467356, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 53, "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": 56, "raw_elo_rating": 1495.9131766564717, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 30.918572488692377, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 60, "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": 62, "raw_elo_rating": 1474.580133477346, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 26.500511836933963, "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": 62, "generated_at": "2026-07-02T06:10:40Z", "losses": 4, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-786cc9019eb3ee2b", "rated_matches": 68, "raw_elo_rating": 1498.4882992808675, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 32.66300084521741, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 53, "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": 60, "raw_elo_rating": 1442.6014891166542, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 18.771059148236457, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 70, "generated_at": "2026-07-02T16:51:45Z", "losses": 2, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-51e935956fa76015", "rated_matches": 72, "raw_elo_rating": 1500.601598880668, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 33.47633212325143, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 66, "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": 66, "raw_elo_rating": 1485.0271335560255, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 29.322508371054298, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 51, "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": 64, "raw_elo_rating": 1502.7262761164538, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 33.31778502129591, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 76, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 37, "draws": 70, "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": 76, "raw_elo_rating": 1477.289710549957, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 28.272874772560343, "uncertainty": 13.230288229818967, "unilateral_faults": 0, "wins": 3 }, { "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": 2, "model": "inclusionai/ling-3.0-flash", "point_rating_method": "sequential_elo", "public_id": "E-fc495094a55d2f94", "rated_matches": 66, "raw_elo_rating": 1471.8518908493445, "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": 26.217532415940592, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 67, "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": 68, "raw_elo_rating": 1479.8498057623008, "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": 28.27051445972222, "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": 65, "generated_at": "2026-07-02T16:51:45Z", "losses": 1, "model": "minimax/minimax-m3", "point_rating_method": "sequential_elo", "public_id": "E-1e46941293882535", "rated_matches": 66, "raw_elo_rating": 1471.6428922171287, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 26.16827823959424, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 39, "generated_at": "2026-07-24T14:00:00Z", "losses": 0, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-d3d3da42e99695b1", "rated_matches": 40, "raw_elo_rating": 1506.1574106540736, "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": 31.096742630840403, "uncertainty": 34.33688094430304, "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": 1522.0566255972044, "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": 35.190119418577666, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 58, "generated_at": "2026-07-11T17:22:09Z", "losses": 7, "model": "nex-agi/nex-n2-pro", "point_rating_method": "sequential_elo", "public_id": "E-811f47e902ce0d21", "rated_matches": 68, "raw_elo_rating": 1476.372168299665, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 27.45094847961234, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 38, "generated_at": "2026-07-21T14:20:15Z", "losses": 1, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-e48b0ea99dfc517c", "rated_matches": 40, "raw_elo_rating": 1474.570314492858, "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": 23.652691977966807, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 43, "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": 44, "raw_elo_rating": 1488.805306711772, "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": 27.67695362975448, "uncertainty": 30.785599249992988, "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": 2, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-d8c7a78cc7f666dc", "rated_matches": 68, "raw_elo_rating": 1479.0793242660857, "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": 28.088937044196097, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 54, "generated_at": "2026-07-02T16:51:45Z", "losses": 6, "model": "qwen/qwen3.7-max", "point_rating_method": "sequential_elo", "public_id": "E-5f64c2ae9860ba38", "rated_matches": 66, "raw_elo_rating": 1500.6469304986908, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 33.0035862085153, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 60, "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": 60, "raw_elo_rating": 1493.0380666605308, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 30.657319160171507, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 66, "generated_at": "2026-07-02T16:51:45Z", "losses": 6, "model": "tencent/hy3-preview", "point_rating_method": "sequential_elo", "public_id": "E-d910e47dd13c2c71", "rated_matches": 72, "raw_elo_rating": 1466.230042358881, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 25.376074775744662, "uncertainty": 14.770573598065289, "unilateral_faults": 1, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 68, "generated_at": "2026-07-24T13:40:00Z", "losses": 1, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-66a4f0abd099d8f1", "rated_matches": 70, "raw_elo_rating": 1497.9528618673835, "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": 32.69779419789101, "uncertainty": 15.58908290969266, "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": 1479.099098563037, "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": 24.719979006893933, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 44, "generated_at": "2026-07-24T14:00:00Z", "losses": 3, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-1b0da3150a77b47b", "rated_matches": 50, "raw_elo_rating": 1482.683841994756, "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": 27.0867978500241, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 61, "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": 64, "raw_elo_rating": 1467.6684243184336, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 25.05579021071138, "uncertainty": 18.26736729460423, "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": 1476.1302139151496, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 27.04995865374969, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 39, "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": 42, "raw_elo_rating": 1467.0613447958626, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 22.22952139890711, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 44, "generated_at": "2026-07-11T14:00:45Z", "losses": 2, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-925b589068dc7268", "rated_matches": 46, "raw_elo_rating": 1481.2115840910012, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 26.18959978556957, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 35, "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": 42, "raw_elo_rating": 1486.6279450324444, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 26.840732335241476, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 3 } ], "GB2-03": [ { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 9, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 40, "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": 58, "raw_elo_rating": 1548.522194338608, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 54.88884061800323, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 4, "generated_at": "2026-07-25T15:48:00Z", "losses": 16, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-49aaba66f6b19080", "rated_matches": 44, "raw_elo_rating": 1586.523100982404, "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": 59.97948109091506, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 11, "generated_at": "2026-07-25T15:48:00Z", "losses": 16, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-ecf847457e616425", "rated_matches": 44, "raw_elo_rating": 1467.6921639227314, "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": 40.111977681850504, "uncertainty": 30.785599249992988, "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": 1487.6967601875272, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 42.71712204291151, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 3, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 26, "generated_at": "2026-07-02T06:10:40Z", "losses": 19, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-4e52c100ed276347", "rated_matches": 56, "raw_elo_rating": 1446.536779333255, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 37.68633239449348, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 78, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 39, "draws": 36, "generated_at": "2026-07-02T16:51:45Z", "losses": 22, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-ae9d59ec3a8a1d63", "rated_matches": 78, "raw_elo_rating": 1482.1225653402416, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 44.96978300688633, "uncertainty": 12.5043950463012, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 18, "generated_at": "2026-07-02T16:51:45Z", "losses": 31, "model": "deepseek/deepseek-v4-pro", "point_rating_method": "sequential_elo", "public_id": "E-f82a334a0fd1fb8e", "rated_matches": 58, "raw_elo_rating": 1341.7414384682531, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 20.31688929088188, "uncertainty": 21.344455490411935, "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": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 10, "generated_at": "2026-07-02T16:51:45Z", "losses": 11, "model": "gpt-4.1", "point_rating_method": "sequential_elo", "public_id": "E-c7da9914f86ee846", "rated_matches": 32, "raw_elo_rating": 1525.6726149306114, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 48.13346165011627, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 2, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 32, "generated_at": "2026-07-02T16:51:45Z", "losses": 10, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-ebd456dc6b320c61", "rated_matches": 56, "raw_elo_rating": 1552.4602360612246, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 55.3958168916667, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 70, "generated_at": "2026-07-02T16:51:45Z", "losses": 2, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-35117a2e624d7970", "rated_matches": 72, "raw_elo_rating": 1494.1421634084834, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 46.676247354738535, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 23, "generated_at": "2026-07-01T00:15:48Z", "losses": 14, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-a51cd55f211305c2", "rated_matches": 56, "raw_elo_rating": 1531.6573984374318, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 51.91776262704892, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 23, "generated_at": "2026-07-02T06:10:40Z", "losses": 10, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-dfa5098ec9c3cf47", "rated_matches": 58, "raw_elo_rating": 1540.239622647847, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 53.504066371719354, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 9, "generated_at": "2026-07-01T00:15:48Z", "losses": 28, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-0ecb5b73c09f13b2", "rated_matches": 54, "raw_elo_rating": 1412.860488094673, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 31.896331503262783, "uncertainty": 23.66998624632421, "unilateral_faults": 1, "wins": 17 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 37, "draws": 41, "generated_at": "2026-07-02T06:10:40Z", "losses": 23, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-e4eac938bdd5d40e", "rated_matches": 74, "raw_elo_rating": 1421.5124258286896, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 34.6382536024244, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 25, "generated_at": "2026-07-09T17:30:50Z", "losses": 22, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-f2a7b43bf689e68e", "rated_matches": 68, "raw_elo_rating": 1510.1867737968605, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 49.13508489782365, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 2, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 22, "generated_at": "2026-07-02T16:51:45Z", "losses": 10, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-446036823932df16", "rated_matches": 50, "raw_elo_rating": 1532.4592771605007, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 51.54525524994926, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 23, "generated_at": "2026-07-10T05:30:29Z", "losses": 18, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-d192bb239087b778", "rated_matches": 56, "raw_elo_rating": 1470.4123206900906, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 41.67811610871256, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 10, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 34, "generated_at": "2026-07-10T05:30:29Z", "losses": 20, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-527999604d620080", "rated_matches": 72, "raw_elo_rating": 1495.3996940005095, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 46.88649557748494, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 10, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 28, "generated_at": "2026-07-10T10:07:13Z", "losses": 21, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-c2f0f8f062659e83", "rated_matches": 64, "raw_elo_rating": 1509.542473344345, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 48.7833388899691, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 18, "generated_at": "2026-07-24T13:40:00Z", "losses": 23, "model": "inclusionai/ling-3.0-flash", "point_rating_method": "sequential_elo", "public_id": "E-2524de3c7d4a81b7", "rated_matches": 52, "raw_elo_rating": 1390.930627546129, "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": 28.061280343833168, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 20, "generated_at": "2026-07-24T13:40:00Z", "losses": 23, "model": "inclusionai/ling-3.0-flash", "point_rating_method": "sequential_elo", "public_id": "E-641ddca04b054d56", "rated_matches": 50, "raw_elo_rating": 1384.2919804431226, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 26.77296660624224, "uncertainty": 26.26400420140049, "unilateral_faults": 1, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 4, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 26, "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": 52, "raw_elo_rating": 1421.9129068998388, "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": 33.24124909533193, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 5, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 25, "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": 54, "raw_elo_rating": 1449.8161521192164, "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": 38.074998432592515, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 24, "generated_at": "2026-07-02T16:51:45Z", "losses": 14, "model": "minimax/minimax-m3", "point_rating_method": "sequential_elo", "public_id": "E-44cc758f104a74ab", "rated_matches": 66, "raw_elo_rating": 1531.065473656246, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 52.50654226647922, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 10, "generated_at": "2026-07-24T14:00:00Z", "losses": 3, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-09859be1b47131a0", "rated_matches": 38, "raw_elo_rating": 1673.7136397706963, "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": 73.81753310342788, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 2, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 14, "generated_at": "2026-07-21T14:20:15Z", "losses": 5, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-a12d08354d94b221", "rated_matches": 38, "raw_elo_rating": 1621.890061963377, "reasoning": "low", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "low", "repair_status": "first_pass", "score": 65.15307976969873, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 4, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 37, "generated_at": "2026-07-02T16:51:45Z", "losses": 15, "model": "nex-agi/nex-n2-pro", "point_rating_method": "sequential_elo", "public_id": "E-a05d4cef5f788f16", "rated_matches": 58, "raw_elo_rating": 1418.3320938153308, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 33.122183466475484, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 4, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 21, "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": 34, "raw_elo_rating": 1422.2873610539257, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 31.1858555184372, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 23, "generated_at": "2026-07-21T14:20:15Z", "losses": 10, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-08888c30d05ca8cb", "rated_matches": 38, "raw_elo_rating": 1451.4587426506623, "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": 36.658439390347205, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 29, "generated_at": "2026-07-21T14:20:15Z", "losses": 12, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-c90a449ff5e7b79a", "rated_matches": 46, "raw_elo_rating": 1447.733296866472, "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": 36.98944800191301, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 16, "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": 52, "raw_elo_rating": 1445.7977395279188, "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": 37.23458622962569, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 7, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 31, "generated_at": "2026-07-24T13:40:00Z", "losses": 14, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-91efdb0c216f8504", "rated_matches": 56, "raw_elo_rating": 1502.7276421965807, "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": 47.08095796186405, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 4, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 48, "generated_at": "2026-07-02T16:51:45Z", "losses": 8, "model": "qwen/qwen3.7-max", "point_rating_method": "sequential_elo", "public_id": "E-3325ebad2ef000c1", "rated_matches": 60, "raw_elo_rating": 1434.9623243276997, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 36.04653434402484, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 7, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 24, "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": 46, "raw_elo_rating": 1538.934447109512, "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": 52.23749037369294, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugin_count": 1, "attempted_matches": 80, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 40, "draws": 26, "generated_at": "2026-07-02T16:51:45Z", "losses": 26, "model": "tencent/hy3-preview", "point_rating_method": "sequential_elo", "public_id": "E-2346cd049910cc0a", "rated_matches": 80, "raw_elo_rating": 1427.499195255498, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 35.93070058290421, "uncertainty": 11.805555555555554, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 5, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 28, "generated_at": "2026-07-24T13:40:00Z", "losses": 15, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-78048b7c08122f1c", "rated_matches": 52, "raw_elo_rating": 1435.6332279487651, "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": 35.53516793463317, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 8, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 21, "generated_at": "2026-07-24T13:40:00Z", "losses": 12, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-adf1f0bb193bd39b", "rated_matches": 52, "raw_elo_rating": 1611.5217807019071, "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": 64.9422104767928, "uncertainty": 24.930281974344517, "unilateral_faults": 1, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 10, "generated_at": "2026-07-24T14:00:00Z", "losses": 26, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-02f7e54245bd5c85", "rated_matches": 38, "raw_elo_rating": 1312.7162394535528, "reasoning": "low", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "low", "repair_status": "repaired", "score": 13.461894589336923, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 34, "generated_at": "2026-07-21T14:20:15Z", "losses": 7, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-3c1904811d11cd84", "rated_matches": 52, "raw_elo_rating": 1522.4166372444274, "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": 50.044602284763734, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 2, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 32, "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": 54, "raw_elo_rating": 1537.4103736250274, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 52.71999356132024, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 4, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 35, "generated_at": "2026-07-02T16:51:45Z", "losses": 9, "model": "xiaomi/mimo-v2.5-pro", "point_rating_method": "sequential_elo", "public_id": "E-b0948c64dddf57ad", "rated_matches": 54, "raw_elo_rating": 1447.7436441756136, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 37.72849305567903, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 1, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 23, "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": 32, "raw_elo_rating": 1503.721201303524, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 44.46337542626583, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 4, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 17, "generated_at": "2026-07-11T14:00:45Z", "losses": 9, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-583be34ca1fb2631", "rated_matches": 34, "raw_elo_rating": 1493.010827082733, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 43.010206459325595, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 5, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 10, "generated_at": "2026-07-02T06:10:40Z", "losses": 15, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-f1af7b938699d971", "rated_matches": 32, "raw_elo_rating": 1365.8175451624577, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 21.40707858725937, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 7 } ], "GB2-04": [ { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 40, "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": 60, "raw_elo_rating": 1533.6903460135152, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 42.34172688645558, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 42, "generated_at": "2026-07-02T16:51:45Z", "losses": 9, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-688a139ef8557587", "rated_matches": 56, "raw_elo_rating": 1478.6538182736597, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 31.21093844748892, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 27, "generated_at": "2026-07-25T15:48:00Z", "losses": 15, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-72e9307528761b35", "rated_matches": 60, "raw_elo_rating": 1518.6489524149345, "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": 39.39430573777955, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 15, "generated_at": "2026-07-25T15:48:00Z", "losses": 17, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-9e7782014171d35f", "rated_matches": 56, "raw_elo_rating": 1607.7985303782043, "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": 56.51736056867651, "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": 35, "generated_at": "2026-07-02T16:51:45Z", "losses": 2, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-be938b7d5557f479", "rated_matches": 42, "raw_elo_rating": 1529.625293105078, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 39.62781716181058, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 27, "generated_at": "2026-07-02T16:51:45Z", "losses": 22, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-81bc9a578754f220", "rated_matches": 50, "raw_elo_rating": 1340.394586255456, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 3.524766962285257, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 78, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 39, "draws": 69, "generated_at": "2026-07-01T00:15:48Z", "losses": 2, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-a43d18fadfcc5a89", "rated_matches": 78, "raw_elo_rating": 1518.5161209085754, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 40.585393362011814, "uncertainty": 12.5043950463012, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 37, "draws": 72, "generated_at": "2026-07-02T06:10:40Z", "losses": 1, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-cb48b9466ec54175", "rated_matches": 74, "raw_elo_rating": 1504.575065127242, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 37.621479220114104, "uncertainty": 13.985026918962571, "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-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": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 45, "generated_at": "2026-07-02T16:51:45Z", "losses": 5, "model": "google/gemma-4-31b-it", "point_rating_method": "sequential_elo", "public_id": "E-ec0cf4b37c805eee", "rated_matches": 54, "raw_elo_rating": 1488.6170542412904, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 32.97619808478928, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 4 }, { "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": 9, "model": "gpt-4.1", "point_rating_method": "sequential_elo", "public_id": "E-ecb06954153be8d5", "rated_matches": 38, "raw_elo_rating": 1461.6738793317916, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 25.714447304211713, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 53, "generated_at": "2026-07-02T16:51:45Z", "losses": 8, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-8d62bf1b340a70dc", "rated_matches": 72, "raw_elo_rating": 1493.812998783348, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 35.38946453067582, "uncertainty": 14.770573598065289, "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": 1490.7178079038288, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 34.65463738122138, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 37, "draws": 60, "generated_at": "2026-07-02T06:10:40Z", "losses": 8, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-c9bf6a0be0c43fd1", "rated_matches": 74, "raw_elo_rating": 1461.710286970976, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 29.221954745001227, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 49, "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": 62, "raw_elo_rating": 1472.4242445605073, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 30.49697174316458, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 47, "generated_at": "2026-07-01T00:15:48Z", "losses": 13, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-48f60c9100c65daa", "rated_matches": 66, "raw_elo_rating": 1473.6556896663606, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 31.037595179911463, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 55, "generated_at": "2026-07-02T06:10:40Z", "losses": 9, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-c8f4bd9fcf2e481e", "rated_matches": 70, "raw_elo_rating": 1498.1287649236724, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 36.106844007492846, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 52, "generated_at": "2026-07-02T16:51:45Z", "losses": 12, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-ba1aa87056709e9a", "rated_matches": 70, "raw_elo_rating": 1498.9622499050838, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 36.27016871841243, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 76, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 38, "draws": 54, "generated_at": "2026-07-10T05:30:29Z", "losses": 15, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-71a01107bf3f9fc1", "rated_matches": 76, "raw_elo_rating": 1489.5809864033852, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 34.80164485846782, "uncertainty": 13.230288229818967, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 57, "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": 66, "raw_elo_rating": 1480.824684786784, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 32.44238840563259, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 80, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 40, "draws": 75, "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": 80, "raw_elo_rating": 1517.755122369414, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 40.54582497036699, "uncertainty": 11.805555555555554, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 59, "generated_at": "2026-07-24T13:40:00Z", "losses": 5, "model": "inclusionai/ling-3.0-flash", "point_rating_method": "sequential_elo", "public_id": "E-f38039bb8cc277a1", "rated_matches": 66, "raw_elo_rating": 1476.8265619678257, "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": 31.65894027136433, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 40, "generated_at": "2026-07-24T13:40:00Z", "losses": 15, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-9e1d4bf411e97fa6", "rated_matches": 72, "raw_elo_rating": 1567.8900482908955, "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": 49.905158234128194, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 23, "generated_at": "2026-07-24T14:00:00Z", "losses": 6, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-3c06949f23d4a77f", "rated_matches": 38, "raw_elo_rating": 1533.7867296752677, "reasoning": "low", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "low", "repair_status": "repaired", "score": 39.84524833675206, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 33, "generated_at": "2026-07-21T14:20:15Z", "losses": 7, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-818ed7ee27b56509", "rated_matches": 46, "raw_elo_rating": 1494.5305918681663, "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": 33.27082079801426, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 55, "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": 60, "raw_elo_rating": 1490.7581639196449, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 33.928994340568096, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 30, "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": 42, "raw_elo_rating": 1500.908758448871, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 34.00069750646294, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 22, "generated_at": "2026-07-21T14:20:15Z", "losses": 9, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-a4643af0a1bcc24c", "rated_matches": 38, "raw_elo_rating": 1478.3686604298084, "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": 28.985856336779992, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 30, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 15, "draws": 17, "generated_at": "2026-07-21T14:20:15Z", "losses": 12, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-f6de1ce39e48807c", "rated_matches": 30, "raw_elo_rating": 1415.9403697276475, "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": 15.226133451490124, "uncertainty": 46.05265101338746, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 44, "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": 50, "raw_elo_rating": 1511.7005114932745, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 37.09284718239884, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 18, "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": 32, "raw_elo_rating": 1557.208361778728, "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": 43.34142642641564, "uncertainty": 43.288827977848925, "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": "2026-07-02T16:51:45Z", "losses": 7, "model": "tencent/hy3-preview", "point_rating_method": "sequential_elo", "public_id": "E-3fd10f7865cc280e", "rated_matches": 54, "raw_elo_rating": 1521.3603548320514, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 39.39237860730228, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 34, "generated_at": "2026-07-24T13:40:00Z", "losses": 16, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-646ff33c7bab8b13", "rated_matches": 56, "raw_elo_rating": 1434.5376024796492, "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": 22.56618976920879, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 53, "generated_at": "2026-07-24T13:40:00Z", "losses": 8, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-ddc16fa197bfc7c5", "rated_matches": 66, "raw_elo_rating": 1509.591619925644, "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": 38.07938423684785, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 25, "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": 32, "raw_elo_rating": 1537.8466070366878, "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": 39.54741325681464, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 37, "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": 46, "raw_elo_rating": 1527.8099734039513, "reasoning": "low", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "low", "repair_status": "repaired", "score": 39.79204852273032, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 50, "generated_at": "2026-07-01T00:15:48Z", "losses": 6, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-7ad356726cce2b22", "rated_matches": 68, "raw_elo_rating": 1474.9093182327397, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 31.42304943743622, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 62, "generated_at": "2026-07-02T06:10:40Z", "losses": 4, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-d58c55e107783a21", "rated_matches": 70, "raw_elo_rating": 1504.3586208087058, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 37.3276091492603, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 30, "generated_at": "2026-07-02T16:51:45Z", "losses": 6, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-1d5f5ff0402ff944", "rated_matches": 42, "raw_elo_rating": 1537.4697859315131, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 41.16497686085959, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 38, "generated_at": "2026-07-02T06:10:40Z", "losses": 2, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-3efc86009429a22c", "rated_matches": 42, "raw_elo_rating": 1494.0667529675093, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 32.659979206462815, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 34, "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": 44, "raw_elo_rating": 1487.9896459881716, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 31.7377887024233, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 24, "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": 48, "raw_elo_rating": 1513.300187609426, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 37.18455802803732, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 13 } ], "GB2-05": [ { "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": 27, "model": "claude-opus-4-5", "point_rating_method": "sequential_elo", "public_id": "E-934b5bc34a7e20b9", "rated_matches": 78, "raw_elo_rating": 1525.0054661960344, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 50.01236594378325, "uncertainty": 12.5043950463012, "unilateral_faults": 0, "wins": 51 }, { "admitted_plugin_count": 1, "attempted_matches": 86, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 41, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 48, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-233f9cae6335e53d", "rated_matches": 82, "raw_elo_rating": 1395.2014642843967, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 35.51777926697464, "uncertainty": 11.132129994845172, "unilateral_faults": 2, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 0, "generated_at": "2026-07-25T10:50:00Z", "losses": 15, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-09963ffe0b0fa5fd", "rated_matches": 64, "raw_elo_rating": 1848.732893856415, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 85.95057329747303, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 49 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "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": 62, "raw_elo_rating": 1837.282768557701, "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": 84.57309131433091, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 48 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 28, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-e619c51e7d5d70d2", "rated_matches": 52, "raw_elo_rating": 1434.5922020031153, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 38.71073878713191, "uncertainty": 24.930281974344517, "unilateral_faults": 2, "wins": 24 }, { "admitted_plugin_count": 1, "attempted_matches": 76, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 38, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 42, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-0dca18c79b6ac9d7", "rated_matches": 76, "raw_elo_rating": 1470.9876886709974, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 43.86361290746909, "uncertainty": 13.230288229818967, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 92, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 44, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 62, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-b8554f0ccf0845da", "rated_matches": 88, "raw_elo_rating": 1380.4056653616792, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 34.02108976107974, "uncertainty": 9.249894000318006, "unilateral_faults": 2, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 92, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 46, "draws": 0, "generated_at": "2026-07-01T00:15:48Z", "losses": 51, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-efa8d9109b008ee9", "rated_matches": 92, "raw_elo_rating": 1438.0999111227916, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 40.62229553055088, "uncertainty": 8.09758473652126, "unilateral_faults": 0, "wins": 41 }, { "admitted_plugin_count": 1, "attempted_matches": 86, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 43, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 48, "model": "deepseek/deepseek-v4-pro", "point_rating_method": "sequential_elo", "public_id": "E-da5f3b1a4e370e1a", "rated_matches": 86, "raw_elo_rating": 1400.7555461917282, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 36.25827225605603, "uncertainty": 9.855626741889738, "unilateral_faults": 0, "wins": 38 }, { "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": 36, "model": "google/gemini-3.1-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-d979b43c3aeea657", "rated_matches": 52, "raw_elo_rating": 1272.024034199102, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 20.402696248566944, "uncertainty": 24.930281974344517, "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": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 45, "model": "google/gemma-4-31b-it", "point_rating_method": "sequential_elo", "public_id": "E-e8e17fbbdd12faa4", "rated_matches": 70, "raw_elo_rating": 1284.119780904192, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 22.606477627919652, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 25 }, { "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": "gpt-4.1", "point_rating_method": "sequential_elo", "public_id": "E-1b9f1f7b70f02927", "rated_matches": 52, "raw_elo_rating": 1322.2740939222144, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 26.061739119033867, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 88, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 44, "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": 88, "raw_elo_rating": 1767.2078133828695, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 77.5818327751585, "uncertainty": 9.249894000318006, "unilateral_faults": 0, "wins": 63 }, { "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": 47, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-427bdffeacc6c394", "rated_matches": 68, "raw_elo_rating": 1289.0925360366127, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 23.08957126865442, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 37, "draws": 0, "generated_at": "2026-07-01T00:15:48Z", "losses": 36, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-8ed627956c0a0292", "rated_matches": 74, "raw_elo_rating": 1391.2479155648975, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 34.81551075849012, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 38 }, { "admitted_plugin_count": 1, "attempted_matches": 86, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 43, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 52, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-cdd304da89074d54", "rated_matches": 86, "raw_elo_rating": 1357.1978658786666, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 31.352909325386037, "uncertainty": 9.855626741889738, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 82, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 41, "draws": 0, "generated_at": "2026-07-09T17:30:50Z", "losses": 59, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-3311575b341ee4a8", "rated_matches": 82, "raw_elo_rating": 1319.4297397884322, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 26.98454687571744, "uncertainty": 11.132129994845172, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 84, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 42, "draws": 0, "generated_at": "2026-07-01T00:15:48Z", "losses": 56, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-49b3c6006a3b9fcc", "rated_matches": 84, "raw_elo_rating": 1380.0275715590533, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 33.86744888185659, "uncertainty": 10.482614454664043, "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": "2026-07-02T16:51:45Z", "losses": 50, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-6c37eeef15b82287", "rated_matches": 68, "raw_elo_rating": 1255.8506947784497, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 19.345953732481064, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 18 }, { "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": 31, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-6f42dbbf02274b56", "rated_matches": 74, "raw_elo_rating": 1594.0645150033788, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 57.656236468847425, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 43 }, { "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": 61, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-59156a669808a24f", "rated_matches": 66, "raw_elo_rating": 1084.779723090878, "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": 17.33472217815261, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 37, "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": 74, "raw_elo_rating": 1611.7895712923712, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 59.65239038336131, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 49 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 37, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 27, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-1f00b423eab1c19d", "rated_matches": 74, "raw_elo_rating": 1599.653295433683, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 58.28563170186785, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 47 }, { "admitted_plugin_count": 1, "attempted_matches": 78, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 39, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 62, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-067ab716d64e3e9a", "rated_matches": 78, "raw_elo_rating": 1239.039256360454, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 17.80752778276196, "uncertainty": 12.5043950463012, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 82, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 37, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 46, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-8cc657b7db4428cb", "rated_matches": 74, "raw_elo_rating": 1344.4909352072373, "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": 29.549850224043485, "uncertainty": 13.985026918962571, "unilateral_faults": 4, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 94, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 47, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 42, "model": "minimax/minimax-m3", "point_rating_method": "sequential_elo", "public_id": "E-33797d7b77c7800c", "rated_matches": 94, "raw_elo_rating": 1478.69665172829, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 45.24363611055831, "uncertainty": 7.54891760425771, "unilateral_faults": 0, "wins": 52 }, { "admitted_plugin_count": 1, "attempted_matches": 94, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 47, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 53, "model": "mistralai/mistral-medium-3-5", "point_rating_method": "sequential_elo", "public_id": "E-4a7d37b86196302f", "rated_matches": 94, "raw_elo_rating": 1414.8804142848849, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 38.05680239306483, "uncertainty": 7.54891760425771, "unilateral_faults": 0, "wins": 41 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 24, "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": 48, "raw_elo_rating": 1695.0977713005702, "reasoning": "low", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "low", "repair_status": "first_pass", "score": 67.80065514605346, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 37 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 24, "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": 48, "raw_elo_rating": 1664.197870454584, "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": 64.32078139975053, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 90, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 45, "draws": 0, "generated_at": "2026-07-11T17:22:09Z", "losses": 47, "model": "nex-agi/nex-n2-pro", "point_rating_method": "sequential_elo", "public_id": "E-962a9da8812a74d4", "rated_matches": 90, "raw_elo_rating": 1460.6854546643076, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 43.1147735572218, "uncertainty": 8.664241836095918, "unilateral_faults": 0, "wins": 43 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 17, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-4477e0de2e04aad4", "rated_matches": 54, "raw_elo_rating": 1547.5175821569976, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 51.541673218867665, "uncertainty": 23.66998624632421, "unilateral_faults": 2, "wins": 37 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 0, "generated_at": "2026-07-21T14:20:15Z", "losses": 12, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-b556333d605791f4", "rated_matches": 48, "raw_elo_rating": 1672.7981964551377, "reasoning": "low", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "low", "repair_status": "first_pass", "score": 65.28932977173861, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 36 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 0, "generated_at": "2026-07-21T14:20:15Z", "losses": 27, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-172336d3fd38632a", "rated_matches": 48, "raw_elo_rating": 1361.7503235309423, "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": 30.259854038877847, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 21 }, { "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": 21, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-1ca53619662c7f6f", "rated_matches": 74, "raw_elo_rating": 1717.6790913377977, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 71.57741767232629, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 53 }, { "admitted_plugin_count": 1, "attempted_matches": 76, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 37, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-21623e96b2b104e9", "rated_matches": 72, "raw_elo_rating": 1397.8682571935017, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 35.49030484656112, "uncertainty": 14.770573598065289, "unilateral_faults": 2, "wins": 35 }, { "admitted_plugin_count": 1, "attempted_matches": 76, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 38, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 38, "model": "qwen/qwen3.7-max", "point_rating_method": "sequential_elo", "public_id": "E-c577c41440c17864", "rated_matches": 76, "raw_elo_rating": 1546.3265864598327, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 52.348101378726525, "uncertainty": 13.230288229818967, "unilateral_faults": 0, "wins": 38 }, { "admitted_plugin_count": 1, "attempted_matches": 78, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 39, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 41, "model": "qwen/qwen3.7-plus", "point_rating_method": "sequential_elo", "public_id": "E-94daaf1196d89c6c", "rated_matches": 78, "raw_elo_rating": 1403.12799966028, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 36.28681393707585, "uncertainty": 12.5043950463012, "unilateral_faults": 0, "wins": 37 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 0, "generated_at": "2026-07-21T14:20:15Z", "losses": 30, "model": "stepfun/step-3.7-flash", "point_rating_method": "sequential_elo", "public_id": "E-386b7a319dfe25ad", "rated_matches": 48, "raw_elo_rating": 1356.3943755691175, "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": 29.656679847743195, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 102, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 51, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 69, "model": "tencent/hy3-preview", "point_rating_method": "sequential_elo", "public_id": "E-1bb81f8a4ae78954", "rated_matches": 102, "raw_elo_rating": 1351.9190552018522, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 31.14935515682644, "uncertainty": 5.516463908214657, "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": "2026-07-24T13:40:00Z", "losses": 44, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-0f05573125dedc2b", "rated_matches": 76, "raw_elo_rating": 1430.9712174685433, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 39.357052570878395, "uncertainty": 13.230288229818967, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugin_count": 1, "attempted_matches": 76, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 38, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 50, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-f7a1d86c7e241f8d", "rated_matches": 76, "raw_elo_rating": 1462.3133546536524, "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": 42.886729927679795, "uncertainty": 13.230288229818967, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 25, "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": 50, "raw_elo_rating": 1615.4876782359684, "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": 58.96259893763863, "uncertainty": 26.26400420140049, "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": "2026-07-21T14:20:15Z", "losses": 3, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-fcfafa8fb4ccd299", "rated_matches": 46, "raw_elo_rating": 1849.6069103410052, "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": 85.06561420733325, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 43 }, { "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": 30, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-09d406abc15f7c9a", "rated_matches": 76, "raw_elo_rating": 1612.214190816547, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 59.768207538630506, "uncertainty": 13.230288229818967, "unilateral_faults": 0, "wins": 46 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 37, "draws": 0, "generated_at": "2026-07-01T00:15:48Z", "losses": 47, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-9490f08c56c27d13", "rated_matches": 74, "raw_elo_rating": 1305.8159334017118, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 25.194362997981777, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 27 }, { "admitted_plugin_count": 1, "attempted_matches": 82, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 39, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 43, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-be8fc9653466bbe1", "rated_matches": 78, "raw_elo_rating": 1403.3936759128974, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 36.316733768246415, "uncertainty": 12.5043950463012, "unilateral_faults": 2, "wins": 35 }, { "admitted_plugin_count": 1, "attempted_matches": 98, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 49, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 55, "model": "xiaomi/mimo-v2.5-pro", "point_rating_method": "sequential_elo", "public_id": "E-af55f57b03605914", "rated_matches": 98, "raw_elo_rating": 1350.1016690927315, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 30.855904278592035, "uncertainty": 6.501890762960602, "unilateral_faults": 0, "wins": 43 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 0, "generated_at": "2026-07-11T14:00:45Z", "losses": 26, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-38e323f4ce233fa1", "rated_matches": 52, "raw_elo_rating": 1444.743330661769, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 39.85393488638997, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 0, "generated_at": "2026-07-01T00:15:48Z", "losses": 29, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-6370c4b68d38a97e", "rated_matches": 52, "raw_elo_rating": 1368.3671536085135, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 31.252630477831257, "uncertainty": 24.930281974344517, "unilateral_faults": 2, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 32, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-a6655b3c71893984", "rated_matches": 52, "raw_elo_rating": 1406.828924920958, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 35.584104190112406, "uncertainty": 24.930281974344517, "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": "2026-07-02T16:51:45Z", "losses": 22, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-d8655d29a4806df8", "rated_matches": 52, "raw_elo_rating": 1593.3125482263345, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 56.58544876045006, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 30 } ], "GB2-06": [ { "admitted_plugin_count": 1, "attempted_matches": 78, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 39, "draws": 3, "generated_at": "2026-07-02T16:51:45Z", "losses": 36, "model": "claude-opus-4-5", "point_rating_method": "sequential_elo", "public_id": "E-40a259ca8a40b5b4", "rated_matches": 78, "raw_elo_rating": 1491.4086342006274, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 53.20069535861266, "uncertainty": 12.5043950463012, "unilateral_faults": 0, "wins": 39 }, { "admitted_plugin_count": 1, "attempted_matches": 82, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 41, "draws": 5, "generated_at": "2026-07-02T16:51:45Z", "losses": 33, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-db414178442322d3", "rated_matches": 82, "raw_elo_rating": 1514.105193415293, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 56.281940805437515, "uncertainty": 11.132129994845172, "unilateral_faults": 0, "wins": 44 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 13, "generated_at": "2026-07-25T10:50:00Z", "losses": 8, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-ca8985adf5006428", "rated_matches": 60, "raw_elo_rating": 1785.4552045796995, "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": 90.4738514404464, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 39 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 2, "generated_at": "2026-07-02T16:51:45Z", "losses": 23, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-500304c7462c6005", "rated_matches": 46, "raw_elo_rating": 1516.9982745147104, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 54.78663788327743, "uncertainty": 29.182495748947275, "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": "2026-07-01T00:15:48Z", "losses": 39, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-8daa317358045ed1", "rated_matches": 62, "raw_elo_rating": 1342.4504929366262, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 33.21319976929683, "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": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 50, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-db0efb02339d9e80", "rated_matches": 64, "raw_elo_rating": 1184.1074694015106, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 12.80979743959458, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 6, "generated_at": "2026-07-02T16:51:45Z", "losses": 14, "model": "deepseek/deepseek-v4-pro", "point_rating_method": "sequential_elo", "public_id": "E-945bebaa34963e03", "rated_matches": 68, "raw_elo_rating": 1694.0603780225329, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 79.03501098478921, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 48 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 1, "generated_at": "2026-07-02T16:51:45Z", "losses": 21, "model": "google/gemini-3.1-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-dc1c0f46738d1091", "rated_matches": 46, "raw_elo_rating": 1412.2766689959317, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 41.225742883378615, "uncertainty": 29.182495748947275, "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": "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": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 46, "model": "google/gemma-4-31b-it", "point_rating_method": "sequential_elo", "public_id": "E-da266f7bbd330107", "rated_matches": 70, "raw_elo_rating": 1369.8707689668845, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 37.14262287973516, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 9, "generated_at": "2026-07-02T16:51:45Z", "losses": 17, "model": "gpt-4.1", "point_rating_method": "sequential_elo", "public_id": "E-4dcd6d3653c67437", "rated_matches": 48, "raw_elo_rating": 1509.3680825685708, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 53.954368519741806, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 22 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "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": 63, "raw_elo_rating": 1654.8715395144725, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 73.72126024399091, "uncertainty": 18.75, "unilateral_faults": 1, "wins": 42 }, { "admitted_plugin_count": 1, "attempted_matches": 82, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 41, "draws": 5, "generated_at": "2026-07-01T00:15:48Z", "losses": 42, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-050fceb6ddf16bc3", "rated_matches": 82, "raw_elo_rating": 1422.45955765613, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 44.41431485019834, "uncertainty": 11.132129994845172, "unilateral_faults": 0, "wins": 35 }, { "admitted_plugin_count": 1, "attempted_matches": 80, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 40, "draws": 4, "generated_at": "2026-07-02T16:51:45Z", "losses": 41, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-144154b792c9e9a6", "rated_matches": 80, "raw_elo_rating": 1422.0682161048328, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 44.29387414191289, "uncertainty": 11.805555555555554, "unilateral_faults": 0, "wins": 35 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 1, "generated_at": "2026-07-02T06:10:40Z", "losses": 37, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-e726e4bfd20b0da9", "rated_matches": 70, "raw_elo_rating": 1340.587052453575, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 33.35053620500806, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 2, "generated_at": "2026-07-02T06:10:40Z", "losses": 23, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-3d7e23d6ea4c2792", "rated_matches": 68, "raw_elo_rating": 1625.0398154861382, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 70.09721255481617, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 43 }, { "admitted_plugin_count": 1, "attempted_matches": 80, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 40, "draws": 0, "generated_at": "2026-07-09T17:30:50Z", "losses": 49, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-a1fb59d78d39d217", "rated_matches": 77, "raw_elo_rating": 1375.5414747998316, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 38.159271786120144, "uncertainty": 12.86385170722978, "unilateral_faults": 1, "wins": 28 }, { "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": 18, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-d5866895bf388f66", "rated_matches": 66, "raw_elo_rating": 1667.896647873528, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 75.55455981019395, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 48 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 52, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-ae522f9c5c491f57", "rated_matches": 62, "raw_elo_rating": 1151.0525414647095, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 8.428175606914639, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugin_count": 1, "attempted_matches": 86, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 43, "draws": 1, "generated_at": "2026-07-10T05:30:29Z", "losses": 51, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-992b9a5ebbb74c80", "rated_matches": 86, "raw_elo_rating": 1400.8514714375945, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 41.748422117643045, "uncertainty": 9.855626741889738, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 78, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 39, "draws": 1, "generated_at": "2026-07-10T05:30:29Z", "losses": 47, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-22ffdca36d9bac9c", "rated_matches": 78, "raw_elo_rating": 1345.2675207188454, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 34.27619276645788, "uncertainty": 12.5043950463012, "unilateral_faults": 0, "wins": 30 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 3, "generated_at": "2026-07-24T13:40:00Z", "losses": 40, "model": "inclusionai/ling-3.0-flash", "point_rating_method": "sequential_elo", "public_id": "E-6807fffacebac165", "rated_matches": 70, "raw_elo_rating": 1368.0002176088735, "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": 36.90039635511072, "uncertainty": 15.58908290969266, "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": 63, "model": "inclusionai/ling-3.0-flash", "point_rating_method": "sequential_elo", "public_id": "E-9bde0475193e2c4a", "rated_matches": 66, "raw_elo_rating": 1084.4399654313177, "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": 17.33472217815261, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 2, "generated_at": "2026-07-24T13:40:00Z", "losses": 43, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-3e8b2d11481a50d7", "rated_matches": 70, "raw_elo_rating": 1449.8704786885137, "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": 47.502162901902345, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 14, "generated_at": "2026-07-24T13:40:00Z", "losses": 29, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-e3023ff7ecf82fc4", "rated_matches": 72, "raw_elo_rating": 1529.236235750301, "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": 57.86440350919441, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 5, "generated_at": "2026-07-02T16:51:45Z", "losses": 37, "model": "mistralai/mistral-medium-3-5", "point_rating_method": "sequential_elo", "public_id": "E-cf0bc4a1e7a8d72a", "rated_matches": 68, "raw_elo_rating": 1319.423486454839, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 30.52151155484641, "uncertainty": 16.4429265428846, "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": "2026-07-21T14:20:15Z", "losses": 5, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-2f8c760ee4329d00", "rated_matches": 41, "raw_elo_rating": 1793.063355178339, "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": 90.0985190987841, "uncertainty": 33.40167498104595, "unilateral_faults": 1, "wins": 36 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 2, "generated_at": "2026-07-24T14:00:00Z", "losses": 22, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-95a5c0e17cd4b70a", "rated_matches": 58, "raw_elo_rating": 1523.8597797113378, "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": 56.48715444231329, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 2, "generated_at": "2026-07-11T17:22:09Z", "losses": 47, "model": "nex-agi/nex-n2-pro", "point_rating_method": "sequential_elo", "public_id": "E-973417dedd770061", "rated_matches": 70, "raw_elo_rating": 1316.479215503516, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 30.228698605833657, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 21 }, { "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": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-6e76a1c11ba24bc6", "rated_matches": 46, "raw_elo_rating": 1359.117852968085, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 34.3419568785575, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 1, "generated_at": "2026-07-21T14:20:15Z", "losses": 4, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-e4a4a86669325de4", "rated_matches": 41, "raw_elo_rating": 1801.1941168780218, "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": 91.1514098096587, "uncertainty": 33.40167498104595, "unilateral_faults": 0, "wins": 36 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 1, "generated_at": "2026-07-21T14:20:15Z", "losses": 33, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-b75de88bfc62ab22", "rated_matches": 60, "raw_elo_rating": 1489.4394058512037, "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": 52.1413684252918, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 2, "generated_at": "2026-07-24T13:40:00Z", "losses": 34, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-a29031412bc33c39", "rated_matches": 68, "raw_elo_rating": 1339.4494417733786, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 33.11476703447791, "uncertainty": 16.4429265428846, "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": 41, "model": "qwen/qwen3.7-max", "point_rating_method": "sequential_elo", "public_id": "E-0c7e9f6c7d4cb892", "rated_matches": 66, "raw_elo_rating": 1331.436946958018, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 31.98480499971793, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 25 }, { "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": 59, "model": "qwen/qwen3.7-plus", "point_rating_method": "sequential_elo", "public_id": "E-2fb82a23fdec2792", "rated_matches": 78, "raw_elo_rating": 1329.0543202231288, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 32.17666890559334, "uncertainty": 12.5043950463012, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 0, "generated_at": "2026-07-21T14:20:15Z", "losses": 28, "model": "stepfun/step-3.7-flash", "point_rating_method": "sequential_elo", "public_id": "E-8a88dceef8a0239c", "rated_matches": 42, "raw_elo_rating": 1341.761233690627, "reasoning": "low", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "low", "repair_status": "repaired", "score": 31.75076094863466, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 14 }, { "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": 40, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-02be9616e86c7055", "rated_matches": 70, "raw_elo_rating": 1419.683927091336, "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": 43.593163850651706, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 30 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 3, "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": 42, "raw_elo_rating": 1588.4968458398534, "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": 63.70171999396187, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 1, "generated_at": "2026-07-21T14:20:15Z", "losses": 16, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-9eb453b88beb68a4", "rated_matches": 42, "raw_elo_rating": 1597.027458180251, "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": 64.80638925165604, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 25 }, { "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": 35, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-d572bc902e0e416b", "rated_matches": 58, "raw_elo_rating": 1357.045266862595, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 34.885555784666536, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 22 }, { "admitted_plugin_count": 1, "attempted_matches": 76, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 38, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 51, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-d79ad8bc05d1b933", "rated_matches": 76, "raw_elo_rating": 1394.8106074391387, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 40.61656144874905, "uncertainty": 13.230288229818967, "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": "2026-07-01T00:15:48Z", "losses": 22, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-ff7683792b6b3363", "rated_matches": 66, "raw_elo_rating": 1622.5314133163806, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 69.68000145685647, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 44 }, { "admitted_plugin_count": 1, "attempted_matches": 84, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 42, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 41, "model": "xiaomi/mimo-v2.5-pro", "point_rating_method": "sequential_elo", "public_id": "E-6b662c734cdcff91", "rated_matches": 84, "raw_elo_rating": 1470.1028400149814, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 50.65115543258182, "uncertainty": 10.482614454664043, "unilateral_faults": 0, "wins": 43 }, { "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": 38, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-18454080fac44f8c", "rated_matches": 46, "raw_elo_rating": 1171.824448870106, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 10.08844992968959, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 4, "generated_at": "2026-07-11T14:00:45Z", "losses": 21, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-657c61c9039ce566", "rated_matches": 46, "raw_elo_rating": 1472.5353616420934, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 49.02892542395991, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 6, "generated_at": "2026-07-02T06:10:40Z", "losses": 21, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-6954e92d5890c32a", "rated_matches": 46, "raw_elo_rating": 1511.653239266157, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 54.094484039595265, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 3, "generated_at": "2026-07-02T16:51:45Z", "losses": 19, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-ec1479c855f477b4", "rated_matches": 46, "raw_elo_rating": 1607.0088479011472, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 66.44253189413912, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 24 } ], "GB2-07": [ { "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": 34, "model": "claude-opus-4-5", "point_rating_method": "sequential_elo", "public_id": "E-ca22621c58b6f244", "rated_matches": 68, "raw_elo_rating": 1503.5474590816427, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 49.099189369518875, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 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": 70, "raw_elo_rating": 1632.6918398913665, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 65.03810238045806, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 45 }, { "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": 20, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-914b104a64ab3110", "rated_matches": 58, "raw_elo_rating": 1760.002791541305, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 80.1027947182233, "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": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 22, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-cd6f193a087d8c8d", "rated_matches": 48, "raw_elo_rating": 1573.5069374964892, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 56.58459268593973, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 26 }, { "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": 44, "model": "cohere/north-mini-code", "point_rating_method": "sequential_elo", "public_id": "E-3b908f26a42804a4", "rated_matches": 80, "raw_elo_rating": 1472.3535265304024, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 45.72497508816168, "uncertainty": 11.805555555555554, "unilateral_faults": 0, "wins": 36 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 0, "generated_at": "2026-07-11T17:22:09Z", "losses": 60, "model": "cohere/north-mini-code", "point_rating_method": "sequential_elo", "public_id": "E-c7f5dc6d5d3c2a8d", "rated_matches": 74, "raw_elo_rating": 1198.2973912049488, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 11.8650523130411, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 14 }, { "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": 43, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-8f6a725b68dde85b", "rated_matches": 68, "raw_elo_rating": 1389.6727978939712, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 35.11880048485162, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugin_count": 1, "attempted_matches": 80, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 39, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 46, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-c394c0713cfcfaa4", "rated_matches": 80, "raw_elo_rating": 1404.5796614045998, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 37.40437961245555, "uncertainty": 11.805555555555554, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 82, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 41, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 43, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-c8fd55a5d257c569", "rated_matches": 82, "raw_elo_rating": 1420.6304474348074, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 39.4410753019693, "uncertainty": 11.132129994845172, "unilateral_faults": 0, "wins": 39 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 32, "model": "deepseek/deepseek-v4-pro", "point_rating_method": "sequential_elo", "public_id": "E-f76d96b0f3163d4b", "rated_matches": 72, "raw_elo_rating": 1455.8188321632083, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 43.40379899145002, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 40 }, { "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": 44, "model": "google/gemini-3.1-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-3d6a15fe821fe6ad", "rated_matches": 48, "raw_elo_rating": 1112.6076468036076, "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": 27.67857142857143, "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": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 41, "model": "google/gemma-4-31b-it", "point_rating_method": "sequential_elo", "public_id": "E-3f820f7e8ff15839", "rated_matches": 66, "raw_elo_rating": 1341.3548030169743, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 29.09921306138233, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 25 }, { "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": 22, "model": "gpt-4.1", "point_rating_method": "sequential_elo", "public_id": "E-fcfa606d3cbb0ba0", "rated_matches": 48, "raw_elo_rating": 1491.4730488103537, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 46.513294527136985, "uncertainty": 27.67857142857143, "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": "2026-07-02T16:51:45Z", "losses": 49, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-c8176c382cf75e88", "rated_matches": 84, "raw_elo_rating": 1377.5240664717653, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 34.212698952097796, "uncertainty": 10.482614454664043, "unilateral_faults": 0, "wins": 35 }, { "admitted_plugin_count": 1, "attempted_matches": 78, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 37, "draws": 0, "generated_at": "2026-07-01T00:15:48Z", "losses": 45, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-022243613d51f0fb", "rated_matches": 78, "raw_elo_rating": 1349.6658377833614, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 30.593973859680652, "uncertainty": 12.5043950463012, "unilateral_faults": 0, "wins": 33 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 52, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-6a87ebc54bdde781", "rated_matches": 68, "raw_elo_rating": 1229.885941388591, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 15.50177269916906, "uncertainty": 16.4429265428846, "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": 50, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-c2ab31787514c10c", "rated_matches": 66, "raw_elo_rating": 1233.8027831068532, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 15.895054664836817, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 82, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 41, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 47, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-4e14ae758717169e", "rated_matches": 82, "raw_elo_rating": 1466.9726248764337, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 45.13050309599317, "uncertainty": 11.132129994845172, "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": "2026-07-02T06:10:40Z", "losses": 41, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-ce2925d9379d2a5d", "rated_matches": 72, "raw_elo_rating": 1327.8725244447637, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 27.69583446619687, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 31 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 29, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-4edfe4117ad3e936", "rated_matches": 72, "raw_elo_rating": 1492.1662742344863, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 47.8661734110052, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 43 }, { "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": 53, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-ea529147555b5f2e", "rated_matches": 68, "raw_elo_rating": 1213.9388734979989, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 13.543951632081598, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 15 }, { "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": 31, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-bef852aad169a609", "rated_matches": 68, "raw_elo_rating": 1611.5214513976898, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 62.35515330622509, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 37 }, { "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": 41, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-8ebe8776c7d44d46", "rated_matches": 78, "raw_elo_rating": 1494.0340188618018, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 48.318051305868195, "uncertainty": 12.5043950463012, "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": "2026-07-24T13:40:00Z", "losses": 34, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-c1f595f47c71e648", "rated_matches": 70, "raw_elo_rating": 1354.8088835261667, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 30.922419805526225, "uncertainty": 15.58908290969266, "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": 38, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-e2db910734ca5315", "rated_matches": 70, "raw_elo_rating": 1496.5580733489744, "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": 48.32496377045103, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 32 }, { "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": 43, "model": "minimax/minimax-m3", "point_rating_method": "sequential_elo", "public_id": "E-24e15c4d7490cdf3", "rated_matches": 76, "raw_elo_rating": 1411.2345057212497, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 38.08146314653779, "uncertainty": 13.230288229818967, "unilateral_faults": 0, "wins": 33 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 0, "generated_at": "2026-07-24T14:00:00Z", "losses": 31, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-4d8815930b656774", "rated_matches": 52, "raw_elo_rating": 1412.2381481716995, "reasoning": "low", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "low", "repair_status": "first_pass", "score": 37.055553984478195, "uncertainty": 24.930281974344517, "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": "2026-07-21T14:20:15Z", "losses": 16, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-c00660d2a8eb25c9", "rated_matches": 44, "raw_elo_rating": 1588.5127334969732, "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": 58.12169405695604, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 37, "draws": 0, "generated_at": "2026-07-11T17:22:09Z", "losses": 23, "model": "nex-agi/nex-n2-pro", "point_rating_method": "sequential_elo", "public_id": "E-1006c453b0c3a745", "rated_matches": 74, "raw_elo_rating": 1677.0084877720944, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 70.63639989478703, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 51 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 0, "generated_at": "2026-07-03T18:15:00Z", "losses": 36, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-0e1c7f89e1c19b69", "rated_matches": 48, "raw_elo_rating": 1325.8842408601347, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 26.183961329145713, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 0, "generated_at": "2026-07-21T14:20:15Z", "losses": 26, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-3fae70801895971d", "rated_matches": 50, "raw_elo_rating": 1384.6707866645224, "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": 33.54011697208183, "uncertainty": 26.26400420140049, "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": "2026-07-21T14:20:15Z", "losses": 28, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-759d747bb732d949", "rated_matches": 44, "raw_elo_rating": 1347.04247733592, "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": 28.47639764067811, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 16 }, { "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": 42, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-069a963abdd14cdf", "rated_matches": 70, "raw_elo_rating": 1496.6901741690908, "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": 48.3411817843441, "uncertainty": 15.58908290969266, "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": 30, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-d8e68d23876f6d21", "rated_matches": 72, "raw_elo_rating": 1591.0944960346465, "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": 60.01158836118017, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 42 }, { "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": 22, "model": "qwen/qwen3.7-max", "point_rating_method": "sequential_elo", "public_id": "E-3142a09c7f192060", "rated_matches": 72, "raw_elo_rating": 1780.423050630861, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 83.25544957333192, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 50 }, { "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": 43, "model": "qwen/qwen3.7-plus", "point_rating_method": "sequential_elo", "public_id": "E-737a66790985a5e6", "rated_matches": 68, "raw_elo_rating": 1226.7047132781258, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 15.111213415380366, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 0, "generated_at": "2026-07-21T14:20:15Z", "losses": 33, "model": "stepfun/step-3.7-flash", "point_rating_method": "sequential_elo", "public_id": "E-1140a7c92290e8f4", "rated_matches": 58, "raw_elo_rating": 1387.7648759569868, "reasoning": "low", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "low", "repair_status": "repaired", "score": 34.40315650889252, "uncertainty": 21.344455490411935, "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": "2026-07-24T13:40:00Z", "losses": 45, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-062d41f517db2ccb", "rated_matches": 72, "raw_elo_rating": 1355.947726299098, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 31.142626191814056, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 27 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 22, "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": 44, "raw_elo_rating": 1716.430482163852, "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": 73.82615238826833, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 37 }, { "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": 5, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-ca54791ad3682b4f", "rated_matches": 46, "raw_elo_rating": 1780.9617876853945, "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": 81.90610929109198, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 41 }, { "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": 40, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-0984b025e9005f5b", "rated_matches": 70, "raw_elo_rating": 1306.2839817049132, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 24.965019002081572, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 30 }, { "admitted_plugin_count": 1, "attempted_matches": 82, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 41, "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": 82, "raw_elo_rating": 1480.5760444250511, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 46.80059452342257, "uncertainty": 11.132129994845172, "unilateral_faults": 0, "wins": 38 }, { "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": "xiaomi/mimo-v2.5-pro", "point_rating_method": "sequential_elo", "public_id": "E-83580d03385c6759", "rated_matches": 64, "raw_elo_rating": 1672.9945867330275, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 69.72301913548274, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 42 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 0, "generated_at": "2026-07-11T14:00:45Z", "losses": 21, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-62e8714f035ebc68", "rated_matches": 48, "raw_elo_rating": 1537.5715700070969, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 52.17280865097196, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 27 }, { "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": 25, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-e31f275ab7ef3741", "rated_matches": 48, "raw_elo_rating": 1539.433180620169, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 52.401358532491955, "uncertainty": 27.67857142857143, "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": "2026-07-01T00:15:48Z", "losses": 20, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-f7579fbfcb1dcbb9", "rated_matches": 48, "raw_elo_rating": 1568.8284110167365, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 56.01021012434106, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 28 } ], "GB2-08": [ { "admitted_plugin_count": 1, "attempted_matches": 82, "capped_draws": 6, "coverage_status": "rated", "distinct_rated_opponents": 41, "draws": 6, "generated_at": "2026-07-02T16:51:45Z", "losses": 20, "model": "claude-opus-4-5", "point_rating_method": "sequential_elo", "public_id": "E-01b57d5e6655f927", "rated_matches": 82, "raw_elo_rating": 1661.7483294998035, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 61.56795396592303, "uncertainty": 11.132129994845172, "unilateral_faults": 0, "wins": 56 }, { "admitted_plugin_count": 1, "attempted_matches": 82, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 41, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 23, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-c9d7578e8375d994", "rated_matches": 82, "raw_elo_rating": 1670.7429079994065, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 62.88796737924806, "uncertainty": 11.132129994845172, "unilateral_faults": 0, "wins": 59 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 0, "generated_at": "2026-07-25T10:50:00Z", "losses": 27, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-5a7942274854aaa6", "rated_matches": 62, "raw_elo_rating": 1573.2699692206909, "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": 47.63078866300169, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 35 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 48, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 48, "generated_at": "2026-07-02T16:51:45Z", "losses": 2, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-cf0ed4bbe4aaadd7", "rated_matches": 50, "raw_elo_rating": 1437.362421007031, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 26.861288109097305, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 55, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 55, "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": 68, "raw_elo_rating": 1447.898423960942, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 29.56056174566684, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 44, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 44, "generated_at": "2026-07-02T16:51:45Z", "losses": 18, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-4375cf96eeb624e2", "rated_matches": 70, "raw_elo_rating": 1423.4125728363276, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 26.06734815221141, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 76, "capped_draws": 63, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 63, "generated_at": "2026-07-02T06:10:40Z", "losses": 9, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-95b070e1c29e44f0", "rated_matches": 72, "raw_elo_rating": 1408.6028863434017, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 23.990026774405592, "uncertainty": 14.770573598065289, "unilateral_faults": 2, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 60, "coverage_status": "rated", "distinct_rated_opponents": 37, "draws": 60, "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": 74, "raw_elo_rating": 1438.9170506943865, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 28.531056604920728, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 80, "capped_draws": 67, "coverage_status": "rated", "distinct_rated_opponents": 40, "draws": 67, "generated_at": "2026-07-02T16:51:45Z", "losses": 9, "model": "deepseek/deepseek-v4-pro", "point_rating_method": "sequential_elo", "public_id": "E-c296a7abab6975d7", "rated_matches": 80, "raw_elo_rating": 1442.4017586919488, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 29.298341747357632, "uncertainty": 11.805555555555554, "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-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": 84, "capped_draws": 59, "coverage_status": "rated", "distinct_rated_opponents": 40, "draws": 59, "generated_at": "2026-07-02T16:51:45Z", "losses": 18, "model": "google/gemma-4-31b-it", "point_rating_method": "sequential_elo", "public_id": "E-8546650b7690a81a", "rated_matches": 79, "raw_elo_rating": 1426.0434530743848, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 26.8570139531642, "uncertainty": 12.151699437494736, "unilateral_faults": 2, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 33, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 33, "generated_at": "2026-07-02T16:51:45Z", "losses": 14, "model": "gpt-4.1", "point_rating_method": "sequential_elo", "public_id": "E-eabc996d553eebe0", "rated_matches": 54, "raw_elo_rating": 1419.0289552749614, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 24.4752830412746, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 78, "capped_draws": 51, "coverage_status": "rated", "distinct_rated_opponents": 39, "draws": 51, "generated_at": "2026-07-02T16:51:45Z", "losses": 17, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-95f891d54f35bb4a", "rated_matches": 78, "raw_elo_rating": 1436.845557932157, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 28.40088540388973, "uncertainty": 12.5043950463012, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 38, "coverage_status": "rated", "distinct_rated_opponents": 37, "draws": 38, "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": 74, "raw_elo_rating": 1436.7317351212178, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 28.210347205468835, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 82, "capped_draws": 57, "coverage_status": "rated", "distinct_rated_opponents": 41, "draws": 57, "generated_at": "2026-07-01T00:15:48Z", "losses": 21, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-7ff0b78720f446ad", "rated_matches": 82, "raw_elo_rating": 1419.0534911448178, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 25.95089397945687, "uncertainty": 11.132129994845172, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 63, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 63, "generated_at": "2026-07-02T16:51:45Z", "losses": 7, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-bb8ac98c284a38ce", "rated_matches": 70, "raw_elo_rating": 1427.6035082282665, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 26.68239542007192, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 100, "capped_draws": 73, "coverage_status": "rated", "distinct_rated_opponents": 42, "draws": 73, "generated_at": "2026-07-09T17:30:50Z", "losses": 11, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-024aff0a983df40d", "rated_matches": 84, "raw_elo_rating": 1403.53396138828, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 23.749557689174935, "uncertainty": 10.482614454664043, "unilateral_faults": 8, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 80, "capped_draws": 64, "coverage_status": "rated", "distinct_rated_opponents": 40, "draws": 64, "generated_at": "2026-07-02T06:10:40Z", "losses": 14, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-814593575d73a7cd", "rated_matches": 80, "raw_elo_rating": 1413.551380104126, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 25.06435938597039, "uncertainty": 11.805555555555554, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 84, "capped_draws": 61, "coverage_status": "rated", "distinct_rated_opponents": 40, "draws": 61, "generated_at": "2026-07-01T00:15:48Z", "losses": 14, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-c320ceaf4558afab", "rated_matches": 80, "raw_elo_rating": 1445.963699766453, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 29.821079971947757, "uncertainty": 11.805555555555554, "unilateral_faults": 2, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 78, "capped_draws": 4, "coverage_status": "rated", "distinct_rated_opponents": 39, "draws": 4, "generated_at": "2026-07-02T16:51:45Z", "losses": 25, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-fd5a36e5fd795426", "rated_matches": 78, "raw_elo_rating": 1612.235845265633, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 54.14056090478664, "uncertainty": 12.5043950463012, "unilateral_faults": 0, "wins": 49 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 55, "coverage_status": "rated", "distinct_rated_opponents": 37, "draws": 55, "generated_at": "2026-07-02T16:51:45Z", "losses": 14, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-c42fbee03a029c83", "rated_matches": 74, "raw_elo_rating": 1435.4933507900123, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 28.028606179125585, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 59, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 59, "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": 68, "raw_elo_rating": 1434.0824942540764, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 27.53298340706836, "uncertainty": 16.4429265428846, "unilateral_faults": 2, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 7, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 7, "generated_at": "2026-07-10T05:30:29Z", "losses": 26, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-994624d0bc2e266d", "rated_matches": 70, "raw_elo_rating": 1514.8243499856248, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 39.48262625315627, "uncertainty": 15.58908290969266, "unilateral_faults": 2, "wins": 37 }, { "admitted_plugin_count": 1, "attempted_matches": 84, "capped_draws": 61, "coverage_status": "rated", "distinct_rated_opponents": 42, "draws": 61, "generated_at": "2026-07-10T05:30:29Z", "losses": 19, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-44cace55a6126cdf", "rated_matches": 84, "raw_elo_rating": 1431.615078138953, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 27.87064582839924, "uncertainty": 10.482614454664043, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 60, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 60, "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": 72, "raw_elo_rating": 1418.054546041148, "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": 25.377119852726032, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 78, "capped_draws": 63, "coverage_status": "rated", "distinct_rated_opponents": 39, "draws": 63, "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": 78, "raw_elo_rating": 1423.165394767332, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 26.39323169617664, "uncertainty": 12.5043950463012, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 61, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 61, "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": 72, "raw_elo_rating": 1419.4833709182178, "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": 25.58680927876285, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 60, "coverage_status": "rated", "distinct_rated_opponents": 37, "draws": 60, "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": 74, "raw_elo_rating": 1429.999497281636, "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": 27.222347128496388, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 78, "capped_draws": 7, "coverage_status": "rated", "distinct_rated_opponents": 39, "draws": 7, "generated_at": "2026-07-02T16:51:45Z", "losses": 35, "model": "minimax/minimax-m3", "point_rating_method": "sequential_elo", "public_id": "E-e67e41d4491d7ad3", "rated_matches": 78, "raw_elo_rating": 1523.287920626812, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 41.08686932648167, "uncertainty": 12.5043950463012, "unilateral_faults": 0, "wins": 36 }, { "admitted_plugin_count": 1, "attempted_matches": 92, "capped_draws": 61, "coverage_status": "rated", "distinct_rated_opponents": 40, "draws": 61, "generated_at": "2026-07-02T16:51:45Z", "losses": 18, "model": "mistralai/mistral-medium-3-5", "point_rating_method": "sequential_elo", "public_id": "E-ba85be2fa53925f5", "rated_matches": 80, "raw_elo_rating": 1416.3368045051216, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 25.473138693558756, "uncertainty": 11.805555555555554, "unilateral_faults": 6, "wins": 1 }, { "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": 2, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-3e1be56b9d966ded", "rated_matches": 46, "raw_elo_rating": 1820.3922762390605, "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": 82.73078641197665, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 44 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 16, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 16, "generated_at": "2026-07-21T14:20:15Z", "losses": 15, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-b88e77144afeb8fd", "rated_matches": 46, "raw_elo_rating": 1514.7954980475845, "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": 37.88245401936075, "uncertainty": 29.182495748947275, "unilateral_faults": 2, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 56, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 56, "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": 64, "raw_elo_rating": 1435.7725076009103, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 27.5668050336474, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 44, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 44, "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": 50, "raw_elo_rating": 1448.227540293634, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 28.45581565658891, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 24, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 24, "generated_at": "2026-07-21T14:20:15Z", "losses": 13, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-cbb72b5e25b55cee", "rated_matches": 46, "raw_elo_rating": 1499.982489727866, "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": 35.70854785193036, "uncertainty": 29.182495748947275, "unilateral_faults": 2, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 37, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 37, "generated_at": "2026-07-21T14:20:15Z", "losses": 6, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-f6e9da46c61ad315", "rated_matches": 46, "raw_elo_rating": 1428.8001234106816, "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": 25.262068527185047, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 76, "capped_draws": 66, "coverage_status": "rated", "distinct_rated_opponents": 38, "draws": 66, "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": 76, "raw_elo_rating": 1416.5330777584284, "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": 25.334671986602174, "uncertainty": 13.230288229818967, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 76, "capped_draws": 59, "coverage_status": "rated", "distinct_rated_opponents": 38, "draws": 59, "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": 76, "raw_elo_rating": 1413.9390431952345, "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": 24.95398039352798, "uncertainty": 13.230288229818967, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 78, "capped_draws": 50, "coverage_status": "rated", "distinct_rated_opponents": 39, "draws": 50, "generated_at": "2026-07-02T16:51:45Z", "losses": 23, "model": "qwen/qwen3.7-max", "point_rating_method": "sequential_elo", "public_id": "E-a667eb7d15f7f43e", "rated_matches": 78, "raw_elo_rating": 1451.3049117986232, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 30.52289045977884, "uncertainty": 12.5043950463012, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 38, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 38, "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": 46, "raw_elo_rating": 1404.3431246021992, "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": 21.672843475861427, "uncertainty": 29.182495748947275, "unilateral_faults": 2, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 84, "capped_draws": 68, "coverage_status": "rated", "distinct_rated_opponents": 42, "draws": 68, "generated_at": "2026-07-02T16:51:45Z", "losses": 15, "model": "tencent/hy3-preview", "point_rating_method": "sequential_elo", "public_id": "E-56487337fad4192f", "rated_matches": 84, "raw_elo_rating": 1444.6787048624783, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 29.78781876790787, "uncertainty": 10.482614454664043, "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": 1642.069056814891, "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": 58.05637618014437, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 23, "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": 46, "raw_elo_rating": 1738.5892014713577, "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": 70.72564843365268, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 38 }, { "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": 7, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-b914d026c7631fcb", "rated_matches": 46, "raw_elo_rating": 1774.8087656357409, "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": 76.04110713178775, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 39 }, { "admitted_plugin_count": 1, "attempted_matches": 76, "capped_draws": 52, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 52, "generated_at": "2026-07-02T16:51:45Z", "losses": 18, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-cabbf604f15eb575", "rated_matches": 72, "raw_elo_rating": 1366.1166145408445, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 17.7548876109612, "uncertainty": 14.770573598065289, "unilateral_faults": 2, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 62, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 62, "generated_at": "2026-07-01T00:15:48Z", "losses": 9, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-d51fce0298267f96", "rated_matches": 71, "raw_elo_rating": 1432.5748367505894, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 27.460519662064947, "uncertainty": 15.175565098878964, "unilateral_faults": 1, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 40, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 40, "generated_at": "2026-07-11T14:00:45Z", "losses": 7, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-6a361d88d8c1fb48", "rated_matches": 50, "raw_elo_rating": 1459.5233969442024, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 30.113556738553537, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 3 }, { "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": 17, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-97efd9455394f6d7", "rated_matches": 50, "raw_elo_rating": 1626.635475853018, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 54.63835083513168, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 33 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 3, "coverage_status": "rated", "distinct_rated_opponents": 24, "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": 48, "raw_elo_rating": 1549.0618224868374, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 43.08783058121371, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 28 } ] }, "full_freedom/intensive": { "GB2-01": [ { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 0, "generated_at": "2026-07-03T17:50:00Z", "losses": 24, "model": "claude-fable-5", "point_rating_method": "sequential_elo", "public_id": "E-8000131e469a8bb6", "rated_matches": 62, "raw_elo_rating": 1623.8224065469774, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 62.704408645378294, "uncertainty": 19.244078834871203, "unilateral_faults": 2, "wins": 38 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 8, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 8, "generated_at": "2026-07-03T17:20:00Z", "losses": 20, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-3308d2952452916e", "rated_matches": 66, "raw_elo_rating": 1599.7404917395845, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 59.935555530461315, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 38 }, { "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": 1814.056473405188, "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": 84.57587239799292, "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": 1471.6432199903884, "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": 42.540138172824065, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 78, "capped_draws": 15, "coverage_status": "rated", "distinct_rated_opponents": 39, "draws": 15, "generated_at": "2026-07-03T16:50:00Z", "losses": 19, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-5e353d79b07fa294", "rated_matches": 78, "raw_elo_rating": 1590.9475808519617, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 59.33049896491237, "uncertainty": 12.5043950463012, "unilateral_faults": 0, "wins": 44 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 20, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 20, "generated_at": "2026-07-02T16:51:45Z", "losses": 30, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-b9882650a0cde9ac", "rated_matches": 68, "raw_elo_rating": 1393.1716315858814, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 34.664092493110076, "uncertainty": 16.4429265428846, "unilateral_faults": 2, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 14, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 14, "generated_at": "2026-07-02T06:10:40Z", "losses": 26, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-cb8739e00cafec5b", "rated_matches": 64, "raw_elo_rating": 1500.5473654729128, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 47.66669797717743, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 14, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 14, "generated_at": "2026-07-02T16:51:45Z", "losses": 24, "model": "deepseek/deepseek-v4-pro", "point_rating_method": "sequential_elo", "public_id": "E-e192048d4eaa3c43", "rated_matches": 66, "raw_elo_rating": 1485.451431444242, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 45.905068931277405, "uncertainty": 17.33472217815261, "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": 62, "capped_draws": 7, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 7, "generated_at": "2026-07-02T16:51:45Z", "losses": 25, "model": "gpt-5", "point_rating_method": "sequential_elo", "public_id": "E-3e63b136f656e976", "rated_matches": 46, "raw_elo_rating": 1465.651346316106, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 42.3107717111968, "uncertainty": 29.182495748947275, "unilateral_faults": 8, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 2, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-5d8a6b14c27539ab", "rated_matches": 64, "raw_elo_rating": 1926.8421962372731, "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": 18.26736729460423, "unilateral_faults": 0, "wins": 62 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 8, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 8, "generated_at": "2026-07-02T06:10:40Z", "losses": 25, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-ca99b677101014a8", "rated_matches": 70, "raw_elo_rating": 1517.1215772809917, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 49.96443638296805, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 37 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 35, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 35, "generated_at": "2026-07-09T17:30:50Z", "losses": 20, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-db1fc33e2a2467d5", "rated_matches": 64, "raw_elo_rating": 1416.3463423379596, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 37.32991400433134, "uncertainty": 18.26736729460423, "unilateral_faults": 2, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 9, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 9, "generated_at": "2026-07-02T06:10:40Z", "losses": 48, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-fbb3f2dccb7c7fba", "rated_matches": 64, "raw_elo_rating": 1239.1718459938568, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 15.579412335586763, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 21, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 21, "generated_at": "2026-07-02T16:51:45Z", "losses": 12, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-8c61292c31db2722", "rated_matches": 64, "raw_elo_rating": 1738.5848065889888, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 76.88892728812435, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 31 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "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-luna", "point_rating_method": "sequential_elo", "public_id": "E-38187ed58fb76057", "rated_matches": 60, "raw_elo_rating": 1651.564129610822, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 66.009467280089, "uncertainty": 20.268439966447993, "unilateral_faults": 2, "wins": 40 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 17, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-9e683b3cd6c7f7c3", "rated_matches": 62, "raw_elo_rating": 1721.8625437609876, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 74.74012604307732, "uncertainty": 19.244078834871203, "unilateral_faults": 2, "wins": 45 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 13, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 13, "generated_at": "2026-07-10T05:30:29Z", "losses": 30, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-36d36f4895d90b11", "rated_matches": 62, "raw_elo_rating": 1444.5042092762435, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 40.69073946920973, "uncertainty": 19.244078834871203, "unilateral_faults": 2, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 6, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 6, "generated_at": "2026-07-02T16:51:45Z", "losses": 26, "model": "mistralai/mistral-medium-3-5", "point_rating_method": "sequential_elo", "public_id": "E-99c7b0d758665b66", "rated_matches": 36, "raw_elo_rating": 1297.9505795131518, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 20.813178268089132, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 1, "generated_at": "2026-07-17T22:36:00Z", "losses": 24, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-c89e5a24623ed70c", "rated_matches": 50, "raw_elo_rating": 1514.4057262201663, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "score": 48.58264022845683, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 16, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 16, "generated_at": "2026-07-17T22:36:00Z", "losses": 20, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-d2f6679f6ac952b3", "rated_matches": 50, "raw_elo_rating": 1467.5034498820974, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "score": 42.824768408249774, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 5, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 5, "generated_at": "2026-07-24T14:00:00Z", "losses": 18, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-dbb89dcf5242a5a0", "rated_matches": 44, "raw_elo_rating": 1529.9518155525486, "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": 50.047059085574304, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 9, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 9, "generated_at": "2026-07-11T17:22:09Z", "losses": 22, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-ce064a9927030b28", "rated_matches": 36, "raw_elo_rating": 1347.5257898660675, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 26.899187923876408, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 1, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 1, "generated_at": "2026-07-02T16:51:45Z", "losses": 32, "model": "stepfun/step-3.7-flash", "point_rating_method": "sequential_elo", "public_id": "E-4b0ce2bc67b08d8a", "rated_matches": 36, "raw_elo_rating": 1229.3525267234986, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 12.391864295359213, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 4, "coverage_status": "rated", "distinct_rated_opponents": 22, "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": 44, "raw_elo_rating": 1582.666949871878, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 56.51853574073472, "uncertainty": 30.785599249992988, "unilateral_faults": 6, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 5, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "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": 36, "raw_elo_rating": 1654.2401596445443, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 64.55241425921825, "uncertainty": 38.449493652678655, "unilateral_faults": 2, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 10, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 10, "generated_at": "2026-07-24T14:00:00Z", "losses": 6, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-1c8e452ede41ea2e", "rated_matches": 36, "raw_elo_rating": 1692.7204147120556, "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": 69.27637210490104, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 3, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "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": 36, "raw_elo_rating": 1610.216180559382, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 59.14789131536924, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 33, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 33, "generated_at": "2026-07-02T06:10:40Z", "losses": 13, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-8478c64d84536b61", "rated_matches": 48, "raw_elo_rating": 1293.44691203047, "reasoning": "highest", "reasoning_bracket": "highest", "reasoning_setting": "highest", "repair_status": "repaired", "score": 21.31811178953796, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 36, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 36, "generated_at": "2026-07-11T14:00:45Z", "losses": 14, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-5ab5088af70c19d6", "rated_matches": 64, "raw_elo_rating": 1461.622752883799, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 42.88818939640259, "uncertainty": 18.26736729460423, "unilateral_faults": 2, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 80, "capped_draws": 48, "coverage_status": "rated", "distinct_rated_opponents": 40, "draws": 48, "generated_at": "2026-07-03T18:27:00Z", "losses": 17, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-88bed07a2e526eed", "rated_matches": 80, "raw_elo_rating": 1516.6932618433234, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 50.28343725469852, "uncertainty": 11.805555555555554, "unilateral_faults": 0, "wins": 15 } ], "GB2-02": [ { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 27, "generated_at": "2026-07-03T17:50:00Z", "losses": 3, "model": "claude-fable-5", "point_rating_method": "sequential_elo", "public_id": "E-f6a30e7d9986c9b8", "rated_matches": 62, "raw_elo_rating": 1675.2224541849737, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 73.7853774932965, "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": 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": 60, "raw_elo_rating": 1746.8507510957204, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 90.47270926865744, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 37 }, { "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": 1660.854766399915, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 67.55387519409311, "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": 1747.9087192203456, "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": 88.06965895024113, "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": 1528.8802538058603, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 38.687839752916766, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 56, "generated_at": "2026-07-02T16:51:45Z", "losses": 8, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-12dcb25370550495", "rated_matches": 68, "raw_elo_rating": 1469.9439655992894, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 25.936030290732113, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 58, "generated_at": "2026-07-02T06:10:40Z", "losses": 7, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-f2e6dd87c5656ee3", "rated_matches": 68, "raw_elo_rating": 1491.4884345889675, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 31.01336052805069, "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-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": 1484.7600002274844, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 25.68130071513402, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 39, "generated_at": "2026-07-02T16:51:45Z", "losses": 7, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-4aa582caf9d9f6da", "rated_matches": 66, "raw_elo_rating": 1602.558018732674, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 57.0207132983657, "uncertainty": 17.33472217815261, "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": 1485.9681038721687, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 28.57484246757806, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 58, "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": 64, "raw_elo_rating": 1477.7748776841786, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 27.43755238319894, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 64, "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": 68, "raw_elo_rating": 1469.8136765250715, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 25.905325395826853, "uncertainty": 16.4429265428846, "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": 1495.0208034325651, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 32.30922247837311, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 66, "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": 72, "raw_elo_rating": 1471.706546099867, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 26.66670849023619, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "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": 60, "raw_elo_rating": 1787.2775916050075, "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": 45 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 41, "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": 64, "raw_elo_rating": 1554.51478910498, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 45.52265222263585, "uncertainty": 18.26736729460423, "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": 1492.9402178593853, "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": 27.981880405129896, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 24, "generated_at": "2026-07-18T00:14:00Z", "losses": 6, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-97d6a124a1509fc1", "rated_matches": 34, "raw_elo_rating": 1500.7329502647428, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "score": 28.6063748434055, "uncertainty": 40.76542547285167, "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": 1465.3469691951177, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "score": 20.267050641538766, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 35, "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": 42, "raw_elo_rating": 1468.6948724253036, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 22.61449070264951, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 31, "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": 36, "raw_elo_rating": 1474.5104940152412, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 22.863227052428083, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 30, "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": 34, "raw_elo_rating": 1449.166076833186, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 16.453740873013416, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 0 }, { "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": 5, "model": "tencent/hy3-preview", "point_rating_method": "sequential_elo", "public_id": "E-fbf6af15f65f01d7", "rated_matches": 34, "raw_elo_rating": 1439.0333836038849, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 14.065794818587444, "uncertainty": 40.76542547285167, "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": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 18, "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": 34, "raw_elo_rating": 1531.5155213105586, "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": 35.86082510756406, "uncertainty": 40.76542547285167, "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": 1499.4387882182075, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 28.301382963865, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 37, "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": 42, "raw_elo_rating": 1485.4236953036248, "reasoning": "highest", "reasoning_bracket": "highest", "reasoning_setting": "highest", "repair_status": "repaired", "score": 26.556929863045585, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 57, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 46, "generated_at": "2026-07-11T14:00:45Z", "losses": 8, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-4442c0e8a06187bf", "rated_matches": 57, "raw_elo_rating": 1476.956020516428, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 26.559093337903025, "uncertainty": 21.90321642986127, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 58, "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": 62, "raw_elo_rating": 1467.1991422445142, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 24.761052396750248, "uncertainty": 19.244078834871203, "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": 1498.8696729023943, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 32.031638978317616, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 7 } ], "GB2-03": [ { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 21, "generated_at": "2026-07-03T17:50:00Z", "losses": 4, "model": "claude-fable-5", "point_rating_method": "sequential_elo", "public_id": "E-04fa5b762ca703f0", "rated_matches": 44, "raw_elo_rating": 1646.2996143800208, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 69.97359637011016, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 19 }, { "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": 1828.7336971220263, "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": 1817.031961601465, "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": 98.04357117683936, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 36 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 18, "generated_at": "2026-07-19T15:25:00Z", "losses": 9, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-1c251b669239429c", "rated_matches": 42, "raw_elo_rating": 1578.2542907653385, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 58.367796890295175, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 3, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 12, "generated_at": "2026-07-03T16:50:00Z", "losses": 25, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-2e43b0d163a7f12d", "rated_matches": 40, "raw_elo_rating": 1320.2042410476315, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 14.97827962852532, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 2, "coverage_status": "rated", "distinct_rated_opponents": 25, "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": 50, "raw_elo_rating": 1545.5752895760347, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 53.738138920033414, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 22, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 11, "draws": 15, "generated_at": "2026-07-02T16:51:45Z", "losses": 3, "model": "google/gemini-3.5-flash", "point_rating_method": "sequential_elo", "public_id": "E-46c3bb79de67d970", "rated_matches": 22, "raw_elo_rating": 1516.880077333121, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 44.360414450649905, "uncertainty": 60.5072070285374, "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": 1450.1918496770988, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 32.89731675267175, "uncertainty": 62.850358177805205, "unilateral_faults": 1, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 7, "coverage_status": "rated", "distinct_rated_opponents": 23, "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": 46, "raw_elo_rating": 1461.2984840176907, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 39.257429797226955, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 3, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 15, "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": 50, "raw_elo_rating": 1421.5214998503109, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 32.99741978352148, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 2, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 21, "generated_at": "2026-07-02T16:51:45Z", "losses": 15, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-e53a932f820d9724", "rated_matches": 47, "raw_elo_rating": 1513.6863551335346, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 48.1183769229996, "uncertainty": 28.418783648703226, "unilateral_faults": 0, "wins": 11 }, { "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": 1405.5751168246516, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 29.94096545666281, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 5, "generated_at": "2026-07-10T05:30:29Z", "losses": 16, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-2ac4e83a1b9ba989", "rated_matches": 50, "raw_elo_rating": 1590.6444127760449, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 61.27330594787659, "uncertainty": 26.26400420140049, "unilateral_faults": 1, "wins": 29 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 22, "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": 44, "raw_elo_rating": 1555.6224588373111, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 54.81316137358737, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 22, "capped_draws": 2, "coverage_status": "under_covered", "distinct_rated_opponents": 11, "draws": 10, "generated_at": "2026-07-24T14:00:00Z", "losses": 6, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-c0c60ca46f3ce498", "rated_matches": 22, "raw_elo_rating": 1516.6952603309, "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": 44.329514648691465, "uncertainty": 60.5072070285374, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 21, "generated_at": "2026-07-19T14:50:00Z", "losses": 15, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-714519b339aeb2e2", "rated_matches": 58, "raw_elo_rating": 1552.4724697885567, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 55.549292457486665, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 22 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 8, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 23, "generated_at": "2026-07-11T15:43:48Z", "losses": 20, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-bd2653f21938737f", "rated_matches": 50, "raw_elo_rating": 1418.58964495931, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 32.50723904033177, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 7 } ], "GB2-04": [ { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "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": 58, "raw_elo_rating": 1828.795087741824, "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": 48 }, { "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": 1579.5576387423876, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 51.78950505760701, "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": 1643.6380792859509, "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": 61.68101057822674, "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": 1754.2494224092084, "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": 83.35574502807938, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 27 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 43, "generated_at": "2026-07-03T16:50:00Z", "losses": 9, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-8e980ad934b3251e", "rated_matches": 68, "raw_elo_rating": 1540.7026544738983, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 44.315516442451184, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 25, "generated_at": "2026-07-02T16:51:45Z", "losses": 20, "model": "deepseek/deepseek-v4-pro", "point_rating_method": "sequential_elo", "public_id": "E-38bc194a470fbf62", "rated_matches": 52, "raw_elo_rating": 1437.033942799334, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 22.67071339758295, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 20, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 10, "draws": 16, "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": 20, "raw_elo_rating": 1451.381288182883, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 19.144406619465567, "uncertainty": 65.3589451179962, "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": 1481.8176682330727, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 28.568318927201943, "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": 1467.4471341169822, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 24.84174288121968, "uncertainty": 49.09766908852594, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 28, "generated_at": "2026-07-02T16:51:45Z", "losses": 13, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-9279285adff8ed29", "rated_matches": 70, "raw_elo_rating": 1620.454608682286, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 60.07708164277407, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 41, "generated_at": "2026-07-02T06:10:40Z", "losses": 15, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-040a4b654fceeb0c", "rated_matches": 66, "raw_elo_rating": 1479.9001298332687, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 32.26121816995966, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 15, "generated_at": "2026-07-09T17:30:50Z", "losses": 24, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-3403c285ceec6345", "rated_matches": 70, "raw_elo_rating": 1529.549353889867, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 42.263833904463375, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 31 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 26, "generated_at": "2026-07-02T06:10:40Z", "losses": 24, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-bbf36865f2b7fe63", "rated_matches": 58, "raw_elo_rating": 1375.9421461186027, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 11.261657463283376, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 44, "generated_at": "2026-07-02T16:51:45Z", "losses": 13, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-64bf5daf186f8119", "rated_matches": 68, "raw_elo_rating": 1470.7482297231588, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 30.607667525230426, "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": 36, "generated_at": "2026-07-10T05:30:29Z", "losses": 18, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-e348813cda8b38b7", "rated_matches": 68, "raw_elo_rating": 1515.6939072556113, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 39.41495254390206, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 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": 1653.6598205873045, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 65.31698730595153, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 27, "generated_at": "2026-07-10T05:30:29Z", "losses": 13, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-b85c80e7475ef9ec", "rated_matches": 60, "raw_elo_rating": 1564.0392200957288, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 48.288709971644074, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 17, "generated_at": "2026-07-17T22:36:00Z", "losses": 8, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-2a7239d6b25916b0", "rated_matches": 34, "raw_elo_rating": 1527.691200643713, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "score": 37.952997454116975, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 11, "generated_at": "2026-07-24T14:00:00Z", "losses": 8, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-601725df2c678708", "rated_matches": 34, "raw_elo_rating": 1566.4219216942895, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "score": 45.54243692857585, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 10, "generated_at": "2026-07-17T22:36:00Z", "losses": 10, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-6f3da6d3b01bcfad", "rated_matches": 34, "raw_elo_rating": 1536.1330457194156, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "score": 39.60721071214382, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 27, "generated_at": "2026-07-11T17:22:09Z", "losses": 6, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-958dea26b779a042", "rated_matches": 34, "raw_elo_rating": 1446.8683525897754, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 22.115437583807967, "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": 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": 1458.718033081689, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 24.43742980201681, "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": 1435.454832644688, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 15.145849175849548, "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": 1491.7333881559198, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 30.906920487109797, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 28, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 14, "draws": 18, "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": 28, "raw_elo_rating": 1413.645049227228, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 14.299009469743243, "uncertainty": 49.09766908852594, "unilateral_faults": 0, "wins": 1 }, { "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": 1464.0149828787098, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 21.620029552164407, "uncertainty": 65.3589451179962, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 34, "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": 44, "raw_elo_rating": 1495.3820186822695, "reasoning": "highest", "reasoning_bracket": "highest", "reasoning_setting": "highest", "repair_status": "repaired", "score": 33.18635365584194, "uncertainty": 30.785599249992988, "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": 1516.0566774459735, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 40.213007904288595, "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": 1437.9506430561107, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 22.641265916399533, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 9 } ], "GB2-05": [ { "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": "claude-fable-5", "point_rating_method": "sequential_elo", "public_id": "E-5aa4402ccce7b855", "rated_matches": 66, "raw_elo_rating": 1911.0343695647828, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 93.05084396084196, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 58 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 40, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-6774d700e60de31a", "rated_matches": 70, "raw_elo_rating": 1537.5424446121715, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 51.146338598706805, "uncertainty": 15.58908290969266, "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": "2026-07-25T10:50:00Z", "losses": 0, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-3f3686d02d1503fa", "rated_matches": 40, "raw_elo_rating": 1986.3418503572475, "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": 1748.5260593214266, "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": 73.21774811489999, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 80, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 40, "draws": 0, "generated_at": "2026-07-03T16:50:00Z", "losses": 41, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-c902807aab849f31", "rated_matches": 80, "raw_elo_rating": 1548.872594045111, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 52.76318675006037, "uncertainty": 11.805555555555554, "unilateral_faults": 0, "wins": 39 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 59, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-b306c8f5ffbbec38", "rated_matches": 72, "raw_elo_rating": 1273.5353446820234, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 21.48822632188929, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 13 }, { "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": 32, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-b3d889b0631db85f", "rated_matches": 78, "raw_elo_rating": 1554.0311357346932, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 53.28116819334009, "uncertainty": 12.5043950463012, "unilateral_faults": 0, "wins": 46 }, { "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": 24, "model": "deepseek/deepseek-v4-pro", "point_rating_method": "sequential_elo", "public_id": "E-0ca4798825ceaccb", "rated_matches": 76, "raw_elo_rating": 1770.1139868621165, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 77.55050909177413, "uncertainty": 13.230288229818967, "unilateral_faults": 0, "wins": 52 }, { "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": 36, "model": "google/gemini-3.1-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-a72dd193e1dc4331", "rated_matches": 40, "raw_elo_rating": 1220.515329898098, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 13.754428661395163, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 22, "model": "google/gemini-3.5-flash", "point_rating_method": "sequential_elo", "public_id": "E-b50da126631c1ea1", "rated_matches": 42, "raw_elo_rating": 1449.780390545928, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 39.73927406715561, "uncertainty": 32.49928516630233, "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": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "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": 42, "raw_elo_rating": 1659.4999295403002, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 63.35739250290029, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 28 }, { "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": 4, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-f6403f7a30e19e82", "rated_matches": 66, "raw_elo_rating": 1949.760418649385, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 97.41208001073208, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 62 }, { "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": 39, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-481582e8f8e3217e", "rated_matches": 74, "raw_elo_rating": 1562.7396128928744, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 54.1285000853822, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 35 }, { "admitted_plugin_count": 1, "attempted_matches": 88, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 44, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 46, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-95d1a872f51b78e7", "rated_matches": 88, "raw_elo_rating": 1458.205063342578, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 42.782673944191146, "uncertainty": 9.249894000318006, "unilateral_faults": 0, "wins": 42 }, { "admitted_plugin_count": 1, "attempted_matches": 73, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 37, "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": 73, "raw_elo_rating": 1586.2542378517353, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 56.741633620377705, "uncertainty": 14.373819371909642, "unilateral_faults": 0, "wins": 38 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 0, "generated_at": "2026-07-09T17:30:50Z", "losses": 27, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-b05a7e0987de9967", "rated_matches": 72, "raw_elo_rating": 1685.5719142551734, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 67.89081020463259, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 45 }, { "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": 17, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-762e9d80a60b41ed", "rated_matches": 72, "raw_elo_rating": 1833.5200064511591, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 84.55237440881977, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 55 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 33, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-25a83ddaeb1268a4", "rated_matches": 72, "raw_elo_rating": 1586.9806489073471, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 56.78769509728259, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 39 }, { "admitted_plugin_count": 1, "attempted_matches": 80, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 40, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 25, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-af9c2c2998294ad0", "rated_matches": 80, "raw_elo_rating": 1726.1579161055558, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 72.72864039076802, "uncertainty": 11.805555555555554, "unilateral_faults": 0, "wins": 55 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 26, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-012ecb9ce0709c05", "rated_matches": 72, "raw_elo_rating": 1634.0374245901774, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 62.08711787214945, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 46 }, { "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": "mistralai/mistral-medium-3-5", "point_rating_method": "sequential_elo", "public_id": "E-1954b83d439b455c", "rated_matches": 42, "raw_elo_rating": 1179.3522444981809, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 9.284295898021144, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "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": 56, "raw_elo_rating": 1515.7955265246053, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "score": 48.07672580576763, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugin_count": 1, "attempted_matches": 47, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 0, "generated_at": "2026-07-17T22:08:39Z", "losses": 21, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-95ac38f534c0080f", "rated_matches": 47, "raw_elo_rating": 1509.7234507830926, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "score": 46.85754887233867, "uncertainty": 28.418783648703226, "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": "2026-07-02T16:51:45Z", "losses": 34, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-48ed5c5e00ef38fb", "rated_matches": 42, "raw_elo_rating": 1277.3343405722885, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 20.31880780262193, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 0, "generated_at": "2026-07-11T17:22:09Z", "losses": 28, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-da3b98638ff53ea9", "rated_matches": 42, "raw_elo_rating": 1340.928743214023, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 27.48065900945308, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 0, "generated_at": "2026-07-03T16:00:00Z", "losses": 28, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-4fc62dc65156d576", "rated_matches": 52, "raw_elo_rating": 1450.5284147399018, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 40.5054373719154, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 24 }, { "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": 24, "model": "stepfun/step-3.7-flash", "point_rating_method": "sequential_elo", "public_id": "E-358338a9fbdbcb6a", "rated_matches": 42, "raw_elo_rating": 1468.455994851599, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 41.84247645099394, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 0, "generated_at": "2026-07-03T19:10:00Z", "losses": 23, "model": "tencent/hy3-preview", "point_rating_method": "sequential_elo", "public_id": "E-92dc0ac61d798488", "rated_matches": 52, "raw_elo_rating": 1489.1164768211524, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 44.85113365186623, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 29 }, { "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": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 0, "generated_at": "2026-07-18T00:06:00Z", "losses": 21, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-87d1c39ddc685d7b", "rated_matches": 42, "raw_elo_rating": 1549.543321271408, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 50.97433935801821, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 0, "generated_at": "2026-07-18T00:06:00Z", "losses": 25, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-bd7fcc801178eba2", "rated_matches": 54, "raw_elo_rating": 1518.5692090151308, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 48.28157590668977, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 29 }, { "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": 42, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-235e4beedf22bc99", "rated_matches": 76, "raw_elo_rating": 1576.055795890647, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 55.69613462686788, "uncertainty": 13.230288229818967, "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": 43, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-503ecd021099d8f9", "rated_matches": 70, "raw_elo_rating": 1411.5878999859724, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 36.96163570089199, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 27 }, { "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": 33, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-51c8f79c1671819e", "rated_matches": 76, "raw_elo_rating": 1570.0501335274976, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 55.01979113661367, "uncertainty": 13.230288229818967, "unilateral_faults": 0, "wins": 43 } ], "GB2-06": [ { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "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": 60, "raw_elo_rating": 1718.7719507864515, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 81.83872215206208, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 40 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "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": 58, "raw_elo_rating": 1716.028915302819, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 81.37204287643961, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 39 }, { "admitted_plugin_count": 1, "attempted_matches": 90, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 45, "draws": 10, "generated_at": "2026-07-03T16:50:00Z", "losses": 39, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-51f3682dc3b76107", "rated_matches": 90, "raw_elo_rating": 1502.9657308011708, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 55.09510200081964, "uncertainty": 8.664241836095918, "unilateral_faults": 0, "wins": 41 }, { "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": 48, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-5f5fd61f4544b8d7", "rated_matches": 70, "raw_elo_rating": 1304.3081774256607, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 28.65261343605491, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 22 }, { "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": 45, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-f527097ad30176f4", "rated_matches": 62, "raw_elo_rating": 1329.244669375893, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 31.50311534300162, "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": 2, "generated_at": "2026-07-02T16:51:45Z", "losses": 36, "model": "deepseek/deepseek-v4-pro", "point_rating_method": "sequential_elo", "public_id": "E-c9778645f1bbd12c", "rated_matches": 64, "raw_elo_rating": 1411.0223538755488, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 42.19407690153233, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 37, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 32, "model": "google/gemini-3.1-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-6238c7d8dc9e77d9", "rated_matches": 37, "raw_elo_rating": 1259.0217150803967, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 20.53280700393271, "uncertainty": 37.360710565381275, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "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": 38, "raw_elo_rating": 1632.226637510412, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 68.96930081774572, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 21 }, { "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": 46, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 23, "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": 46, "raw_elo_rating": 1599.685910965938, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 65.49425022506708, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "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": 56, "raw_elo_rating": 1795.1084078077092, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 91.4951323889829, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 39 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 9, "generated_at": "2026-07-02T06:10:40Z", "losses": 17, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-0b7e07d12feb8fb5", "rated_matches": 70, "raw_elo_rating": 1658.2754812633734, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 74.48951038736966, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 44 }, { "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": 44, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-eca073d7ce610515", "rated_matches": 68, "raw_elo_rating": 1442.576048285256, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 46.46911808434478, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "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": 58, "raw_elo_rating": 1706.2621455889364, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 80.10729776560946, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 8, "generated_at": "2026-07-02T16:51:45Z", "losses": 20, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-4175a77ccf4c269b", "rated_matches": 70, "raw_elo_rating": 1740.1552092126217, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 85.09250284379188, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 42 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 13, "generated_at": "2026-07-10T05:30:29Z", "losses": 16, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-9eafeacabdedfdba", "rated_matches": 60, "raw_elo_rating": 1693.5550142801062, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 78.57326201623226, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 31 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "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": 58, "raw_elo_rating": 1692.6757781194096, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 78.34793491234177, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 31 }, { "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": 1645.4373743096698, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 73.14660395348105, "uncertainty": 12.5043950463012, "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": 31, "model": "mistralai/mistral-medium-3-5", "point_rating_method": "sequential_elo", "public_id": "E-6c35f5ff426e7ada", "rated_matches": 38, "raw_elo_rating": 1276.7474041824191, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 22.93661698020659, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "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": 38, "raw_elo_rating": 1688.0709353285413, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "score": 76.20084253545677, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 27 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 4, "generated_at": "2026-07-17T22:36:00Z", "losses": 13, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-3f2124a8621f4c67", "rated_matches": 40, "raw_elo_rating": 1603.2184180725008, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "score": 65.41771870952734, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 37, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 2, "generated_at": "2026-07-11T17:22:09Z", "losses": 21, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-ba2fb1c121873708", "rated_matches": 37, "raw_elo_rating": 1419.633107652117, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 41.331134337274186, "uncertainty": 37.360710565381275, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 4, "generated_at": "2026-07-03T16:00:00Z", "losses": 17, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-4162fe183e6383e1", "rated_matches": 38, "raw_elo_rating": 1458.9852716129876, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 46.53545862314014, "uncertainty": 36.31407690254356, "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": 1545.5402070118414, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 59.053740144696384, "uncertainty": 23.66998624632421, "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": "2026-07-02T16:51:45Z", "losses": 26, "model": "stepfun/step-3.7-flash", "point_rating_method": "sequential_elo", "public_id": "E-2d684425ca56be18", "rated_matches": 38, "raw_elo_rating": 1364.8232167706008, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 34.341969682948694, "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": 33, "model": "tencent/hy3-preview", "point_rating_method": "sequential_elo", "public_id": "E-3627e3dbf7a48738", "rated_matches": 38, "raw_elo_rating": 1240.6039192958517, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 18.256226519717732, "uncertainty": 36.31407690254356, "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": 48, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 4, "generated_at": "2026-07-24T14:00:00Z", "losses": 25, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-5a1e23bce371a184", "rated_matches": 48, "raw_elo_rating": 1466.526062035418, "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": 48.40655306031008, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "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": 56, "raw_elo_rating": 1572.8669502398702, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 62.71603703638642, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 31 }, { "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": 1479.2712311236176, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 49.55757958350315, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 7, "generated_at": "2026-07-02T06:10:40Z", "losses": 20, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-51421c7ae2af8f7b", "rated_matches": 46, "raw_elo_rating": 1510.9452000729912, "reasoning": "highest", "reasoning_bracket": "highest", "reasoning_setting": "highest", "repair_status": "repaired", "score": 54.00279670242382, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "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": 56, "raw_elo_rating": 1641.3436578799765, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 71.58340912876453, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 33 } ], "GB2-07": [ { "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": 26, "model": "claude-fable-5", "point_rating_method": "sequential_elo", "public_id": "E-babd82321b910e7b", "rated_matches": 66, "raw_elo_rating": 1607.2707269530913, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 61.74570340856937, "uncertainty": 17.33472217815261, "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": "2026-07-03T17:20:00Z", "losses": 21, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-5e09cecd1172d99b", "rated_matches": 60, "raw_elo_rating": 1641.587990360725, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 65.67069489296186, "uncertainty": 20.268439966447993, "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": 1, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-1e882072d8d97548", "rated_matches": 40, "raw_elo_rating": 1916.2342017734409, "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": 98.00725670704736, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 39 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 0, "generated_at": "2026-07-03T16:50:00Z", "losses": 42, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-2146a36b46e938d6", "rated_matches": 70, "raw_elo_rating": 1408.057840072436, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 37.459792671933386, "uncertainty": 15.58908290969266, "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": "2026-07-02T06:10:40Z", "losses": 40, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-20285efe5ad468c1", "rated_matches": 68, "raw_elo_rating": 1403.9709488893493, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 36.87418407205407, "uncertainty": 16.4429265428846, "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": 27, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-ecf2a6ea6f9fe06c", "rated_matches": 64, "raw_elo_rating": 1602.0602420013795, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 61.01441166930439, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 37 }, { "admitted_plugin_count": 1, "attempted_matches": 86, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 43, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 46, "model": "deepseek/deepseek-v4-pro", "point_rating_method": "sequential_elo", "public_id": "E-f398fd6ac8c8bada", "rated_matches": 86, "raw_elo_rating": 1579.7533840085564, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 59.10196667088018, "uncertainty": 9.855626741889738, "unilateral_faults": 0, "wins": 40 }, { "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": 30, "model": "google/gemini-3.1-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-0d43f308cfa4da52", "rated_matches": 42, "raw_elo_rating": 1371.4066804602294, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 31.29927882215666, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 12 }, { "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": 21, "model": "google/gemini-3.5-flash", "point_rating_method": "sequential_elo", "public_id": "E-f7f306cca2bb9532", "rated_matches": 42, "raw_elo_rating": 1620.9930296932216, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 61.9409877518634, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 21 }, { "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": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 29, "model": "gpt-5", "point_rating_method": "sequential_elo", "public_id": "E-15dad0db253c0497", "rated_matches": 56, "raw_elo_rating": 1513.9390847536845, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 49.78236406777454, "uncertainty": 22.47661785325219, "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": "2026-07-02T16:51:45Z", "losses": 6, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-80aa3ec3ac4ad97f", "rated_matches": 68, "raw_elo_rating": 1856.3853633771, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 92.41708874989084, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 62 }, { "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": 22, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-1b33882368041bb3", "rated_matches": 66, "raw_elo_rating": 1626.8346327510485, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 64.14756356170453, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 44 }, { "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": 31, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-e453890c6dd35fa3", "rated_matches": 70, "raw_elo_rating": 1673.8683195169865, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 70.0933376019181, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 39 }, { "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": 32, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-b9e3f57bc887c6ae", "rated_matches": 70, "raw_elo_rating": 1621.1065450200133, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 63.61577606171604, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 38 }, { "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": 43, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-e0e874b71d913c12", "rated_matches": 68, "raw_elo_rating": 1351.6091494472687, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 30.445727457857856, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 25 }, { "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": 8, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-6201278165db862a", "rated_matches": 70, "raw_elo_rating": 1830.6078371029448, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 89.33624367595237, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 62 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 23, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-73a7b73c1df452ad", "rated_matches": 60, "raw_elo_rating": 1633.1851088462413, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 64.63907337067556, "uncertainty": 20.268439966447993, "unilateral_faults": 1, "wins": 37 }, { "admitted_plugin_count": 1, "attempted_matches": 92, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 46, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 30, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-1b522c9c14f3860c", "rated_matches": 92, "raw_elo_rating": 1579.5870696464758, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 59.254216074642976, "uncertainty": 8.09758473652126, "unilateral_faults": 0, "wins": 62 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 28, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-65bf9818e3e1b632", "rated_matches": 72, "raw_elo_rating": 1698.0816425356322, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 73.14639726550367, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 44 }, { "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": 42, "model": "mistralai/mistral-medium-3-5", "point_rating_method": "sequential_elo", "public_id": "E-d0d0df9d83b6e37e", "rated_matches": 42, "raw_elo_rating": 1137.8670302315995, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 2.6276226685145265, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 25, "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": 50, "raw_elo_rating": 1584.61656565071, "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": 58.08745451776987, "uncertainty": 26.26400420140049, "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": "2026-07-17T22:36:00Z", "losses": 27, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-49105fbc7f72e6fe", "rated_matches": 54, "raw_elo_rating": 1544.0348616044523, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "score": 53.36001388500844, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 27 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 0, "generated_at": "2026-07-17T22:36:00Z", "losses": 21, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-77d9c422124dcbfe", "rated_matches": 48, "raw_elo_rating": 1479.9441320255862, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "score": 45.09788974446648, "uncertainty": 27.67857142857143, "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": "2026-07-03T16:00:00Z", "losses": 30, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-312d25e3a9eeeee3", "rated_matches": 42, "raw_elo_rating": 1333.288936469953, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 26.619564486831397, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 12 }, { "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": 30, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-29bc7f4fdf0f7b14", "rated_matches": 42, "raw_elo_rating": 1331.052671295428, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 26.3450182755582, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 12 }, { "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": 34, "model": "stepfun/step-3.7-flash", "point_rating_method": "sequential_elo", "public_id": "E-6a5e44fe2dde4257", "rated_matches": 42, "raw_elo_rating": 1270.3439970507015, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 18.891816081480037, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 8 }, { "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": 31, "model": "tencent/hy3-preview", "point_rating_method": "sequential_elo", "public_id": "E-dfed1e345a939bcd", "rated_matches": 42, "raw_elo_rating": 1312.6965015166088, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 24.09143183881845, "uncertainty": 32.49928516630233, "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": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "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-0929811cef80813b", "rated_matches": 42, "raw_elo_rating": 1486.9924022493417, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 45.48973456773819, "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": 0, "generated_at": "2026-07-24T14:00:00Z", "losses": 28, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-436a3933a93e10cd", "rated_matches": 54, "raw_elo_rating": 1579.7204087357854, "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": 57.74112748178963, "uncertainty": 23.66998624632421, "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": 14, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-8e7f3829f3e45642", "rated_matches": 42, "raw_elo_rating": 1695.9832479560628, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 71.14753469502215, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 82, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 41, "draws": 0, "generated_at": "2026-07-11T14:00:45Z", "losses": 32, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-c81741d135c9dc9c", "rated_matches": 82, "raw_elo_rating": 1578.724896071838, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 58.85032622224363, "uncertainty": 11.132129994845172, "unilateral_faults": 0, "wins": 50 }, { "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": 29, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-cb438d112c0ea172", "rated_matches": 64, "raw_elo_rating": 1539.7607316995222, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 53.36590257816522, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 35 }, { "admitted_plugin_count": 1, "attempted_matches": 92, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 46, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 43, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-d96269dd04d644e0", "rated_matches": 92, "raw_elo_rating": 1604.195460142954, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 62.27538746938836, "uncertainty": 8.09758473652126, "unilateral_faults": 0, "wins": 49 } ], "GB2-08": [ { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 35, "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": 70, "raw_elo_rating": 1927.1900602587184, "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": 15.58908290969266, "unilateral_faults": 0, "wins": 65 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "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": 70, "raw_elo_rating": 1701.9428640249134, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 66.94349597864887, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 50 }, { "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": 1802.7270448826368, "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": 79.53314592026378, "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": 1590.1043440935753, "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": 48.32936944187184, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugin_count": 1, "attempted_matches": 86, "capped_draws": 48, "coverage_status": "rated", "distinct_rated_opponents": 43, "draws": 48, "generated_at": "2026-07-03T16:50:00Z", "losses": 28, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-b5805acb90227d50", "rated_matches": 86, "raw_elo_rating": 1466.5948946196706, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 33.07777506796782, "uncertainty": 9.855626741889738, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 50, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 50, "generated_at": "2026-07-02T16:51:45Z", "losses": 16, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-a7310645c3b96434", "rated_matches": 70, "raw_elo_rating": 1421.8047486009973, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 25.83138939583402, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 54, "coverage_status": "rated", "distinct_rated_opponents": 37, "draws": 54, "generated_at": "2026-07-02T16:51:45Z", "losses": 14, "model": "deepseek/deepseek-v4-pro", "point_rating_method": "sequential_elo", "public_id": "E-3a5b5c4507a989d3", "rated_matches": 74, "raw_elo_rating": 1431.6177940617447, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 27.45984279953629, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 31, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 31, "generated_at": "2026-07-02T16:51:45Z", "losses": 8, "model": "google/gemini-3.1-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-b335c9f92035f80b", "rated_matches": 42, "raw_elo_rating": 1404.8828757455797, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 21.362647009504503, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 29, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 29, "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": 42, "raw_elo_rating": 1368.1960198159356, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 15.978610178652271, "uncertainty": 32.49928516630233, "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": 1418.548656749578, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 23.368190040746796, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 17, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 17, "generated_at": "2026-07-02T16:51:45Z", "losses": 28, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-ddc1f3e68bf1e74a", "rated_matches": 72, "raw_elo_rating": 1532.2005706493428, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 42.12879794049859, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 27 }, { "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": 30, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-1e5d07fc67fd8710", "rated_matches": 70, "raw_elo_rating": 1547.462785687673, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 44.272530851637754, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 84, "capped_draws": 48, "coverage_status": "rated", "distinct_rated_opponents": 42, "draws": 48, "generated_at": "2026-07-02T06:10:40Z", "losses": 24, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-b63acb1096519102", "rated_matches": 84, "raw_elo_rating": 1430.2312733062938, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 27.667563389281582, "uncertainty": 10.482614454664043, "unilateral_faults": 0, "wins": 12 }, { "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": 15, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-98e55f26cfe52488", "rated_matches": 74, "raw_elo_rating": 1764.5695291816269, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 76.32269461271417, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 59 }, { "admitted_plugin_count": 1, "attempted_matches": 84, "capped_draws": 66, "coverage_status": "rated", "distinct_rated_opponents": 42, "draws": 66, "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": 84, "raw_elo_rating": 1428.5388283371356, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 27.419185984970532, "uncertainty": 10.482614454664043, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 49, "coverage_status": "rated", "distinct_rated_opponents": 37, "draws": 49, "generated_at": "2026-07-09T17:30:50Z", "losses": 18, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-bb4437fab8180bfc", "rated_matches": 74, "raw_elo_rating": 1418.331238451975, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 25.509953583208976, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 11, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 11, "generated_at": "2026-07-02T16:51:45Z", "losses": 16, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-3e859a6b27767128", "rated_matches": 72, "raw_elo_rating": 1701.0119250403293, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 66.90297186399128, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 45 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 5, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 5, "generated_at": "2026-07-10T05:30:29Z", "losses": 31, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-0fb7de4e8156a229", "rated_matches": 72, "raw_elo_rating": 1553.7066794269651, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 45.28496051733778, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 36 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 12, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 12, "generated_at": "2026-07-10T05:30:29Z", "losses": 36, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-3ae62f195160add3", "rated_matches": 68, "raw_elo_rating": 1353.9117026482218, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 15.76739369307706, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 78, "capped_draws": 11, "coverage_status": "rated", "distinct_rated_opponents": 39, "draws": 11, "generated_at": "2026-07-10T05:30:29Z", "losses": 35, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-b061663dc342c859", "rated_matches": 78, "raw_elo_rating": 1553.7992605242216, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 45.56460865855579, "uncertainty": 12.5043950463012, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 27, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 27, "generated_at": "2026-07-18T00:14:00Z", "losses": 13, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-134262cb96978830", "rated_matches": 42, "raw_elo_rating": 1374.9431805127113, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "score": 16.968800282835204, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 33, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 33, "generated_at": "2026-07-17T22:36:00Z", "losses": 22, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-b06cbc77b01de3b3", "rated_matches": 58, "raw_elo_rating": 1406.253121311441, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "score": 22.873375095707896, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 31, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 31, "generated_at": "2026-07-11T17:22:09Z", "losses": 19, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-2e3c01d0103fc439", "rated_matches": 56, "raw_elo_rating": 1409.4549137422746, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 23.210337339298093, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 6 }, { "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": 10, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-8c24e8bcbe9b1228", "rated_matches": 44, "raw_elo_rating": 1412.289677044104, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 22.650839422411963, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 1, "generated_at": "2026-07-03T16:00:00Z", "losses": 15, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-1b6fc7dfefb8cea4", "rated_matches": 42, "raw_elo_rating": 1645.8312203928197, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 56.72339758462758, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 33, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 33, "generated_at": "2026-07-02T16:51:45Z", "losses": 12, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-24a75273941e6ea3", "rated_matches": 50, "raw_elo_rating": 1408.5321189990236, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 22.630252117531743, "uncertainty": 26.26400420140049, "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": 1421.6753565476383, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 24.028249474298484, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 9, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 9, "generated_at": "2026-07-02T16:51:45Z", "losses": 24, "model": "tencent/hy3-preview", "point_rating_method": "sequential_elo", "public_id": "E-81a5e5ef15f371dc", "rated_matches": 48, "raw_elo_rating": 1406.755628453984, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 22.203462855600293, "uncertainty": 27.67857142857143, "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": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "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": 42, "raw_elo_rating": 1660.0254682005177, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 58.80649658688188, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 29 }, { "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": 10, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-60939cc4ea338b18", "rated_matches": 42, "raw_elo_rating": 1689.9450884674038, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 63.19739718057012, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 32 }, { "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": 4, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-707dd709e358a173", "rated_matches": 42, "raw_elo_rating": 1803.6901754826108, "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": 79.89023504579376, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 38 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 43, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 43, "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": 50, "raw_elo_rating": 1434.926356676387, "reasoning": "highest", "reasoning_bracket": "highest", "reasoning_setting": "highest", "repair_status": "repaired", "score": 26.503779684181723, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "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": 68, "raw_elo_rating": 1718.6715254627495, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 69.29829108626797, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 45 }, { "admitted_plugin_count": 1, "attempted_matches": 76, "capped_draws": 62, "coverage_status": "rated", "distinct_rated_opponents": 38, "draws": 62, "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": 76, "raw_elo_rating": 1401.0941966464954, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 23.068914880209483, "uncertainty": 13.230288229818967, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 32, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 32, "generated_at": "2026-07-02T16:51:45Z", "losses": 32, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-bc28f817090c9f60", "rated_matches": 66, "raw_elo_rating": 1295.7349020863935, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 7.124864990950522, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 2 } ] }, "full_freedom/mixed": { "GB2-01": [ { "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": 20, "model": "claude-fable-5", "point_rating_method": "sequential_elo", "public_id": "E-2dbc6efbd7db03b5", "rated_matches": 60, "raw_elo_rating": 1683.5740198568387, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 69.93910267106604, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 40 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 0, "generated_at": "2026-07-03T17:50:00Z", "losses": 24, "model": "claude-fable-5", "point_rating_method": "sequential_elo", "public_id": "E-8000131e469a8bb6", "rated_matches": 62, "raw_elo_rating": 1623.8224065469774, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 62.704408645378294, "uncertainty": 19.244078834871203, "unilateral_faults": 2, "wins": 38 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 42, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 42, "generated_at": "2026-07-02T16:51:45Z", "losses": 15, "model": "claude-opus-4-5", "point_rating_method": "sequential_elo", "public_id": "E-2e3eca63f7980fac", "rated_matches": 68, "raw_elo_rating": 1424.8775888544635, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 38.55641611027493, "uncertainty": 16.4429265428846, "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": "2026-07-02T16:51:45Z", "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": 40, "capped_draws": 5, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 5, "losses": 14, "model": "claude-opus-4-5", "point_rating_method": "sequential_elo", "public_id": "E-5b675f86b98132f4", "rated_matches": 36, "raw_elo_rating": 1541.9987824213997, "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": 50.77330771189236, "uncertainty": 38.449493652678655, "unilateral_faults": 2, "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-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": 34, "capped_draws": 6, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 6, "losses": 13, "model": "claude-opus-4-5", "point_rating_method": "sequential_elo", "public_id": "E-829b603611fbdcef", "rated_matches": 34, "raw_elo_rating": 1544.0068769965058, "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": 50.79237886118905, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 9, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 9, "generated_at": "2026-07-02T16:51:45Z", "losses": 26, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-13ec9509bc80f2bf", "rated_matches": 58, "raw_elo_rating": 1487.721422135228, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 45.78994213262309, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 8, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 8, "generated_at": "2026-07-03T17:20:00Z", "losses": 20, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-3308d2952452916e", "rated_matches": 66, "raw_elo_rating": 1599.7404917395845, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 59.935555530461315, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 38 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 17, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 17, "generated_at": "2026-07-02T16:51:45Z", "losses": 20, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-757a6149e87d8b53", "rated_matches": 66, "raw_elo_rating": 1588.3444361805764, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 58.53653969822832, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 5, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 5, "generated_at": "2026-07-25T15:48:00Z", "losses": 18, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-0437af9582860271", "rated_matches": 54, "raw_elo_rating": 1555.9230220837762, "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": 53.9341946903938, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 31 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 38, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 38, "generated_at": "2026-07-25T15:48:00Z", "losses": 5, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-6c30dc38efb07e9e", "rated_matches": 54, "raw_elo_rating": 1538.9118776023718, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 51.845852778522705, "uncertainty": 23.66998624632421, "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": 1814.056473405188, "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": 84.57587239799292, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 31 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 12, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 12, "generated_at": "2026-07-25T15:48:00Z", "losses": 9, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-865d68ab219fd7ee", "rated_matches": 56, "raw_elo_rating": 1808.7368464219276, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 85.08762089462937, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 35 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 2, "coverage_status": "rated", "distinct_rated_opponents": 27, "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": 54, "raw_elo_rating": 1703.84709742756, "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": 72.09382214243796, "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": "2026-07-25T15:48:00Z", "losses": 21, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-bf06fe9df8858291", "rated_matches": 40, "raw_elo_rating": 1471.6432199903884, "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": 42.540138172824065, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 78, "capped_draws": 15, "coverage_status": "rated", "distinct_rated_opponents": 39, "draws": 15, "generated_at": "2026-07-03T16:50:00Z", "losses": 19, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-5e353d79b07fa294", "rated_matches": 78, "raw_elo_rating": 1590.9475808519617, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 59.33049896491237, "uncertainty": 12.5043950463012, "unilateral_faults": 0, "wins": 44 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 12, "coverage_status": "rated", "distinct_rated_opponents": 25, "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": 50, "raw_elo_rating": 1596.8207633735929, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 58.70017091218334, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 8, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 8, "generated_at": "2026-07-02T16:51:45Z", "losses": 26, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-cd50a27a6bb44b58", "rated_matches": 66, "raw_elo_rating": 1453.4311708784803, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 41.974160447041655, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugin_count": 1, "attempted_matches": 86, "capped_draws": 49, "coverage_status": "rated", "distinct_rated_opponents": 43, "draws": 49, "generated_at": "2026-07-02T16:51:45Z", "losses": 20, "model": "cohere/north-mini-code", "point_rating_method": "sequential_elo", "public_id": "E-194759b182ce3244", "rated_matches": 86, "raw_elo_rating": 1466.6454782536298, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 44.33091655722825, "uncertainty": 9.855626741889738, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 18, "coverage_status": "rated", "distinct_rated_opponents": 37, "draws": 18, "generated_at": "2026-07-11T17:22:09Z", "losses": 53, "model": "cohere/north-mini-code", "point_rating_method": "sequential_elo", "public_id": "E-c309b463b29efb71", "rated_matches": 74, "raw_elo_rating": 1192.0965559736162, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 10.220871729896173, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 20, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 20, "generated_at": "2026-07-02T16:51:45Z", "losses": 30, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-b9882650a0cde9ac", "rated_matches": 68, "raw_elo_rating": 1393.1716315858814, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 34.664092493110076, "uncertainty": 16.4429265428846, "unilateral_faults": 2, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 78, "capped_draws": 26, "coverage_status": "rated", "distinct_rated_opponents": 39, "draws": 26, "generated_at": "2026-07-02T06:10:40Z", "losses": 23, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-c4c43ee3f29394f8", "rated_matches": 78, "raw_elo_rating": 1489.855662825924, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 46.92013530031653, "uncertainty": 12.5043950463012, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 14, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 14, "generated_at": "2026-07-02T06:10:40Z", "losses": 26, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-cb8739e00cafec5b", "rated_matches": 64, "raw_elo_rating": 1500.5473654729128, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 47.66669797717743, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 26, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 26, "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": 48, "raw_elo_rating": 1352.8818752557147, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 28.61453589959575, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 8, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 8, "generated_at": "2026-07-01T00:15:48Z", "losses": 25, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-fd9da5310ad15cac", "rated_matches": 54, "raw_elo_rating": 1620.8077045088708, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 61.89964356979712, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 94, "capped_draws": 31, "coverage_status": "rated", "distinct_rated_opponents": 47, "draws": 31, "generated_at": "2026-07-02T16:51:45Z", "losses": 35, "model": "deepseek/deepseek-v4-pro", "point_rating_method": "sequential_elo", "public_id": "E-e121525dd1846069", "rated_matches": 94, "raw_elo_rating": 1489.9089544458643, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 47.413357618255546, "uncertainty": 7.54891760425771, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 14, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 14, "generated_at": "2026-07-02T16:51:45Z", "losses": 24, "model": "deepseek/deepseek-v4-pro", "point_rating_method": "sequential_elo", "public_id": "E-e192048d4eaa3c43", "rated_matches": 66, "raw_elo_rating": 1485.451431444242, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 45.905068931277405, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 35, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 35, "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": 64, "raw_elo_rating": 1450.7657677567693, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 41.55535155576687, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 23, "coverage_status": "rated", "distinct_rated_opponents": 24, "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": 48, "raw_elo_rating": 1331.1073977123126, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 25.94143215206774, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "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": 60, "raw_elo_rating": 1844.99143016808, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 89.7552146103392, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 51 }, { "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": 72, "capped_draws": 20, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 20, "generated_at": "2026-07-24T13:40:00Z", "losses": 25, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-77d8df8cd762fd09", "rated_matches": 72, "raw_elo_rating": 1489.7919739948888, "reasoning": "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": 46.68975405941891, "uncertainty": 14.770573598065289, "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-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": 66, "capped_draws": 13, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 13, "generated_at": "2026-07-24T13:40:00Z", "losses": 34, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-fc3c30006929710a", "rated_matches": 66, "raw_elo_rating": 1526.2127800710075, "reasoning": "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": 50.90906103861127, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 35, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 35, "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": 66, "raw_elo_rating": 1327.504805744083, "reasoning": "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": 26.5150414908058, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 2, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 2, "generated_at": "2026-07-24T13:40:00Z", "losses": 9, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-7484f4e7d8863a3b", "rated_matches": 66, "raw_elo_rating": 1856.4537079549752, "reasoning": "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": 91.45048207404956, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 55 }, { "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": 86, "capped_draws": 22, "coverage_status": "rated", "distinct_rated_opponents": 43, "draws": 22, "generated_at": "2026-07-02T16:51:45Z", "losses": 30, "model": "google/gemma-4-31b-it", "point_rating_method": "sequential_elo", "public_id": "E-caaa54d3c88e6570", "rated_matches": 86, "raw_elo_rating": 1462.3109351147084, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 43.79879432901968, "uncertainty": 9.855626741889738, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 1, "generated_at": "2026-07-02T16:51:45Z", "losses": 24, "model": "gpt-4.1", "point_rating_method": "sequential_elo", "public_id": "E-f50ec6b60d5b85da", "rated_matches": 48, "raw_elo_rating": 1595.6478858053922, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 58.41725935320175, "uncertainty": 27.67857142857143, "unilateral_faults": 1, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 7, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 7, "generated_at": "2026-07-02T16:51:45Z", "losses": 25, "model": "gpt-5", "point_rating_method": "sequential_elo", "public_id": "E-3e63b136f656e976", "rated_matches": 46, "raw_elo_rating": 1465.651346316106, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 42.3107717111968, "uncertainty": 29.182495748947275, "unilateral_faults": 8, "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": 64, "capped_draws": 19, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 19, "generated_at": "2026-07-02T16:51:45Z", "losses": 29, "model": "gpt-5", "point_rating_method": "sequential_elo", "public_id": "E-adee794ecd761044", "rated_matches": 64, "raw_elo_rating": 1357.5991262730408, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 30.11791991138669, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 26, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 26, "generated_at": "2026-07-02T16:51:45Z", "losses": 13, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-586de6c9939561c3", "rated_matches": 66, "raw_elo_rating": 1666.0791613055155, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 68.07950047101149, "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": "2026-07-02T16:51:45Z", "losses": 2, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-5d8a6b14c27539ab", "rated_matches": 64, "raw_elo_rating": 1926.8421962372731, "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": 18.26736729460423, "unilateral_faults": 0, "wins": 62 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 2, "coverage_status": "rated", "distinct_rated_opponents": 35, "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": 70, "raw_elo_rating": 1868.06073882597, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 93.0468380621979, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 62 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 23, "coverage_status": "rated", "distinct_rated_opponents": 37, "draws": 23, "generated_at": "2026-07-01T00:15:48Z", "losses": 42, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-3834aa9e894c458b", "rated_matches": 74, "raw_elo_rating": 1278.8833780426032, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 20.875096560147092, "uncertainty": 13.985026918962571, "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": 1603.3998294781852, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 60.09666542640562, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 31 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 18, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 18, "generated_at": "2026-07-01T00:15:48Z", "losses": 36, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-aa899d4eca8a2891", "rated_matches": 62, "raw_elo_rating": 1304.5057479594527, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 23.50408546806865, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 84, "capped_draws": 19, "coverage_status": "rated", "distinct_rated_opponents": 42, "draws": 19, "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": 84, "raw_elo_rating": 1498.51458551136, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 48.18169218709777, "uncertainty": 10.482614454664043, "unilateral_faults": 0, "wins": 33 }, { "admitted_plugin_count": 1, "attempted_matches": 84, "capped_draws": 11, "coverage_status": "rated", "distinct_rated_opponents": 42, "draws": 11, "generated_at": "2026-07-02T06:10:40Z", "losses": 33, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-c675a6c67536654d", "rated_matches": 84, "raw_elo_rating": 1502.2011058063451, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 48.634261080942416, "uncertainty": 10.482614454664043, "unilateral_faults": 0, "wins": 40 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 8, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 8, "generated_at": "2026-07-02T06:10:40Z", "losses": 25, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-ca99b677101014a8", "rated_matches": 70, "raw_elo_rating": 1517.1215772809917, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 49.96443638296805, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 37 }, { "admitted_plugin_count": 1, "attempted_matches": 86, "capped_draws": 36, "coverage_status": "rated", "distinct_rated_opponents": 43, "draws": 36, "generated_at": "2026-07-02T16:51:45Z", "losses": 30, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-ea1cb793f92b3cff", "rated_matches": 86, "raw_elo_rating": 1427.498691380369, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 39.52513315847563, "uncertainty": 9.855626741889738, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 19, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 19, "generated_at": "2026-07-02T06:10:40Z", "losses": 25, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-22c14c8deb751cb3", "rated_matches": 60, "raw_elo_rating": 1378.65720566583, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 32.50654994627, "uncertainty": 20.268439966447993, "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": 1396.023730456296, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 35.17846784359503, "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": 1418.5035046960031, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 37.49881072082661, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 10, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 10, "generated_at": "2026-07-01T00:15:48Z", "losses": 49, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-98c36ba5e36ecf75", "rated_matches": 60, "raw_elo_rating": 1113.866457280888, "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": 20.268439966447993, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 86, "capped_draws": 21, "coverage_status": "rated", "distinct_rated_opponents": 43, "draws": 21, "generated_at": "2026-07-09T17:30:50Z", "losses": 23, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-9eb27042bf28d67c", "rated_matches": 86, "raw_elo_rating": 1503.5208554870655, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 48.85785452291434, "uncertainty": 9.855626741889738, "unilateral_faults": 0, "wins": 42 }, { "admitted_plugin_count": 1, "attempted_matches": 84, "capped_draws": 30, "coverage_status": "rated", "distinct_rated_opponents": 42, "draws": 30, "generated_at": "2026-07-02T16:51:45Z", "losses": 30, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-a8887794a1195b75", "rated_matches": 84, "raw_elo_rating": 1525.463439796922, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 51.49001879281006, "uncertainty": 10.482614454664043, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 10, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 10, "generated_at": "2026-07-09T17:30:50Z", "losses": 49, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-c48c1aed1cdecc72", "rated_matches": 60, "raw_elo_rating": 1150.5504577389338, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 4.503443947312286, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 35, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 35, "generated_at": "2026-07-09T17:30:50Z", "losses": 20, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-db1fc33e2a2467d5", "rated_matches": 64, "raw_elo_rating": 1416.3463423379596, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 37.32991400433134, "uncertainty": 18.26736729460423, "unilateral_faults": 2, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 19, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 19, "generated_at": "2026-07-01T00:15:48Z", "losses": 43, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-f491ad1b583dbcac", "rated_matches": 68, "raw_elo_rating": 1197.38613783015, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 10.628845905590964, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 9, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 9, "generated_at": "2026-07-02T06:10:40Z", "losses": 48, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-fbb3f2dccb7c7fba", "rated_matches": 64, "raw_elo_rating": 1239.1718459938568, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 15.579412335586763, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 88, "capped_draws": 62, "coverage_status": "rated", "distinct_rated_opponents": 44, "draws": 62, "generated_at": "2026-07-02T16:51:45Z", "losses": 13, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-58178b9b32a94ca0", "rated_matches": 88, "raw_elo_rating": 1492.6269870813733, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 47.579978108397675, "uncertainty": 9.249894000318006, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 21, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 21, "generated_at": "2026-07-02T16:51:45Z", "losses": 12, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-8c61292c31db2722", "rated_matches": 64, "raw_elo_rating": 1738.5848065889888, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 76.88892728812435, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 31 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 39, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 39, "generated_at": "2026-07-02T16:51:45Z", "losses": 3, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-e4496be687faac9d", "rated_matches": 60, "raw_elo_rating": 1590.4682109147573, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 58.50913902194425, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "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-luna", "point_rating_method": "sequential_elo", "public_id": "E-38187ed58fb76057", "rated_matches": 60, "raw_elo_rating": 1651.564129610822, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 66.009467280089, "uncertainty": 20.268439966447993, "unilateral_faults": 2, "wins": 40 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 8, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 8, "generated_at": "2026-07-10T05:30:29Z", "losses": 26, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-4f775a5b7b265dae", "rated_matches": 68, "raw_elo_rating": 1645.9200434293616, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 65.69228710920916, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 76, "capped_draws": 22, "coverage_status": "rated", "distinct_rated_opponents": 38, "draws": 22, "generated_at": "2026-07-10T05:30:29Z", "losses": 40, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-959ed218b1c5605b", "rated_matches": 75, "raw_elo_rating": 1345.106968705622, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 29.04234144066881, "uncertainty": 13.603933467640434, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 15, "coverage_status": "rated", "distinct_rated_opponents": 36, "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": 72, "raw_elo_rating": 1581.1565667843893, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 57.90596050525336, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 38 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 17, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-9e683b3cd6c7f7c3", "rated_matches": 62, "raw_elo_rating": 1721.8625437609876, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 74.74012604307732, "uncertainty": 19.244078834871203, "unilateral_faults": 2, "wins": 45 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 29, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-bc834303cebba06a", "rated_matches": 62, "raw_elo_rating": 1603.5304016092489, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 60.21329792477527, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 33 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 13, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 13, "generated_at": "2026-07-10T05:30:29Z", "losses": 30, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-36d36f4895d90b11", "rated_matches": 62, "raw_elo_rating": 1444.5042092762435, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 40.69073946920973, "uncertainty": 19.244078834871203, "unilateral_faults": 2, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 23, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 23, "generated_at": "2026-07-10T05:30:29Z", "losses": 26, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-40742129939a44b5", "rated_matches": 72, "raw_elo_rating": 1574.221591188411, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 57.05460096205999, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 22, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 22, "generated_at": "2026-07-10T05:30:29Z", "losses": 20, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-46de264ad4571b48", "rated_matches": 62, "raw_elo_rating": 1498.983410367778, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 47.378778542011254, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 24, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 24, "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": 64, "raw_elo_rating": 1410.8433809053547, "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": 36.654353050059186, "uncertainty": 18.26736729460423, "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": "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": 68, "capped_draws": 15, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 15, "generated_at": "2026-07-24T13:40:00Z", "losses": 35, "model": "inclusionai/ling-3.0-flash", "point_rating_method": "sequential_elo", "public_id": "E-f9af396559c3a1cd", "rated_matches": 68, "raw_elo_rating": 1531.0496105208936, "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": 51.59042936884591, "uncertainty": 16.4429265428846, "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": 66, "capped_draws": 19, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 19, "generated_at": "2026-07-24T13:40:00Z", "losses": 26, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-9f5585b5fd96f2c3", "rated_matches": 66, "raw_elo_rating": 1499.6187640615335, "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": 47.64429550221449, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 26, "coverage_status": "rated", "distinct_rated_opponents": 37, "draws": 26, "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": 74, "raw_elo_rating": 1459.8055386885103, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 43.08567335444458, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 86, "capped_draws": 17, "coverage_status": "rated", "distinct_rated_opponents": 43, "draws": 17, "generated_at": "2026-07-02T16:51:45Z", "losses": 24, "model": "minimax/minimax-m3", "point_rating_method": "sequential_elo", "public_id": "E-444510032bc433fc", "rated_matches": 86, "raw_elo_rating": 1508.925857944881, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 49.52138972354479, "uncertainty": 9.855626741889738, "unilateral_faults": 0, "wins": 45 }, { "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": 1459.2155603129977, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 40.38312858490863, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 6, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 6, "generated_at": "2026-07-02T16:51:45Z", "losses": 26, "model": "mistralai/mistral-medium-3-5", "point_rating_method": "sequential_elo", "public_id": "E-99c7b0d758665b66", "rated_matches": 36, "raw_elo_rating": 1297.9505795131518, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 20.813178268089132, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 78, "capped_draws": 6, "coverage_status": "rated", "distinct_rated_opponents": 37, "draws": 6, "generated_at": "2026-07-02T16:51:45Z", "losses": 46, "model": "mistralai/mistral-medium-3-5", "point_rating_method": "sequential_elo", "public_id": "E-a0a38f5e77e983bc", "rated_matches": 73, "raw_elo_rating": 1392.3613831959185, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 34.7678319511097, "uncertainty": 14.373819371909642, "unilateral_faults": 4, "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": 21, "model": "moonshotai/kimi-k2.7-code", "point_rating_method": "sequential_elo", "public_id": "E-4935e918b1e70ea1", "rated_matches": 42, "raw_elo_rating": 1497.308406643702, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 45.87134893587861, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 7, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 7, "generated_at": "2026-07-21T14:20:15Z", "losses": 18, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-2292c77f8fb54ff1", "rated_matches": 48, "raw_elo_rating": 1568.536622820786, "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": 55.08899494180933, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 28, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 28, "generated_at": "2026-07-24T14:00:00Z", "losses": 12, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-6cc4477cf8936e55", "rated_matches": 48, "raw_elo_rating": 1482.4062234003072, "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": 44.51535463250467, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 1, "generated_at": "2026-07-17T22:36:00Z", "losses": 24, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-c89e5a24623ed70c", "rated_matches": 50, "raw_elo_rating": 1514.4057262201663, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "score": 48.58264022845683, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 16, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 16, "generated_at": "2026-07-17T22:36:00Z", "losses": 20, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-d2f6679f6ac952b3", "rated_matches": 50, "raw_elo_rating": 1467.5034498820974, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "score": 42.824768408249774, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 5, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 5, "generated_at": "2026-07-24T14:00:00Z", "losses": 18, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-dbb89dcf5242a5a0", "rated_matches": 44, "raw_elo_rating": 1529.9518155525486, "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": 50.047059085574304, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 14, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 14, "generated_at": "2026-07-21T14:43:57Z", "losses": 6, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-ee608da1db5fc482", "rated_matches": 34, "raw_elo_rating": 1589.456695453392, "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": 56.37194235700224, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 32, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 32, "generated_at": "2026-07-24T14:00:00Z", "losses": 5, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-fb8801908d28001f", "rated_matches": 48, "raw_elo_rating": 1584.356578397868, "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": 57.03110273541922, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 12, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 12, "generated_at": "2026-07-02T16:51:45Z", "losses": 19, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-0ce5e196701b51f3", "rated_matches": 48, "raw_elo_rating": 1548.045412820271, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 52.573429177506654, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 14, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 14, "generated_at": "2026-07-02T16:51:45Z", "losses": 29, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-b851008baae8f441", "rated_matches": 72, "raw_elo_rating": 1500.6871955211363, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 48.02728592138475, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 9, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 9, "generated_at": "2026-07-11T17:22:09Z", "losses": 22, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-ce064a9927030b28", "rated_matches": 36, "raw_elo_rating": 1347.5257898660675, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 26.899187923876408, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 10, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 10, "generated_at": "2026-07-02T16:51:45Z", "losses": 24, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-428923c2eb87dc7a", "rated_matches": 68, "raw_elo_rating": 1526.8363065441854, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 51.07319084373484, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 14, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 14, "generated_at": "2026-07-21T14:20:15Z", "losses": 20, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-fbf1a1af436a64a7", "rated_matches": 52, "raw_elo_rating": 1442.2859213259474, "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": 39.85997039408309, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 11, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 11, "generated_at": "2026-07-21T14:20:15Z", "losses": 24, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-55f6c0e3dc8a8065", "rated_matches": 48, "raw_elo_rating": 1363.6774166386915, "reasoning": "low", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "low", "repair_status": "first_pass", "score": 29.93983071183216, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 20, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 20, "generated_at": "2026-07-02T16:51:45Z", "losses": 24, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-a3e0c8f8ea39b5ec", "rated_matches": 60, "raw_elo_rating": 1397.6747028116988, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 34.84119805839559, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 8, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 8, "generated_at": "2026-07-24T13:40:00Z", "losses": 34, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-8461eb1b16e40129", "rated_matches": 72, "raw_elo_rating": 1643.3068833166908, "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": 65.53572997739795, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 30 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 22, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 22, "generated_at": "2026-07-24T13:40:00Z", "losses": 27, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-c58ec61528547516", "rated_matches": 72, "raw_elo_rating": 1516.95537959453, "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": 50.02441966318795, "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": "2026-07-24T13:40:00Z", "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": 34, "capped_draws": 9, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 9, "generated_at": "2026-07-02T16:51:45Z", "losses": 16, "model": "qwen/qwen3.7-max", "point_rating_method": "sequential_elo", "public_id": "E-24581eb49b81bf8f", "rated_matches": 34, "raw_elo_rating": 1429.107788816565, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 36.6870033090479, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 76, "capped_draws": 21, "coverage_status": "rated", "distinct_rated_opponents": 38, "draws": 21, "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": 76, "raw_elo_rating": 1600.9936984199935, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 60.49250178392132, "uncertainty": 13.230288229818967, "unilateral_faults": 0, "wins": 37 }, { "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": 1496.6188223697204, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 45.606222132078074, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 78, "capped_draws": 19, "coverage_status": "rated", "distinct_rated_opponents": 39, "draws": 19, "generated_at": "2026-07-03T18:55:00Z", "losses": 42, "model": "qwen/qwen3.7-plus", "point_rating_method": "sequential_elo", "public_id": "E-5e09f0c994a59f3c", "rated_matches": 78, "raw_elo_rating": 1363.2762547082637, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 31.3808467215317, "uncertainty": 12.5043950463012, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 18, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 18, "generated_at": "2026-07-21T14:20:15Z", "losses": 28, "model": "stepfun/step-3.7-flash", "point_rating_method": "sequential_elo", "public_id": "E-09ecaa63c419b917", "rated_matches": 66, "raw_elo_rating": 1469.4983722127108, "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": 43.94662091196941, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 1, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 1, "generated_at": "2026-07-02T16:51:45Z", "losses": 32, "model": "stepfun/step-3.7-flash", "point_rating_method": "sequential_elo", "public_id": "E-4b0ce2bc67b08d8a", "rated_matches": 36, "raw_elo_rating": 1229.3525267234986, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 12.391864295359213, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 4, "coverage_status": "rated", "distinct_rated_opponents": 22, "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": 44, "raw_elo_rating": 1582.666949871878, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 56.51853574073472, "uncertainty": 30.785599249992988, "unilateral_faults": 6, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 82, "capped_draws": 15, "coverage_status": "rated", "distinct_rated_opponents": 41, "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": 82, "raw_elo_rating": 1704.653117005999, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 73.42412117365035, "uncertainty": 11.132129994845172, "unilateral_faults": 0, "wins": 52 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 15, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 15, "generated_at": "2026-07-24T13:40:00Z", "losses": 24, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-7382cf954e1b755d", "rated_matches": 66, "raw_elo_rating": 1455.0498647650818, "reasoning": "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": 42.17287642935396, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 27 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 34, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 34, "generated_at": "2026-07-24T13:40:00Z", "losses": 26, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-9e638fc0ac98df4f", "rated_matches": 68, "raw_elo_rating": 1355.6784914065313, "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": 30.061315993869457, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 26, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 26, "generated_at": "2026-07-24T13:40:00Z", "losses": 30, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-bc7c657b08ebac66", "rated_matches": 66, "raw_elo_rating": 1291.467544227601, "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": 22.09099326194052, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 26, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 26, "generated_at": "2026-07-24T13:40:00Z", "losses": 27, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-c9890f6abafaf54f", "rated_matches": 66, "raw_elo_rating": 1294.0874891238236, "reasoning": "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": 22.412625985685597, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 5, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "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": 36, "raw_elo_rating": 1654.2401596445443, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 64.55241425921825, "uncertainty": 38.449493652678655, "unilateral_faults": 2, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 10, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 10, "generated_at": "2026-07-24T14:00:00Z", "losses": 6, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-1c8e452ede41ea2e", "rated_matches": 36, "raw_elo_rating": 1692.7204147120556, "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": 69.27637210490104, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 31, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 31, "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": 52, "raw_elo_rating": 1567.42228168583, "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": 55.2221058649925, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 82, "capped_draws": 7, "coverage_status": "rated", "distinct_rated_opponents": 41, "draws": 7, "generated_at": "2026-07-17T22:36:00Z", "losses": 42, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-abb31ae26e404d88", "rated_matches": 82, "raw_elo_rating": 1462.056816210286, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 43.642231826323574, "uncertainty": 11.132129994845172, "unilateral_faults": 0, "wins": 33 }, { "admitted_plugin_count": 1, "attempted_matches": 76, "capped_draws": 6, "coverage_status": "rated", "distinct_rated_opponents": 38, "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": 76, "raw_elo_rating": 1825.3784261046408, "reasoning": "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": 88.03868080320296, "uncertainty": 13.230288229818967, "unilateral_faults": 0, "wins": 60 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 17, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 17, "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": 48, "raw_elo_rating": 1661.320192160666, "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": 66.47939943794896, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 3, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "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": 36, "raw_elo_rating": 1610.216180559382, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 59.14789131536924, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 12, "coverage_status": "rated", "distinct_rated_opponents": 33, "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": 66, "raw_elo_rating": 1646.142849491161, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 65.63205576348118, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 8, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 8, "generated_at": "2026-07-02T16:51:45Z", "losses": 17, "model": "x-ai/grok-build-0.1", "point_rating_method": "sequential_elo", "public_id": "E-f1ded648f3ab17dc", "rated_matches": 44, "raw_elo_rating": 1506.4490343059604, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 47.16178330789564, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 3, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 3, "generated_at": "2026-07-02T16:51:45Z", "losses": 18, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-1208f50b0908ecb4", "rated_matches": 42, "raw_elo_rating": 1492.9024648281463, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 45.33046158025427, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 4, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 4, "generated_at": "2026-07-02T06:10:40Z", "losses": 26, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-2a71bee21bd7c0b9", "rated_matches": 48, "raw_elo_rating": 1488.3764895552486, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 45.248283392825215, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 5, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 5, "generated_at": "2026-07-02T06:10:40Z", "losses": 29, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-2cdd8ae895784956", "rated_matches": 72, "raw_elo_rating": 1621.9825868393657, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 62.91789188170463, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 38 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 33, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 33, "generated_at": "2026-07-02T06:10:40Z", "losses": 13, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-8478c64d84536b61", "rated_matches": 48, "raw_elo_rating": 1293.44691203047, "reasoning": "highest", "reasoning_bracket": "highest", "reasoning_setting": "highest", "repair_status": "repaired", "score": 21.31811178953796, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 92, "capped_draws": 27, "coverage_status": "rated", "distinct_rated_opponents": 46, "draws": 27, "generated_at": "2026-07-02T16:51:45Z", "losses": 36, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-912a4a40bbdcbd45", "rated_matches": 92, "raw_elo_rating": 1462.887330767872, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 44.04221272141304, "uncertainty": 8.09758473652126, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugin_count": 1, "attempted_matches": 82, "capped_draws": 29, "coverage_status": "rated", "distinct_rated_opponents": 41, "draws": 29, "generated_at": "2026-07-01T00:15:48Z", "losses": 36, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-a168350bd057f924", "rated_matches": 82, "raw_elo_rating": 1416.5999005346357, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 38.061797053482614, "uncertainty": 11.132129994845172, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugin_count": 1, "attempted_matches": 94, "capped_draws": 29, "coverage_status": "rated", "distinct_rated_opponents": 47, "draws": 29, "generated_at": "2026-07-02T16:51:45Z", "losses": 40, "model": "xiaomi/mimo-v2.5-pro", "point_rating_method": "sequential_elo", "public_id": "E-9ce4191c7f1f3b3e", "rated_matches": 94, "raw_elo_rating": 1427.9370306043306, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 39.80548819718096, "uncertainty": 7.54891760425771, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 36, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 36, "generated_at": "2026-07-11T14:00:45Z", "losses": 14, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-5ab5088af70c19d6", "rated_matches": 64, "raw_elo_rating": 1461.622752883799, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 42.88818939640259, "uncertainty": 18.26736729460423, "unilateral_faults": 2, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 2, "coverage_status": "rated", "distinct_rated_opponents": 24, "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": 48, "raw_elo_rating": 1529.881929087823, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 50.34362245371306, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 13, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 13, "generated_at": "2026-07-11T14:00:45Z", "losses": 24, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-5c3b7f5666a38043", "rated_matches": 50, "raw_elo_rating": 1449.7679989041592, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 40.64750833949597, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 8, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 8, "generated_at": "2026-07-02T06:10:40Z", "losses": 15, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-6a7eb114b16dc845", "rated_matches": 48, "raw_elo_rating": 1567.659706257965, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 54.98134189040207, "uncertainty": 27.67857142857143, "unilateral_faults": 1, "wins": 25 }, { "admitted_plugin_count": 1, "attempted_matches": 80, "capped_draws": 48, "coverage_status": "rated", "distinct_rated_opponents": 40, "draws": 48, "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": 80, "raw_elo_rating": 1516.6932618433234, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 50.28343725469852, "uncertainty": 11.805555555555554, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 34, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 34, "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": 48, "raw_elo_rating": 1475.508755653665, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 43.66859967155317, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 3, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 3, "generated_at": "2026-07-02T16:51:45Z", "losses": 29, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-c8076ea61de8da45", "rated_matches": 50, "raw_elo_rating": 1347.818567378608, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 28.131873604926756, "uncertainty": 26.26400420140049, "unilateral_faults": 1, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 4, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 4, "generated_at": "2026-07-11T17:22:09Z", "losses": 20, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-f889d782e3cce209", "rated_matches": 50, "raw_elo_rating": 1431.4781468541285, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 38.40218824126544, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 26 } ], "GB2-02": [ { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 31, "generated_at": "2026-07-02T16:51:45Z", "losses": 9, "model": "claude-fable-5", "point_rating_method": "sequential_elo", "public_id": "E-cd3608270e8c00fd", "rated_matches": 64, "raw_elo_rating": 1636.8022098052088, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 64.91511947130134, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 27, "generated_at": "2026-07-03T17:50:00Z", "losses": 3, "model": "claude-fable-5", "point_rating_method": "sequential_elo", "public_id": "E-f6a30e7d9986c9b8", "rated_matches": 62, "raw_elo_rating": 1675.2224541849737, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 73.7853774932965, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 39, "losses": 4, "model": "claude-opus-4-5", "point_rating_method": "sequential_elo", "public_id": "E-03472a04778e9928", "rated_matches": 44, "raw_elo_rating": 1485.1484662563396, "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": 26.81515533589486, "uncertainty": 30.785599249992988, "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": 74, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 37, "draws": 65, "generated_at": "2026-07-02T16:51:45Z", "losses": 6, "model": "claude-opus-4-5", "point_rating_method": "sequential_elo", "public_id": "E-16462f3d1f3a7b19", "rated_matches": 74, "raw_elo_rating": 1500.9638007338544, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 33.709793544320256, "uncertainty": 13.985026918962571, "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": 36, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 33, "losses": 3, "model": "claude-opus-4-5", "point_rating_method": "sequential_elo", "public_id": "E-63fde27ceab11930", "rated_matches": 36, "raw_elo_rating": 1461.1138901432366, "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": 19.706083474218055, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "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": 60, "raw_elo_rating": 1746.8507510957204, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 90.47270926865744, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 37 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 56, "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": 66, "raw_elo_rating": 1478.1224509695917, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 27.69529937871457, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 45, "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": 50, "raw_elo_rating": 1475.402260482471, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 25.370766045966345, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 23, "generated_at": "2026-07-25T10:50:00Z", "losses": 10, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-50b401cafe71e710", "rated_matches": 56, "raw_elo_rating": 1652.955076470378, "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": 67.92823779226067, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 19, "generated_at": "2026-07-25T10:50:00Z", "losses": 11, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-51ddad48e10b006f", "rated_matches": 56, "raw_elo_rating": 1657.241211986099, "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": 68.93834045321007, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 26 }, { "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": 1660.854766399915, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 67.55387519409311, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 34, "generated_at": "2026-07-25T10:50:00Z", "losses": 4, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-772d1a710082ddb3", "rated_matches": 56, "raw_elo_rating": 1594.1213833662362, "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": 54.06305090304598, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 27, "generated_at": "2026-07-25T10:50:00Z", "losses": 7, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-8a5bf2e23121edf6", "rated_matches": 54, "raw_elo_rating": 1631.9817217201396, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 62.76051011951749, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 20 }, { "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": 1747.9087192203456, "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": 88.06965895024113, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 26 }, { "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": 3, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-a1a16bb5799cfdbe", "rated_matches": 60, "raw_elo_rating": 1487.5573627493632, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 29.365695602250742, "uncertainty": 20.268439966447993, "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": 1528.8802538058603, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 38.687839752916766, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 38, "generated_at": "2026-07-02T16:51:45Z", "losses": 3, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-e501d6808bd19ccc", "rated_matches": 42, "raw_elo_rating": 1483.9542755106384, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 26.21063543593213, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 36, "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": 42, "raw_elo_rating": 1449.902229991137, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 18.185676434085963, "uncertainty": 32.49928516630233, "unilateral_faults": 1, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 56, "generated_at": "2026-07-02T16:51:45Z", "losses": 8, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-12dcb25370550495", "rated_matches": 68, "raw_elo_rating": 1469.9439655992894, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 25.936030290732113, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 41, "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": 42, "raw_elo_rating": 1497.5964351716725, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 29.425648522700747, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 69, "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": 72, "raw_elo_rating": 1497.792219534097, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 32.814252834535765, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 63, "generated_at": "2026-07-02T06:10:40Z", "losses": 1, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-bc9a8c3886a48505", "rated_matches": 64, "raw_elo_rating": 1488.2384450412742, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 29.903474702187335, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 58, "generated_at": "2026-07-02T06:10:40Z", "losses": 7, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-f2e6dd87c5656ee3", "rated_matches": 68, "raw_elo_rating": 1491.4884345889675, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 31.01336052805069, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 3 }, { "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": 2, "model": "deepseek/deepseek-v4-pro", "point_rating_method": "sequential_elo", "public_id": "E-6c3b019c1b20a09b", "rated_matches": 58, "raw_elo_rating": 1492.0797054118812, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 30.228599126505976, "uncertainty": 21.344455490411935, "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": "2026-07-02T16:51:45Z", "losses": 3, "model": "google/gemini-3.1-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-20b3484be872df52", "rated_matches": 42, "raw_elo_rating": 1494.771862796145, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 28.759988731473964, "uncertainty": 32.49928516630233, "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": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 53, "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": 62, "raw_elo_rating": 1491.9455099224035, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 30.592965958181995, "uncertainty": 19.244078834871203, "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": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 61, "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": 68, "raw_elo_rating": 1489.7324730104383, "reasoning": "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": 30.599537526773265, "uncertainty": 16.4429265428846, "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": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 67, "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": 68, "raw_elo_rating": 1481.4729062717392, "reasoning": "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": 28.653026430601027, "uncertainty": 16.4429265428846, "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": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 66, "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": 70, "raw_elo_rating": 1470.6574745098255, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 26.26515964856663, "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-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": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 65, "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": 66, "raw_elo_rating": 1481.321900682551, "reasoning": "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": 28.449305559055883, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 35, "generated_at": "2026-07-02T16:51:45Z", "losses": 10, "model": "gpt-4.1", "point_rating_method": "sequential_elo", "public_id": "E-e4707b8e4c581ede", "rated_matches": 48, "raw_elo_rating": 1464.639645646619, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 22.567673997988543, "uncertainty": 27.67857142857143, "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": 1484.7600002274844, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 25.68130071513402, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 39, "generated_at": "2026-07-02T16:51:45Z", "losses": 7, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-4aa582caf9d9f6da", "rated_matches": 66, "raw_elo_rating": 1602.558018732674, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 57.0207132983657, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 68, "generated_at": "2026-07-02T16:51:45Z", "losses": 1, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-98ddce22d3eb5886", "rated_matches": 70, "raw_elo_rating": 1486.4639803433008, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 29.99023869568103, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 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": 1459.0930765758949, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 23.37882885928049, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 53, "generated_at": "2026-07-02T06:10:40Z", "losses": 4, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-3082b8a32a9c1e1f", "rated_matches": 60, "raw_elo_rating": 1494.7479081869635, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 31.060273166015826, "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": 63, "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": 64, "raw_elo_rating": 1483.909003509502, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 28.883166222526008, "uncertainty": 18.26736729460423, "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": "2026-07-01T00:15:48Z", "losses": 4, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-4f2717a1b63468f4", "rated_matches": 64, "raw_elo_rating": 1481.7298499274937, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 28.369610637610304, "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": 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": 1485.9681038721687, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 28.57484246757806, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 2 }, { "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": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-6724998b59176607", "rated_matches": 54, "raw_elo_rating": 1477.6874336305343, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 26.39836748614762, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 58, "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": 64, "raw_elo_rating": 1477.7748776841786, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 27.43755238319894, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 57, "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": 60, "raw_elo_rating": 1498.8962495460976, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 32.03790222837709, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 65, "generated_at": "2026-07-01T00:15:48Z", "losses": 5, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-dd45dfa7984ab9fa", "rated_matches": 72, "raw_elo_rating": 1498.893600981965, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 33.073812600467356, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 53, "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": 56, "raw_elo_rating": 1495.9131766564717, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 30.918572488692377, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 64, "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": 68, "raw_elo_rating": 1469.8136765250715, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 25.905325395826853, "uncertainty": 16.4429265428846, "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": "2026-07-01T00:15:48Z", "losses": 2, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-23b12c36ef5c7ef8", "rated_matches": 62, "raw_elo_rating": 1474.580133477346, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 26.500511836933963, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 63, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 54, "generated_at": "2026-07-01T00:15:48Z", "losses": 7, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-6a4ccfcf11c5e3f3", "rated_matches": 63, "raw_elo_rating": 1474.8171470134807, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 26.64951885685805, "uncertainty": 18.75, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 62, "generated_at": "2026-07-02T06:10:40Z", "losses": 4, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-786cc9019eb3ee2b", "rated_matches": 68, "raw_elo_rating": 1498.4882992808675, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 32.66300084521741, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 49, "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": 52, "raw_elo_rating": 1474.6633957814352, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 25.448091621557595, "uncertainty": 24.930281974344517, "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": 1495.0208034325651, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 32.30922247837311, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 53, "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": 60, "raw_elo_rating": 1442.6014891166542, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 18.771059148236457, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 63, "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": 66, "raw_elo_rating": 1483.123702192543, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 28.873931540448716, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 70, "generated_at": "2026-07-02T16:51:45Z", "losses": 2, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-51e935956fa76015", "rated_matches": 72, "raw_elo_rating": 1500.601598880668, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 33.47633212325143, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 34, "generated_at": "2026-07-02T16:51:45Z", "losses": 12, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-8460841e3919c568", "rated_matches": 62, "raw_elo_rating": 1542.631132430455, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 42.53791776371207, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 66, "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": 72, "raw_elo_rating": 1471.706546099867, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 26.66670849023619, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 66, "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": 66, "raw_elo_rating": 1485.0271335560255, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 29.322508371054298, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 59, "generated_at": "2026-07-10T05:30:29Z", "losses": 1, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-e2dda893ae4363f2", "rated_matches": 60, "raw_elo_rating": 1485.1956413229286, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 28.80911471755574, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 51, "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": 64, "raw_elo_rating": 1502.7262761164538, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 33.31778502129591, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 30, "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": 64, "raw_elo_rating": 1557.8041669293343, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 46.29785153237801, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "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": 60, "raw_elo_rating": 1787.2775916050075, "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": 45 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 41, "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": 64, "raw_elo_rating": 1554.51478910498, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 45.52265222263585, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 54, "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": 56, "raw_elo_rating": 1486.2662373624098, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 28.645102829320255, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 76, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 37, "draws": 70, "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": 76, "raw_elo_rating": 1477.289710549957, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 28.272874772560343, "uncertainty": 13.230288229818967, "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": "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": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 64, "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": 66, "raw_elo_rating": 1471.8518908493445, "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": 26.217532415940592, "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": "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": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 67, "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": 68, "raw_elo_rating": 1479.8498057623008, "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": 28.27051445972222, "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": 65, "generated_at": "2026-07-02T16:51:45Z", "losses": 1, "model": "minimax/minimax-m3", "point_rating_method": "sequential_elo", "public_id": "E-1e46941293882535", "rated_matches": 66, "raw_elo_rating": 1471.6428922171287, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 26.16827823959424, "uncertainty": 17.33472217815261, "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": "2026-07-02T16:51:45Z", "losses": 2, "model": "minimax/minimax-m3", "point_rating_method": "sequential_elo", "public_id": "E-cad87bcb23d33fef", "rated_matches": 32, "raw_elo_rating": 1464.6310084541792, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 19.62257491103967, "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": 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": 1461.747653970409, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 18.943062089796843, "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": 1492.9402178593853, "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": 27.981880405129896, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 38, "generated_at": "2026-07-24T14:00:00Z", "losses": 4, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-8825a1d540d89836", "rated_matches": 42, "raw_elo_rating": 1477.719665153068, "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": 24.741340662338175, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 24, "generated_at": "2026-07-18T00:14:00Z", "losses": 6, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-97d6a124a1509fc1", "rated_matches": 34, "raw_elo_rating": 1500.7329502647428, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "score": 28.6063748434055, "uncertainty": 40.76542547285167, "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": 1465.3469691951177, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "score": 20.267050641538766, "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": 25, "generated_at": "2026-07-21T14:43:57Z", "losses": 3, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-be8e56a3b58c5bcc", "rated_matches": 32, "raw_elo_rating": 1517.4994211194166, "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": 32.0819393239128, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 39, "generated_at": "2026-07-24T14:00:00Z", "losses": 0, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-d3d3da42e99695b1", "rated_matches": 40, "raw_elo_rating": 1506.1574106540736, "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": 31.096742630840403, "uncertainty": 34.33688094430304, "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": 1522.0566255972044, "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": 35.190119418577666, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 58, "generated_at": "2026-07-11T17:22:09Z", "losses": 7, "model": "nex-agi/nex-n2-pro", "point_rating_method": "sequential_elo", "public_id": "E-811f47e902ce0d21", "rated_matches": 68, "raw_elo_rating": 1476.372168299665, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 27.45094847961234, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 35, "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": 42, "raw_elo_rating": 1468.6948724253036, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 22.61449070264951, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 31, "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": 36, "raw_elo_rating": 1474.5104940152412, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 22.863227052428083, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 1 }, { "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": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-bd70ebbd81fdbef0", "rated_matches": 60, "raw_elo_rating": 1477.573967254025, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 27.012934165249288, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 38, "generated_at": "2026-07-21T14:20:15Z", "losses": 1, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-e48b0ea99dfc517c", "rated_matches": 40, "raw_elo_rating": 1474.570314492858, "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": 23.652691977966807, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 43, "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": 44, "raw_elo_rating": 1488.805306711772, "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": 27.67695362975448, "uncertainty": 30.785599249992988, "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": "2026-07-02T16:51:45Z", "losses": 4, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-8f0c6569aa132f8e", "rated_matches": 60, "raw_elo_rating": 1478.4308374646337, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 27.214870589482516, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 30, "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": 34, "raw_elo_rating": 1449.166076833186, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 16.453740873013416, "uncertainty": 40.76542547285167, "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": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 63, "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": 68, "raw_elo_rating": 1479.0793242660857, "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": 28.088937044196097, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 54, "generated_at": "2026-07-02T16:51:45Z", "losses": 6, "model": "qwen/qwen3.7-max", "point_rating_method": "sequential_elo", "public_id": "E-5f64c2ae9860ba38", "rated_matches": 66, "raw_elo_rating": 1500.6469304986908, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 33.0035862085153, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 32, "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": 36, "raw_elo_rating": 1501.7510369677718, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 29.282936560242895, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 60, "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": 60, "raw_elo_rating": 1493.0380666605308, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 30.657319160171507, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 38, "generated_at": "2026-07-02T16:51:45Z", "losses": 5, "model": "qwen/qwen3.7-plus", "point_rating_method": "sequential_elo", "public_id": "E-57293d5b71f14882", "rated_matches": 44, "raw_elo_rating": 1484.4653388827323, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 26.65416444437566, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 53, "generated_at": "2026-07-02T16:51:45Z", "losses": 6, "model": "stepfun/step-3.7-flash", "point_rating_method": "sequential_elo", "public_id": "E-0ccea44addccfff0", "rated_matches": 60, "raw_elo_rating": 1492.386996118362, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 30.503883020623825, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 66, "generated_at": "2026-07-02T16:51:45Z", "losses": 6, "model": "tencent/hy3-preview", "point_rating_method": "sequential_elo", "public_id": "E-d910e47dd13c2c71", "rated_matches": 72, "raw_elo_rating": 1466.230042358881, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 25.376074775744662, "uncertainty": 14.770573598065289, "unilateral_faults": 1, "wins": 0 }, { "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": 5, "model": "tencent/hy3-preview", "point_rating_method": "sequential_elo", "public_id": "E-fbf6af15f65f01d7", "rated_matches": 34, "raw_elo_rating": 1439.0333836038849, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 14.065794818587444, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 65, "generated_at": "2026-07-24T13:40:00Z", "losses": 7, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-63e0985794df5d5b", "rated_matches": 72, "raw_elo_rating": 1474.1670464469105, "reasoning": "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": 27.24656835203928, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 68, "generated_at": "2026-07-24T13:40:00Z", "losses": 1, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-66a4f0abd099d8f1", "rated_matches": 70, "raw_elo_rating": 1497.9528618673835, "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": 32.69779419789101, "uncertainty": 15.58908290969266, "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": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 18, "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": 34, "raw_elo_rating": 1531.5155213105586, "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": 35.86082510756406, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 31, "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": 60, "raw_elo_rating": 1591.688437333961, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 53.906001231790846, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 21 }, { "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": 1479.099098563037, "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": 24.719979006893933, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 44, "generated_at": "2026-07-24T14:00:00Z", "losses": 3, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-1b0da3150a77b47b", "rated_matches": 50, "raw_elo_rating": 1482.683841994756, "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": 27.0867978500241, "uncertainty": 26.26400420140049, "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": "2026-07-17T22:36:00Z", "losses": 6, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-8728b59f87c3369e", "rated_matches": 34, "raw_elo_rating": 1499.4387882182075, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 28.301382963865, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 84, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 42, "draws": 56, "generated_at": "2026-07-24T14:00:00Z", "losses": 15, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-da5ea0258e71b6ab", "rated_matches": 84, "raw_elo_rating": 1506.3447777590582, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 35.638238433963316, "uncertainty": 10.482614454664043, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 33, "generated_at": "2026-07-02T16:51:45Z", "losses": 3, "model": "x-ai/grok-build-0.1", "point_rating_method": "sequential_elo", "public_id": "E-99592fa0331c6679", "rated_matches": 38, "raw_elo_rating": 1505.5724580315348, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 30.586119737224937, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 61, "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": 64, "raw_elo_rating": 1467.6684243184336, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 25.05579021071138, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 32, "generated_at": "2026-07-02T16:51:45Z", "losses": 4, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-5b213ae773e821cc", "rated_matches": 38, "raw_elo_rating": 1492.7593511110604, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 27.56648740223964, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 37, "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": 42, "raw_elo_rating": 1485.4236953036248, "reasoning": "highest", "reasoning_bracket": "highest", "reasoning_setting": "highest", "repair_status": "repaired", "score": 26.556929863045585, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 29, "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": 32, "raw_elo_rating": 1465.4021769870442, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 19.804314238746468, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 0 }, { "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-c37f25e181320efb", "rated_matches": 38, "raw_elo_rating": 1481.6528261727108, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 24.94904090457791, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 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": 1476.1302139151496, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 27.04995865374969, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 40, "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": 42, "raw_elo_rating": 1468.8623880163934, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 22.65396867615027, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 57, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 46, "generated_at": "2026-07-11T14:00:45Z", "losses": 8, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-4442c0e8a06187bf", "rated_matches": 57, "raw_elo_rating": 1476.956020516428, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 26.559093337903025, "uncertainty": 21.90321642986127, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 39, "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": 42, "raw_elo_rating": 1467.0613447958626, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 22.22952139890711, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 44, "generated_at": "2026-07-11T14:00:45Z", "losses": 2, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-925b589068dc7268", "rated_matches": 46, "raw_elo_rating": 1481.2115840910012, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 26.18959978556957, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 58, "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": 62, "raw_elo_rating": 1467.1991422445142, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 24.761052396750248, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 35, "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": 42, "raw_elo_rating": 1486.6279450324444, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 26.840732335241476, "uncertainty": 32.49928516630233, "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": 1498.8696729023943, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 32.031638978317616, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 7 } ], "GB2-03": [ { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 21, "generated_at": "2026-07-03T17:50:00Z", "losses": 4, "model": "claude-fable-5", "point_rating_method": "sequential_elo", "public_id": "E-04fa5b762ca703f0", "rated_matches": 44, "raw_elo_rating": 1646.2996143800208, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 69.97359637011016, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 9, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 40, "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": 58, "raw_elo_rating": 1548.522194338608, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 54.88884061800323, "uncertainty": 21.344455490411935, "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": "2026-07-02T16:51:45Z", "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": 22, "capped_draws": 1, "coverage_status": "under_covered", "distinct_rated_opponents": 11, "draws": 4, "losses": 10, "model": "claude-opus-4-5", "point_rating_method": "sequential_elo", "public_id": "E-d5810442d7094396", "rated_matches": 22, "raw_elo_rating": 1453.813901657228, "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": 33.81629613230089, "uncertainty": 60.5072070285374, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 24, "capped_draws": 3, "coverage_status": "under_covered", "distinct_rated_opponents": 12, "draws": 13, "losses": 6, "model": "claude-opus-4-5", "point_rating_method": "sequential_elo", "public_id": "E-dfb18dba94eee30b", "rated_matches": 24, "raw_elo_rating": 1507.6894676690647, "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": 43.39323863302372, "uncertainty": 56.25, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 5, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 25, "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": 42, "raw_elo_rating": 1456.992704704807, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 38.09391002162233, "uncertainty": 32.49928516630233, "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": 1828.7336971220263, "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": 44, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 4, "generated_at": "2026-07-25T15:48:00Z", "losses": 16, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-49aaba66f6b19080", "rated_matches": 44, "raw_elo_rating": 1586.523100982404, "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": 59.97948109091506, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 24 }, { "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": 1817.031961601465, "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": 98.04357117683936, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 36 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "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": 42, "raw_elo_rating": 1770.1925604080766, "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": 90.45821307999611, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 33 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 22, "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": 44, "raw_elo_rating": 1806.7805996235456, "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": 96.80462707901296, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 38 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 11, "generated_at": "2026-07-25T15:48:00Z", "losses": 16, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-ecf847457e616425", "rated_matches": 44, "raw_elo_rating": 1467.6921639227314, "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": 40.111977681850504, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 18, "generated_at": "2026-07-19T15:25:00Z", "losses": 9, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-1c251b669239429c", "rated_matches": 42, "raw_elo_rating": 1578.2542907653385, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 58.367796890295175, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 3, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 12, "generated_at": "2026-07-03T16:50:00Z", "losses": 25, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-2e43b0d163a7f12d", "rated_matches": 40, "raw_elo_rating": 1320.2042410476315, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 14.97827962852532, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 2, "coverage_status": "rated", "distinct_rated_opponents": 25, "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": 50, "raw_elo_rating": 1545.5752895760347, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 53.738138920033414, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 20 }, { "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": 1487.6967601875272, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 42.71712204291151, "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": 1444.616242265077, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 32.27852714847803, "uncertainty": 60.5072070285374, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 9, "generated_at": "2026-07-01T00:15:48Z", "losses": 10, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-32e04fe5ad231857", "rated_matches": 32, "raw_elo_rating": 1548.4644867532702, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 51.94406520454458, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 3, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 26, "generated_at": "2026-07-02T06:10:40Z", "losses": 19, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-4e52c100ed276347", "rated_matches": 56, "raw_elo_rating": 1446.536779333255, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 37.68633239449348, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 78, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 39, "draws": 36, "generated_at": "2026-07-02T16:51:45Z", "losses": 22, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-ae9d59ec3a8a1d63", "rated_matches": 78, "raw_elo_rating": 1482.1225653402416, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 44.96978300688633, "uncertainty": 12.5043950463012, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 18, "generated_at": "2026-07-02T16:51:45Z", "losses": 31, "model": "deepseek/deepseek-v4-pro", "point_rating_method": "sequential_elo", "public_id": "E-f82a334a0fd1fb8e", "rated_matches": 58, "raw_elo_rating": 1341.7414384682531, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 20.31688929088188, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 22, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 11, "draws": 15, "generated_at": "2026-07-02T16:51:45Z", "losses": 3, "model": "google/gemini-3.5-flash", "point_rating_method": "sequential_elo", "public_id": "E-46c3bb79de67d970", "rated_matches": 22, "raw_elo_rating": 1516.880077333121, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 44.360414450649905, "uncertainty": 60.5072070285374, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 16, "generated_at": "2026-07-02T16:51:45Z", "losses": 15, "model": "google/gemini-3.5-flash", "point_rating_method": "sequential_elo", "public_id": "E-8ed795ea8fd1e0aa", "rated_matches": 54, "raw_elo_rating": 1584.4380808026062, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 60.58261886572101, "uncertainty": 23.66998624632421, "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": 54, "capped_draws": 3, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 21, "generated_at": "2026-07-24T13:40:00Z", "losses": 18, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-36e89f1dca2cd568", "rated_matches": 54, "raw_elo_rating": 1534.5721625266235, "reasoning": "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": 52.245469249146645, "uncertainty": 23.66998624632421, "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": 54, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 18, "generated_at": "2026-07-24T13:40:00Z", "losses": 19, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-e51f710b50e975e5", "rated_matches": 54, "raw_elo_rating": 1494.9601751869436, "reasoning": "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": 45.62268806956448, "uncertainty": 23.66998624632421, "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": 52, "capped_draws": 2, "coverage_status": "rated", "distinct_rated_opponents": 26, "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": 52, "raw_elo_rating": 1568.0269179489935, "reasoning": "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": 57.67024616007308, "uncertainty": 24.930281974344517, "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-3.6-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": 56, "capped_draws": 3, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 14, "generated_at": "2026-07-24T13:40:00Z", "losses": 19, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-f44c7c8e627e08cd", "rated_matches": 56, "raw_elo_rating": 1551.7329489848184, "reasoning": "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": 55.27422079196909, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 10, "generated_at": "2026-07-02T16:51:45Z", "losses": 11, "model": "gpt-4.1", "point_rating_method": "sequential_elo", "public_id": "E-c7da9914f86ee846", "rated_matches": 32, "raw_elo_rating": 1525.6726149306114, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 48.13346165011627, "uncertainty": 43.288827977848925, "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": "2026-07-21T14:20:15Z", "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": 1450.1918496770988, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 32.89731675267175, "uncertainty": 62.850358177805205, "unilateral_faults": 1, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 29, "generated_at": "2026-07-02T16:51:45Z", "losses": 12, "model": "gpt-5", "point_rating_method": "sequential_elo", "public_id": "E-e724ba162431d43a", "rated_matches": 46, "raw_elo_rating": 1431.7303930296262, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 34.31390109131504, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 2, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 25, "generated_at": "2026-07-02T16:51:45Z", "losses": 19, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-496f83ad0bd69447", "rated_matches": 56, "raw_elo_rating": 1400.8815780438904, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 30.053178186490474, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 7, "coverage_status": "rated", "distinct_rated_opponents": 23, "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": 46, "raw_elo_rating": 1461.2984840176907, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 39.257429797226955, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 2, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 32, "generated_at": "2026-07-02T16:51:45Z", "losses": 10, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-ebd456dc6b320c61", "rated_matches": 56, "raw_elo_rating": 1552.4602360612246, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 55.3958168916667, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 70, "generated_at": "2026-07-02T16:51:45Z", "losses": 2, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-35117a2e624d7970", "rated_matches": 72, "raw_elo_rating": 1494.1421634084834, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 46.676247354738535, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 8, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 21, "generated_at": "2026-07-01T00:15:48Z", "losses": 13, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-3e164d6fc6c16cbb", "rated_matches": 50, "raw_elo_rating": 1552.5018653012748, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 54.89620238599134, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 13, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 27, "generated_at": "2026-07-02T06:10:40Z", "losses": 11, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-7cbcc752e71e2d3b", "rated_matches": 44, "raw_elo_rating": 1461.2632800472154, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 39.037123982353414, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 9, "coverage_status": "rated", "distinct_rated_opponents": 27, "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": 54, "raw_elo_rating": 1537.3428421012582, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 52.70870287547778, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 23, "generated_at": "2026-07-01T00:15:48Z", "losses": 14, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-a51cd55f211305c2", "rated_matches": 56, "raw_elo_rating": 1531.6573984374318, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 51.91776262704892, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 23, "generated_at": "2026-07-02T06:10:40Z", "losses": 10, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-dfa5098ec9c3cf47", "rated_matches": 58, "raw_elo_rating": 1540.239622647847, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 53.504066371719354, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 25 }, { "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": 1408.753378227649, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 30.673497730348966, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 9, "generated_at": "2026-07-01T00:15:48Z", "losses": 28, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-0ecb5b73c09f13b2", "rated_matches": 54, "raw_elo_rating": 1412.860488094673, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 31.896331503262783, "uncertainty": 23.66998624632421, "unilateral_faults": 1, "wins": 17 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 3, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 15, "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": 50, "raw_elo_rating": 1421.5214998503109, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 32.99741978352148, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 37, "draws": 41, "generated_at": "2026-07-02T06:10:40Z", "losses": 23, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-e4eac938bdd5d40e", "rated_matches": 74, "raw_elo_rating": 1421.5124258286896, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 34.6382536024244, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 25, "generated_at": "2026-07-09T17:30:50Z", "losses": 22, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-f2a7b43bf689e68e", "rated_matches": 68, "raw_elo_rating": 1510.1867737968605, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 49.13508489782365, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 2, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 22, "generated_at": "2026-07-02T16:51:45Z", "losses": 10, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-446036823932df16", "rated_matches": 50, "raw_elo_rating": 1532.4592771605007, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 51.54525524994926, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 4, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 23, "generated_at": "2026-07-02T16:51:45Z", "losses": 14, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-c002b0ea38b845f8", "rated_matches": 46, "raw_elo_rating": 1468.040920087715, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 40.38470670777879, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 2, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 21, "generated_at": "2026-07-02T16:51:45Z", "losses": 15, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-e53a932f820d9724", "rated_matches": 47, "raw_elo_rating": 1513.6863551335346, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 48.1183769229996, "uncertainty": 28.418783648703226, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 15, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 35, "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": 44, "raw_elo_rating": 1489.5459265778684, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 43.76573750900555, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 5 }, { "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": 1405.5751168246516, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 29.94096545666281, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 23, "generated_at": "2026-07-10T05:30:29Z", "losses": 18, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-d192bb239087b778", "rated_matches": 56, "raw_elo_rating": 1470.4123206900906, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 41.67811610871256, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 5, "generated_at": "2026-07-10T05:30:29Z", "losses": 16, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-2ac4e83a1b9ba989", "rated_matches": 50, "raw_elo_rating": 1590.6444127760449, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 61.27330594787659, "uncertainty": 26.26400420140049, "unilateral_faults": 1, "wins": 29 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 10, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 34, "generated_at": "2026-07-10T05:30:29Z", "losses": 20, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-527999604d620080", "rated_matches": 72, "raw_elo_rating": 1495.3996940005095, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 46.88649557748494, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 2, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 14, "generated_at": "2026-07-10T05:30:29Z", "losses": 12, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-b741de451c385e8e", "rated_matches": 50, "raw_elo_rating": 1582.5689592229082, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 59.92316006022683, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 22, "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": 44, "raw_elo_rating": 1555.6224588373111, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 54.81316137358737, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 10, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 28, "generated_at": "2026-07-10T10:07:13Z", "losses": 21, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-c2f0f8f062659e83", "rated_matches": 64, "raw_elo_rating": 1509.542473344345, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 48.7833388899691, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 25, "generated_at": "2026-07-10T05:30:29Z", "losses": 9, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-e44c62bb88a3042a", "rated_matches": 40, "raw_elo_rating": 1500.0753756097706, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 45.05117535357613, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 18, "generated_at": "2026-07-24T13:40:00Z", "losses": 23, "model": "inclusionai/ling-3.0-flash", "point_rating_method": "sequential_elo", "public_id": "E-2524de3c7d4a81b7", "rated_matches": 52, "raw_elo_rating": 1390.930627546129, "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": 28.061280343833168, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 20, "generated_at": "2026-07-24T13:40:00Z", "losses": 23, "model": "inclusionai/ling-3.0-flash", "point_rating_method": "sequential_elo", "public_id": "E-641ddca04b054d56", "rated_matches": 50, "raw_elo_rating": 1384.2919804431226, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 26.77296660624224, "uncertainty": 26.26400420140049, "unilateral_faults": 1, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 4, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 26, "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": 52, "raw_elo_rating": 1421.9129068998388, "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": 33.24124909533193, "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": "2026-07-24T13:40:00Z", "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": 54, "capped_draws": 5, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 25, "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": 54, "raw_elo_rating": 1449.8161521192164, "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": 38.074998432592515, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 24, "generated_at": "2026-07-02T16:51:45Z", "losses": 14, "model": "minimax/minimax-m3", "point_rating_method": "sequential_elo", "public_id": "E-44cc758f104a74ab", "rated_matches": 66, "raw_elo_rating": 1531.065473656246, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 52.50654226647922, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 10, "generated_at": "2026-07-24T14:00:00Z", "losses": 3, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-09859be1b47131a0", "rated_matches": 38, "raw_elo_rating": 1673.7136397706963, "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": 73.81753310342788, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugin_count": 1, "attempted_matches": 24, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 11, "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": 22, "raw_elo_rating": 1651.4966395310923, "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": 66.86713765389882, "uncertainty": 60.5072070285374, "unilateral_faults": 1, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 2, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 14, "generated_at": "2026-07-21T14:20:15Z", "losses": 5, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-a12d08354d94b221", "rated_matches": 38, "raw_elo_rating": 1621.890061963377, "reasoning": "low", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "low", "repair_status": "first_pass", "score": 65.15307976969873, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 22, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 11, "draws": 6, "generated_at": "2026-07-24T14:00:00Z", "losses": 8, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-b97350a867368460", "rated_matches": 22, "raw_elo_rating": 1513.3940866178589, "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": 43.77758699735245, "uncertainty": 60.5072070285374, "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": 1477.2378787461882, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 38.806908566038985, "uncertainty": 52.475044864937615, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 4, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 37, "generated_at": "2026-07-02T16:51:45Z", "losses": 15, "model": "nex-agi/nex-n2-pro", "point_rating_method": "sequential_elo", "public_id": "E-a05d4cef5f788f16", "rated_matches": 58, "raw_elo_rating": 1418.3320938153308, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 33.122183466475484, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 4, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 21, "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": 34, "raw_elo_rating": 1422.2873610539257, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 31.1858555184372, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 23, "generated_at": "2026-07-21T14:20:15Z", "losses": 10, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-08888c30d05ca8cb", "rated_matches": 38, "raw_elo_rating": 1451.4587426506623, "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": 36.658439390347205, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 4, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 28, "generated_at": "2026-07-02T16:51:45Z", "losses": 13, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-87b4bd61da369b42", "rated_matches": 48, "raw_elo_rating": 1426.7962430236144, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 33.69010844396414, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 29, "generated_at": "2026-07-21T14:20:15Z", "losses": 12, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-c90a449ff5e7b79a", "rated_matches": 46, "raw_elo_rating": 1447.733296866472, "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": 36.98944800191301, "uncertainty": 29.182495748947275, "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": "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": 52, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 16, "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": 52, "raw_elo_rating": 1445.7977395279188, "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": 37.23458622962569, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 7, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 31, "generated_at": "2026-07-24T13:40:00Z", "losses": 14, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-91efdb0c216f8504", "rated_matches": 56, "raw_elo_rating": 1502.7276421965807, "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": 47.08095796186405, "uncertainty": 22.47661785325219, "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": "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": 60, "capped_draws": 4, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 48, "generated_at": "2026-07-02T16:51:45Z", "losses": 8, "model": "qwen/qwen3.7-max", "point_rating_method": "sequential_elo", "public_id": "E-3325ebad2ef000c1", "rated_matches": 60, "raw_elo_rating": 1434.9623243276997, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 36.04653434402484, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 7, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 24, "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": 46, "raw_elo_rating": 1538.934447109512, "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": 52.23749037369294, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugin_count": 1, "attempted_matches": 80, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 40, "draws": 26, "generated_at": "2026-07-02T16:51:45Z", "losses": 26, "model": "tencent/hy3-preview", "point_rating_method": "sequential_elo", "public_id": "E-2346cd049910cc0a", "rated_matches": 80, "raw_elo_rating": 1427.499195255498, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 35.93070058290421, "uncertainty": 11.805555555555554, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 5, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 28, "generated_at": "2026-07-24T13:40:00Z", "losses": 15, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-78048b7c08122f1c", "rated_matches": 52, "raw_elo_rating": 1435.6332279487651, "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": 35.53516793463317, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 8, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 21, "generated_at": "2026-07-24T13:40:00Z", "losses": 12, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-adf1f0bb193bd39b", "rated_matches": 52, "raw_elo_rating": 1611.5217807019071, "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": 64.9422104767928, "uncertainty": 24.930281974344517, "unilateral_faults": 1, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 10, "generated_at": "2026-07-24T14:00:00Z", "losses": 26, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-02f7e54245bd5c85", "rated_matches": 38, "raw_elo_rating": 1312.7162394535528, "reasoning": "low", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "low", "repair_status": "repaired", "score": 13.461894589336923, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 6, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 33, "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": 60, "raw_elo_rating": 1495.8404344667613, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 46.224827056787426, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 34, "generated_at": "2026-07-21T14:20:15Z", "losses": 7, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-3c1904811d11cd84", "rated_matches": 52, "raw_elo_rating": 1522.4166372444274, "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": 50.044602284763734, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 22, "capped_draws": 2, "coverage_status": "under_covered", "distinct_rated_opponents": 11, "draws": 10, "generated_at": "2026-07-24T14:00:00Z", "losses": 6, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-c0c60ca46f3ce498", "rated_matches": 22, "raw_elo_rating": 1516.6952603309, "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": 44.329514648691465, "uncertainty": 60.5072070285374, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 4, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 24, "generated_at": "2026-07-24T14:00:00Z", "losses": 17, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-cbed46472ce4dd05", "rated_matches": 64, "raw_elo_rating": 1535.107382073436, "reasoning": "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": 53.05757019618682, "uncertainty": 18.26736729460423, "unilateral_faults": 1, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 7, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 20, "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": 44, "raw_elo_rating": 1543.708942096389, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 52.82132456474889, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 22, "capped_draws": 1, "coverage_status": "under_covered", "distinct_rated_opponents": 11, "draws": 10, "generated_at": "2026-07-02T16:51:45Z", "losses": 7, "model": "x-ai/grok-build-0.1", "point_rating_method": "sequential_elo", "public_id": "E-2a93343a8a88fd59", "rated_matches": 22, "raw_elo_rating": 1512.2395415346, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 43.58455705965157, "uncertainty": 60.5072070285374, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 2, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 32, "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": 54, "raw_elo_rating": 1537.4103736250274, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 52.71999356132024, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 4, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 35, "generated_at": "2026-07-02T16:51:45Z", "losses": 9, "model": "xiaomi/mimo-v2.5-pro", "point_rating_method": "sequential_elo", "public_id": "E-b0948c64dddf57ad", "rated_matches": 54, "raw_elo_rating": 1447.7436441756136, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 37.72849305567903, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 6, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 21, "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": 32, "raw_elo_rating": 1483.3794346590705, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 41.06240823577625, "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": 23, "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": 32, "raw_elo_rating": 1503.721201303524, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 44.46337542626583, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 4, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 17, "generated_at": "2026-07-11T14:00:45Z", "losses": 9, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-583be34ca1fb2631", "rated_matches": 34, "raw_elo_rating": 1493.010827082733, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 43.010206459325595, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 21, "generated_at": "2026-07-19T14:50:00Z", "losses": 15, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-714519b339aeb2e2", "rated_matches": 58, "raw_elo_rating": 1552.4724697885567, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 55.549292457486665, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 22 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 8, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 23, "generated_at": "2026-07-11T15:43:48Z", "losses": 20, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-bd2653f21938737f", "rated_matches": 50, "raw_elo_rating": 1418.58964495931, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 32.50723904033177, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 5, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 10, "generated_at": "2026-07-02T06:10:40Z", "losses": 15, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-f1af7b938699d971", "rated_matches": 32, "raw_elo_rating": 1365.8175451624577, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 21.40707858725937, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 7 } ], "GB2-04": [ { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "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": 58, "raw_elo_rating": 1828.795087741824, "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": 48 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 25, "generated_at": "2026-07-02T16:51:45Z", "losses": 15, "model": "claude-fable-5", "point_rating_method": "sequential_elo", "public_id": "E-eb1f17ce19beffd0", "rated_matches": 62, "raw_elo_rating": 1581.0598602467503, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 51.78455451097985, "uncertainty": 19.244078834871203, "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-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": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 40, "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": 60, "raw_elo_rating": 1533.6903460135152, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 42.34172688645558, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 9 }, { "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": 1447.8002185982532, "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": 25.5112133873534, "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": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 19, "losses": 11, "model": "claude-opus-4-5", "point_rating_method": "sequential_elo", "public_id": "E-f40463f635c43598", "rated_matches": 34, "raw_elo_rating": 1422.5164490697043, "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": 17.343584831257935, "uncertainty": 40.76542547285167, "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": 1579.5576387423876, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 51.78950505760701, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 42, "generated_at": "2026-07-02T16:51:45Z", "losses": 9, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-688a139ef8557587", "rated_matches": 56, "raw_elo_rating": 1478.6538182736597, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 31.21093844748892, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 47, "generated_at": "2026-07-02T16:51:45Z", "losses": 7, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-caf91ab5b69b1e64", "rated_matches": 58, "raw_elo_rating": 1466.485643264073, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 29.004017345869457, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 31, "generated_at": "2026-07-25T15:48:00Z", "losses": 13, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-048d3dcf802043b4", "rated_matches": 58, "raw_elo_rating": 1538.6551452561764, "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": 43.14591949521648, "uncertainty": 21.344455490411935, "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": 1643.6380792859509, "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": 61.68101057822674, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 22 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 27, "generated_at": "2026-07-25T15:48:00Z", "losses": 15, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-72e9307528761b35", "rated_matches": 60, "raw_elo_rating": 1518.6489524149345, "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": 39.39430573777955, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 15, "generated_at": "2026-07-25T15:48:00Z", "losses": 17, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-9e7782014171d35f", "rated_matches": 56, "raw_elo_rating": 1607.7985303782043, "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": 56.51736056867651, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 24 }, { "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": 1754.2494224092084, "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": 83.35574502807938, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 27 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 20, "generated_at": "2026-07-25T15:48:00Z", "losses": 14, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-d0f0a2b1c4bbddae", "rated_matches": 54, "raw_elo_rating": 1539.3499750795136, "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": 42.91751654259464, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 43, "generated_at": "2026-07-03T16:50:00Z", "losses": 9, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-8e980ad934b3251e", "rated_matches": 68, "raw_elo_rating": 1540.7026544738983, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 44.315516442451184, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 48, "generated_at": "2026-07-02T16:51:45Z", "losses": 8, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-b1fc5b99a5deb881", "rated_matches": 68, "raw_elo_rating": 1495.0551444554867, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 35.3707045451438, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 35, "generated_at": "2026-07-02T16:51:45Z", "losses": 2, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-be938b7d5557f479", "rated_matches": 42, "raw_elo_rating": 1529.625293105078, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 39.62781716181058, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 24, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 12, "draws": 18, "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": 24, "raw_elo_rating": 1480.403456405545, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 26.259363733302056, "uncertainty": 56.25, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 41, "generated_at": "2026-07-01T00:15:48Z", "losses": 5, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-5d143d6301429619", "rated_matches": 48, "raw_elo_rating": 1466.5672296334092, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 28.02704826832348, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 27, "generated_at": "2026-07-02T16:51:45Z", "losses": 22, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-81bc9a578754f220", "rated_matches": 50, "raw_elo_rating": 1340.394586255456, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 3.524766962285257, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 78, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 39, "draws": 69, "generated_at": "2026-07-01T00:15:48Z", "losses": 2, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-a43d18fadfcc5a89", "rated_matches": 78, "raw_elo_rating": 1518.5161209085754, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 40.585393362011814, "uncertainty": 12.5043950463012, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 37, "draws": 72, "generated_at": "2026-07-02T06:10:40Z", "losses": 1, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-cb48b9466ec54175", "rated_matches": 74, "raw_elo_rating": 1504.575065127242, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 37.621479220114104, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 25, "generated_at": "2026-07-02T16:51:45Z", "losses": 20, "model": "deepseek/deepseek-v4-pro", "point_rating_method": "sequential_elo", "public_id": "E-38bc194a470fbf62", "rated_matches": 52, "raw_elo_rating": 1437.033942799334, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 22.67071339758295, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 20, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 10, "draws": 16, "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": 20, "raw_elo_rating": 1451.381288182883, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 19.144406619465567, "uncertainty": 65.3589451179962, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 43, "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": 50, "raw_elo_rating": 1495.4259070579112, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 33.9037734449991, "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": 34, "generated_at": "2026-07-02T16:51:45Z", "losses": 9, "model": "google/gemini-3.5-flash", "point_rating_method": "sequential_elo", "public_id": "E-32cfa6c9dfb1d16f", "rated_matches": 56, "raw_elo_rating": 1533.857806977198, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 42.028380510266544, "uncertainty": 22.47661785325219, "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": "2026-07-21T14:20:15Z", "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": 1481.8176682330727, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 28.568318927201943, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 56, "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": 67, "raw_elo_rating": 1504.8720377502932, "reasoning": "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": 37.2252346041612, "uncertainty": 16.883906259083243, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 54, "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": 69, "raw_elo_rating": 1472.5821006203996, "reasoning": "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": 31.034664555308932, "uncertainty": 16.01143046671968, "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": 69, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 40, "generated_at": "2026-07-24T13:40:00Z", "losses": 13, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-1ff96286ae16ecd4", "rated_matches": 68, "raw_elo_rating": 1494.233632097183, "reasoning": "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": 35.20972591753903, "uncertainty": 16.4429265428846, "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": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 50, "generated_at": "2026-07-24T13:40:00Z", "losses": 9, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-d109ab12db58a65f", "rated_matches": 68, "raw_elo_rating": 1476.497140927611, "reasoning": "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": 31.734189636018268, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 27, "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": 36, "raw_elo_rating": 1539.3989299517496, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 40.610226642627, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 5 }, { "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": 5, "model": "google/gemma-4-31b-it", "point_rating_method": "sequential_elo", "public_id": "E-ec0cf4b37c805eee", "rated_matches": 54, "raw_elo_rating": 1488.6170542412904, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 32.97619808478928, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 4 }, { "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": 9, "model": "gpt-4.1", "point_rating_method": "sequential_elo", "public_id": "E-ecb06954153be8d5", "rated_matches": 38, "raw_elo_rating": 1461.6738793317916, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 25.714447304211713, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 78, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 39, "draws": 50, "generated_at": "2026-07-02T16:51:45Z", "losses": 12, "model": "gpt-5", "point_rating_method": "sequential_elo", "public_id": "E-6f1aae863396df76", "rated_matches": 78, "raw_elo_rating": 1548.0131095292184, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 46.365446088704815, "uncertainty": 12.5043950463012, "unilateral_faults": 0, "wins": 16 }, { "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": 1467.4471341169822, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 24.84174288121968, "uncertainty": 49.09766908852594, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 43, "generated_at": "2026-07-02T16:51:45Z", "losses": 7, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-0b4132559ee98caf", "rated_matches": 66, "raw_elo_rating": 1521.843945614986, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 40.48027638959632, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 53, "generated_at": "2026-07-02T16:51:45Z", "losses": 8, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-8d62bf1b340a70dc", "rated_matches": 72, "raw_elo_rating": 1493.812998783348, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 35.38946453067582, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 28, "generated_at": "2026-07-02T16:51:45Z", "losses": 13, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-9279285adff8ed29", "rated_matches": 70, "raw_elo_rating": 1620.454608682286, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 60.07708164277407, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 41, "generated_at": "2026-07-02T06:10:40Z", "losses": 15, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-040a4b654fceeb0c", "rated_matches": 66, "raw_elo_rating": 1479.9001298332687, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 32.26121816995966, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 10 }, { "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": 1490.7178079038288, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 34.65463738122138, "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": 41, "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": 62, "raw_elo_rating": 1569.7783785164224, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 49.57390310940306, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 35, "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": 62, "raw_elo_rating": 1568.7055868234213, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 49.36368529259289, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 37, "draws": 60, "generated_at": "2026-07-02T06:10:40Z", "losses": 8, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-c9bf6a0be0c43fd1", "rated_matches": 74, "raw_elo_rating": 1461.710286970976, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 29.221954745001227, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 51, "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": 68, "raw_elo_rating": 1530.5831222317804, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 42.332553683738304, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 49, "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": 62, "raw_elo_rating": 1472.4242445605073, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 30.49697174316458, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 15, "generated_at": "2026-07-09T17:30:50Z", "losses": 24, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-3403c285ceec6345", "rated_matches": 70, "raw_elo_rating": 1529.549353889867, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 42.263833904463375, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 31 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 47, "generated_at": "2026-07-01T00:15:48Z", "losses": 13, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-48f60c9100c65daa", "rated_matches": 66, "raw_elo_rating": 1473.6556896663606, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 31.037595179911463, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 36, "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": 64, "raw_elo_rating": 1573.0644962351932, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 50.370943422371525, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 26, "generated_at": "2026-07-02T06:10:40Z", "losses": 24, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-bbf36865f2b7fe63", "rated_matches": 58, "raw_elo_rating": 1375.9421461186027, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 11.261657463283376, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 55, "generated_at": "2026-07-02T06:10:40Z", "losses": 9, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-c8f4bd9fcf2e481e", "rated_matches": 70, "raw_elo_rating": 1498.1287649236724, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 36.106844007492846, "uncertainty": 15.58908290969266, "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": 1533.704734035738, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 43.078097240001945, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 44, "generated_at": "2026-07-02T16:51:45Z", "losses": 13, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-64bf5daf186f8119", "rated_matches": 68, "raw_elo_rating": 1470.7482297231588, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 30.607667525230426, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 41, "generated_at": "2026-07-02T16:51:45Z", "losses": 14, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-9e7bdad81107b7e4", "rated_matches": 64, "raw_elo_rating": 1449.039720517403, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 26.067793284414353, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 52, "generated_at": "2026-07-02T16:51:45Z", "losses": 12, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-ba1aa87056709e9a", "rated_matches": 70, "raw_elo_rating": 1498.9622499050838, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 36.27016871841243, "uncertainty": 15.58908290969266, "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": 1512.2196063935532, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 38.29503183096133, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 76, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 38, "draws": 54, "generated_at": "2026-07-10T05:30:29Z", "losses": 15, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-71a01107bf3f9fc1", "rated_matches": 76, "raw_elo_rating": 1489.5809864033852, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 34.80164485846782, "uncertainty": 13.230288229818967, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 36, "generated_at": "2026-07-10T05:30:29Z", "losses": 18, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-e348813cda8b38b7", "rated_matches": 68, "raw_elo_rating": 1515.6939072556113, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 39.41495254390206, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 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": 1653.6598205873045, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 65.31698730595153, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 59, "generated_at": "2026-07-10T05:30:29Z", "losses": 7, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-c81bf4d15f3d48f1", "rated_matches": 70, "raw_elo_rating": 1483.3945244178965, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 33.21961073407453, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 57, "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": 66, "raw_elo_rating": 1480.824684786784, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 32.44238840563259, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 80, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 40, "draws": 75, "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": 80, "raw_elo_rating": 1517.755122369414, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 40.54582497036699, "uncertainty": 11.805555555555554, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 54, "generated_at": "2026-07-10T05:30:29Z", "losses": 7, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-89c18d144e85d89f", "rated_matches": 70, "raw_elo_rating": 1505.8676356462586, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 37.623306633454085, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 27, "generated_at": "2026-07-10T05:30:29Z", "losses": 13, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-b85c80e7475ef9ec", "rated_matches": 60, "raw_elo_rating": 1564.0392200957288, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 48.288709971644074, "uncertainty": 20.268439966447993, "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": "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": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 59, "generated_at": "2026-07-24T13:40:00Z", "losses": 5, "model": "inclusionai/ling-3.0-flash", "point_rating_method": "sequential_elo", "public_id": "E-f38039bb8cc277a1", "rated_matches": 66, "raw_elo_rating": 1476.8265619678257, "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": 31.65894027136433, "uncertainty": 17.33472217815261, "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": "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": 72, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 40, "generated_at": "2026-07-24T13:40:00Z", "losses": 15, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-9e1d4bf411e97fa6", "rated_matches": 72, "raw_elo_rating": 1567.8900482908955, "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": 49.905158234128194, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 29, "generated_at": "2026-07-02T16:51:45Z", "losses": 3, "model": "minimax/minimax-m3", "point_rating_method": "sequential_elo", "public_id": "E-c60620c3c72a6064", "rated_matches": 32, "raw_elo_rating": 1462.166968986042, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 24.717685927847732, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 26, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 13, "draws": 20, "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": 26, "raw_elo_rating": 1483.3504319083952, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 27.428609381105517, "uncertainty": 52.475044864937615, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 25, "generated_at": "2026-07-21T14:43:57Z", "losses": 13, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-0f7ca9245c7db7c7", "rated_matches": 52, "raw_elo_rating": 1479.532620120741, "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": 30.99849895195425, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 17, "generated_at": "2026-07-17T22:36:00Z", "losses": 8, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-2a7239d6b25916b0", "rated_matches": 34, "raw_elo_rating": 1527.691200643713, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "score": 37.952997454116975, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 29, "generated_at": "2026-07-24T14:00:00Z", "losses": 6, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-35e5c9532c697b2c", "rated_matches": 38, "raw_elo_rating": 1478.1778373322668, "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": 28.948463788698337, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 23, "generated_at": "2026-07-24T14:00:00Z", "losses": 6, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-3c06949f23d4a77f", "rated_matches": 38, "raw_elo_rating": 1533.7867296752677, "reasoning": "low", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "low", "repair_status": "repaired", "score": 39.84524833675206, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 11, "generated_at": "2026-07-24T14:00:00Z", "losses": 8, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-601725df2c678708", "rated_matches": 34, "raw_elo_rating": 1566.4219216942895, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "score": 45.54243692857585, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 10, "generated_at": "2026-07-17T22:36:00Z", "losses": 10, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-6f3da6d3b01bcfad", "rated_matches": 34, "raw_elo_rating": 1536.1330457194156, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "score": 39.60721071214382, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 33, "generated_at": "2026-07-21T14:20:15Z", "losses": 7, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-818ed7ee27b56509", "rated_matches": 46, "raw_elo_rating": 1494.5305918681663, "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": 33.27082079801426, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 55, "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": 60, "raw_elo_rating": 1490.7581639196449, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 33.928994340568096, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 27, "generated_at": "2026-07-11T17:22:09Z", "losses": 6, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-958dea26b779a042", "rated_matches": 34, "raw_elo_rating": 1446.8683525897754, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 22.115437583807967, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 30, "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": 42, "raw_elo_rating": 1500.908758448871, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 34.00069750646294, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 47, "generated_at": "2026-07-02T16:51:45Z", "losses": 8, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-7e92e17a121661f4", "rated_matches": 58, "raw_elo_rating": 1453.38347630081, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 26.43659540135972, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 22, "generated_at": "2026-07-21T14:20:15Z", "losses": 9, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-a4643af0a1bcc24c", "rated_matches": 38, "raw_elo_rating": 1478.3686604298084, "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": 28.985856336779992, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 7 }, { "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": 1458.718033081689, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 24.43742980201681, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 42, "generated_at": "2026-07-02T16:51:45Z", "losses": 6, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-f1288f2abfdbbfe4", "rated_matches": 52, "raw_elo_rating": 1470.896254983829, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 29.306168711049935, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 30, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 15, "draws": 17, "generated_at": "2026-07-21T14:20:15Z", "losses": 12, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-f6de1ce39e48807c", "rated_matches": 30, "raw_elo_rating": 1415.9403697276475, "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": 15.226133451490124, "uncertainty": 46.05265101338746, "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": 28, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 14, "draws": 17, "generated_at": "2026-07-02T16:51:45Z", "losses": 7, "model": "qwen/qwen3.7-max", "point_rating_method": "sequential_elo", "public_id": "E-ea08328e287de1ad", "rated_matches": 28, "raw_elo_rating": 1483.2326201707826, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "first_pass", "score": 27.934971918287903, "uncertainty": 49.09766908852594, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 44, "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": 50, "raw_elo_rating": 1511.7005114932745, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 37.09284718239884, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 43, "generated_at": "2026-07-02T16:51:45Z", "losses": 4, "model": "stepfun/step-3.7-flash", "point_rating_method": "sequential_elo", "public_id": "E-25e56c6bfae33c62", "rated_matches": 52, "raw_elo_rating": 1525.7581685865202, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 40.05657979162075, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 18, "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": 32, "raw_elo_rating": 1557.208361778728, "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": 43.34142642641564, "uncertainty": 43.288827977848925, "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": "2026-07-02T16:51:45Z", "losses": 7, "model": "tencent/hy3-preview", "point_rating_method": "sequential_elo", "public_id": "E-3fd10f7865cc280e", "rated_matches": 54, "raw_elo_rating": 1521.3603548320514, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 39.39237860730228, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 10 }, { "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": 1435.454832644688, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 15.145849175849548, "uncertainty": 70.95786693528086, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 34, "generated_at": "2026-07-24T13:40:00Z", "losses": 16, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-646ff33c7bab8b13", "rated_matches": 56, "raw_elo_rating": 1434.5376024796492, "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": 22.56618976920879, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 52, "generated_at": "2026-07-24T13:40:00Z", "losses": 8, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-7ca32267720b2e1a", "rated_matches": 64, "raw_elo_rating": 1495.0703113780432, "reasoning": "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": 35.08767140272284, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 42, "generated_at": "2026-07-24T13:40:00Z", "losses": 12, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-d9e91f86e4e39739", "rated_matches": 60, "raw_elo_rating": 1444.4738152198197, "reasoning": "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": 24.859391360201073, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 53, "generated_at": "2026-07-24T13:40:00Z", "losses": 8, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-ddc16fa197bfc7c5", "rated_matches": 66, "raw_elo_rating": 1509.591619925644, "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": 38.07938423684785, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 5 }, { "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": 1491.7333881559198, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 30.906920487109797, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 37, "draws": 57, "generated_at": "2026-07-17T22:36:00Z", "losses": 7, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-1a7064508fe2a12f", "rated_matches": 74, "raw_elo_rating": 1501.568405879708, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 37.032312332420936, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 25, "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": 32, "raw_elo_rating": 1537.8466070366878, "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": 39.54741325681464, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 37, "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": 46, "raw_elo_rating": 1527.8099734039513, "reasoning": "low", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "low", "repair_status": "repaired", "score": 39.79204852273032, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 28, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 14, "draws": 18, "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": 28, "raw_elo_rating": 1413.645049227228, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 14.299009469743243, "uncertainty": 49.09766908852594, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 49, "generated_at": "2026-07-17T22:36:00Z", "losses": 12, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-83f4cc0ffc20bde5", "rated_matches": 70, "raw_elo_rating": 1496.784910839686, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 35.84351043258728, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 86, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 43, "draws": 61, "generated_at": "2026-07-24T14:00:00Z", "losses": 13, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-ba6a8e6d7fc9a48d", "rated_matches": 86, "raw_elo_rating": 1503.1775544812508, "reasoning": "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": 37.994969393101584, "uncertainty": 9.855626741889738, "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": 1464.0149828787098, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 21.620029552164407, "uncertainty": 65.3589451179962, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 28, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 14, "draws": 23, "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": 28, "raw_elo_rating": 1486.6872720566844, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 28.61192475268359, "uncertainty": 49.09766908852594, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 28, "generated_at": "2026-07-02T06:10:40Z", "losses": 6, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-00e6914e513b1656", "rated_matches": 36, "raw_elo_rating": 1464.2307841980507, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 25.880728272069145, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 24, "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": 36, "raw_elo_rating": 1434.6389637716811, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 20.082092874300265, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 30, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 15, "draws": 24, "generated_at": "2026-07-02T16:51:45Z", "losses": 6, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-2f7e15b8aa123825", "rated_matches": 30, "raw_elo_rating": 1444.5321443660189, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 20.828805883070206, "uncertainty": 46.05265101338746, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 50, "generated_at": "2026-07-01T00:15:48Z", "losses": 6, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-7ad356726cce2b22", "rated_matches": 68, "raw_elo_rating": 1474.9093182327397, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 31.42304943743622, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 62, "generated_at": "2026-07-02T06:10:40Z", "losses": 4, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-d58c55e107783a21", "rated_matches": 70, "raw_elo_rating": 1504.3586208087058, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 37.3276091492603, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 34, "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": 44, "raw_elo_rating": 1495.3820186822695, "reasoning": "highest", "reasoning_bracket": "highest", "reasoning_setting": "highest", "repair_status": "repaired", "score": 33.18635365584194, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 15, "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": 32, "raw_elo_rating": 1496.005201975642, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 31.34842282690637, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 30, "generated_at": "2026-07-02T16:51:45Z", "losses": 6, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-1d5f5ff0402ff944", "rated_matches": 42, "raw_elo_rating": 1537.4697859315131, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 41.16497686085959, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 38, "generated_at": "2026-07-02T06:10:40Z", "losses": 2, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-3efc86009429a22c", "rated_matches": 42, "raw_elo_rating": 1494.0667529675093, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 32.659979206462815, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 2 }, { "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": 1516.0566774459735, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 40.213007904288595, "uncertainty": 11.805555555555554, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 27, "generated_at": "2026-07-11T17:22:09Z", "losses": 9, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-912f31ad14c4bf0a", "rated_matches": 44, "raw_elo_rating": 1469.2510998588752, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 28.065895749489687, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 12, "generated_at": "2026-07-01T00:15:48Z", "losses": 17, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-947248ef34168cde", "rated_matches": 42, "raw_elo_rating": 1515.6489399725556, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 36.889094946068, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 34, "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": 44, "raw_elo_rating": 1487.9896459881716, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 31.7377887024233, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 24, "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": 48, "raw_elo_rating": 1513.300187609426, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 37.18455802803732, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 13 }, { "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": 1437.9506430561107, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 22.641265916399533, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 9 } ], "GB2-05": [ { "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": "claude-fable-5", "point_rating_method": "sequential_elo", "public_id": "E-5aa4402ccce7b855", "rated_matches": 66, "raw_elo_rating": 1911.0343695647828, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 93.05084396084196, "uncertainty": 17.33472217815261, "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": 25, "model": "claude-fable-5", "point_rating_method": "sequential_elo", "public_id": "E-ad7cf41c05ec3f64", "rated_matches": 60, "raw_elo_rating": 1576.0871543127037, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 55.065570137094625, "uncertainty": 20.268439966447993, "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": "2026-07-02T16:51:45Z", "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": 78, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 39, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 27, "model": "claude-opus-4-5", "point_rating_method": "sequential_elo", "public_id": "E-934b5bc34a7e20b9", "rated_matches": 78, "raw_elo_rating": 1525.0054661960344, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 50.01236594378325, "uncertainty": 12.5043950463012, "unilateral_faults": 0, "wins": 51 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 0, "losses": 26, "model": "claude-opus-4-5", "point_rating_method": "sequential_elo", "public_id": "E-a75e9d71efa4a6bc", "rated_matches": 56, "raw_elo_rating": 1510.566089787542, "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": 47.48779900953093, "uncertainty": 22.47661785325219, "unilateral_faults": 2, "wins": 30 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 0, "losses": 22, "model": "claude-opus-4-5", "point_rating_method": "sequential_elo", "public_id": "E-ccacc93776fb7c88", "rated_matches": 50, "raw_elo_rating": 1509.1560481862084, "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": 46.98778226570035, "uncertainty": 26.26400420140049, "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": "2026-07-02T16:51:45Z", "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": 86, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 41, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 48, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-233f9cae6335e53d", "rated_matches": 82, "raw_elo_rating": 1395.2014642843967, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 35.51777926697464, "uncertainty": 11.132129994845172, "unilateral_faults": 2, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 40, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-6774d700e60de31a", "rated_matches": 70, "raw_elo_rating": 1537.5424446121715, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 51.146338598706805, "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": "2026-07-02T16:51:45Z", "losses": 30, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-924d7e6ee41b562e", "rated_matches": 70, "raw_elo_rating": 1537.236926140518, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 51.11193183106644, "uncertainty": 15.58908290969266, "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": "2026-07-25T10:50:00Z", "losses": 15, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-09963ffe0b0fa5fd", "rated_matches": 64, "raw_elo_rating": 1848.732893856415, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 85.95057329747303, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 49 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "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": 62, "raw_elo_rating": 1783.7336347634437, "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": 78.54251452521142, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 45 }, { "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": 1986.3418503572475, "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": 1748.5260593214266, "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": 73.21774811489999, "uncertainty": 34.33688094430304, "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": "2026-07-25T10:50:00Z", "losses": 14, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-b53cb955b1d8baab", "rated_matches": 62, "raw_elo_rating": 1837.282768557701, "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": 84.57309131433091, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 48 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "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": 62, "raw_elo_rating": 1844.431383861268, "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": 85.37815146132921, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 51 }, { "admitted_plugin_count": 1, "attempted_matches": 80, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 40, "draws": 0, "generated_at": "2026-07-03T16:50:00Z", "losses": 41, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-c902807aab849f31", "rated_matches": 80, "raw_elo_rating": 1548.872594045111, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 52.76318675006037, "uncertainty": 11.805555555555554, "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": "2026-07-02T16:51:45Z", "losses": 31, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-e0a09b1ea3f11175", "rated_matches": 76, "raw_elo_rating": 1532.0402550957847, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 50.73920853170654, "uncertainty": 13.230288229818967, "unilateral_faults": 0, "wins": 45 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 28, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-e619c51e7d5d70d2", "rated_matches": 52, "raw_elo_rating": 1434.5922020031153, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 38.71073878713191, "uncertainty": 24.930281974344517, "unilateral_faults": 2, "wins": 24 }, { "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": 16, "model": "cohere/north-mini-code", "point_rating_method": "sequential_elo", "public_id": "E-a0518a43c688d1e2", "rated_matches": 42, "raw_elo_rating": 1507.503874989952, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "first_pass", "score": 46.23995635293639, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 0, "generated_at": "2026-07-01T00:15:48Z", "losses": 32, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-06a41d0e11b18b77", "rated_matches": 52, "raw_elo_rating": 1396.8569813632248, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 34.46108749309675, "uncertainty": 24.930281974344517, "unilateral_faults": 2, "wins": 20 }, { "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": 42, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-0dca18c79b6ac9d7", "rated_matches": 76, "raw_elo_rating": 1470.9876886709974, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 43.86361290746909, "uncertainty": 13.230288229818967, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 29, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-2c1cbd253f3a9d69", "rated_matches": 52, "raw_elo_rating": 1363.1128299523764, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 30.660900975633034, "uncertainty": 24.930281974344517, "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": "2026-07-02T06:10:40Z", "losses": 59, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-b306c8f5ffbbec38", "rated_matches": 72, "raw_elo_rating": 1273.5353446820234, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 21.48822632188929, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 13 }, { "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": 32, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-b3d889b0631db85f", "rated_matches": 78, "raw_elo_rating": 1554.0311357346932, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 53.28116819334009, "uncertainty": 12.5043950463012, "unilateral_faults": 0, "wins": 46 }, { "admitted_plugin_count": 1, "attempted_matches": 92, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 44, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 62, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-b8554f0ccf0845da", "rated_matches": 88, "raw_elo_rating": 1380.4056653616792, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 34.02108976107974, "uncertainty": 9.249894000318006, "unilateral_faults": 2, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 92, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 46, "draws": 0, "generated_at": "2026-07-01T00:15:48Z", "losses": 51, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-efa8d9109b008ee9", "rated_matches": 92, "raw_elo_rating": 1438.0999111227916, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 40.62229553055088, "uncertainty": 8.09758473652126, "unilateral_faults": 0, "wins": 41 }, { "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": 24, "model": "deepseek/deepseek-v4-pro", "point_rating_method": "sequential_elo", "public_id": "E-0ca4798825ceaccb", "rated_matches": 76, "raw_elo_rating": 1770.1139868621165, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 77.55050909177413, "uncertainty": 13.230288229818967, "unilateral_faults": 0, "wins": 52 }, { "admitted_plugin_count": 1, "attempted_matches": 86, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 43, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 48, "model": "deepseek/deepseek-v4-pro", "point_rating_method": "sequential_elo", "public_id": "E-da5f3b1a4e370e1a", "rated_matches": 86, "raw_elo_rating": 1400.7555461917282, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 36.25827225605603, "uncertainty": 9.855626741889738, "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": "2026-07-02T16:51:45Z", "losses": 43, "model": "google/gemini-3.1-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-7603462aff103041", "rated_matches": 70, "raw_elo_rating": 1292.0994540643576, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 23.50512954504209, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 27 }, { "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": 36, "model": "google/gemini-3.1-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-a72dd193e1dc4331", "rated_matches": 40, "raw_elo_rating": 1220.515329898098, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 13.754428661395163, "uncertainty": 34.33688094430304, "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": "2026-07-02T16:51:45Z", "losses": 36, "model": "google/gemini-3.1-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-d979b43c3aeea657", "rated_matches": 52, "raw_elo_rating": 1272.024034199102, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 20.402696248566944, "uncertainty": 24.930281974344517, "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": 82, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 41, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 46, "model": "google/gemini-3.5-flash", "point_rating_method": "sequential_elo", "public_id": "E-a7ce764239377b3f", "rated_matches": 82, "raw_elo_rating": 1474.9857181649531, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 44.502893226762005, "uncertainty": 11.132129994845172, "unilateral_faults": 0, "wins": 36 }, { "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": 22, "model": "google/gemini-3.5-flash", "point_rating_method": "sequential_elo", "public_id": "E-b50da126631c1ea1", "rated_matches": 42, "raw_elo_rating": 1449.780390545928, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 39.73927406715561, "uncertainty": 32.49928516630233, "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": 78, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 37, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 38, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-c311887ca24f8a76", "rated_matches": 74, "raw_elo_rating": 1366.5570300915422, "reasoning": "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": 32.03488163738203, "uncertainty": 13.985026918962571, "unilateral_faults": 2, "wins": 36 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 36, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-e3c1bc55ae62b8db", "rated_matches": 70, "raw_elo_rating": 1361.044656121879, "reasoning": "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": 31.26957512593088, "uncertainty": 15.58908290969266, "unilateral_faults": 2, "wins": 34 }, { "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": 78, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 39, "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": 78, "raw_elo_rating": 1828.180387590261, "reasoning": "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": 84.15520849708763, "uncertainty": 12.5043950463012, "unilateral_faults": 0, "wins": 63 }, { "admitted_plugin_count": 1, "attempted_matches": 80, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 40, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 42, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-c7d3f2597dfefeb3", "rated_matches": 80, "raw_elo_rating": 1600.666830764492, "reasoning": "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": 58.59613118143334, "uncertainty": 11.805555555555554, "unilateral_faults": 0, "wins": 38 }, { "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": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 45, "model": "google/gemma-4-31b-it", "point_rating_method": "sequential_elo", "public_id": "E-e8e17fbbdd12faa4", "rated_matches": 70, "raw_elo_rating": 1284.119780904192, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 22.606477627919652, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 26, "model": "google/gemma-4-31b-it", "point_rating_method": "sequential_elo", "public_id": "E-fd1bc1e2e6ac48fb", "rated_matches": 52, "raw_elo_rating": 1529.4989801817678, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 49.398915664339874, "uncertainty": 24.930281974344517, "unilateral_faults": 6, "wins": 26 }, { "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": "gpt-4.1", "point_rating_method": "sequential_elo", "public_id": "E-1b9f1f7b70f02927", "rated_matches": 52, "raw_elo_rating": 1322.2740939222144, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 26.061739119033867, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 20 }, { "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": 32, "model": "gpt-5", "point_rating_method": "sequential_elo", "public_id": "E-9e5b308c41a36374", "rated_matches": 66, "raw_elo_rating": 1594.6561013740363, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 57.42107172094892, "uncertainty": 17.33472217815261, "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": "2026-07-02T16:51:45Z", "losses": 14, "model": "gpt-5", "point_rating_method": "sequential_elo", "public_id": "E-c5ad048b6fb4e93d", "rated_matches": 42, "raw_elo_rating": 1659.4999295403002, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 63.35739250290029, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "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": 88, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 44, "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": 88, "raw_elo_rating": 1767.2078133828695, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 77.5818327751585, "uncertainty": 9.249894000318006, "unilateral_faults": 0, "wins": 63 }, { "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": 34, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-cafab3c275850d3b", "rated_matches": 70, "raw_elo_rating": 1535.7359811804806, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 50.942898959824795, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 36 }, { "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": 4, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-f6403f7a30e19e82", "rated_matches": 66, "raw_elo_rating": 1949.760418649385, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 97.41208001073208, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 62 }, { "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-0791f6b66243ec1a", "rated_matches": 64, "raw_elo_rating": 1461.2661835118558, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 42.31498884641358, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 30 }, { "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": 47, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-427bdffeacc6c394", "rated_matches": 68, "raw_elo_rating": 1289.0925360366127, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 23.08957126865442, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 21 }, { "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": 39, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-481582e8f8e3217e", "rated_matches": 74, "raw_elo_rating": 1562.7396128928744, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 54.1285000853822, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 35 }, { "admitted_plugin_count": 1, "attempted_matches": 80, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 41, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-539afc540807da47", "rated_matches": 72, "raw_elo_rating": 1368.6051517630897, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 32.19476312847781, "uncertainty": 14.770573598065289, "unilateral_faults": 4, "wins": 31 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 37, "draws": 0, "generated_at": "2026-07-01T00:15:48Z", "losses": 36, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-8ed627956c0a0292", "rated_matches": 74, "raw_elo_rating": 1391.2479155648975, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 34.81551075849012, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 38 }, { "admitted_plugin_count": 1, "attempted_matches": 88, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 44, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 46, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-95d1a872f51b78e7", "rated_matches": 88, "raw_elo_rating": 1458.205063342578, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 42.782673944191146, "uncertainty": 9.249894000318006, "unilateral_faults": 0, "wins": 42 }, { "admitted_plugin_count": 1, "attempted_matches": 86, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 43, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 52, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-cdd304da89074d54", "rated_matches": 86, "raw_elo_rating": 1357.1978658786666, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 31.352909325386037, "uncertainty": 9.855626741889738, "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": "2026-07-01T00:15:48Z", "losses": 38, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-ce84b7a3c6105fb2", "rated_matches": 64, "raw_elo_rating": 1400.4932946391689, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 35.47088984657748, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 82, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 41, "draws": 0, "generated_at": "2026-07-09T17:30:50Z", "losses": 59, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-3311575b341ee4a8", "rated_matches": 82, "raw_elo_rating": 1319.4297397884322, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 26.98454687571744, "uncertainty": 11.132129994845172, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 84, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 42, "draws": 0, "generated_at": "2026-07-01T00:15:48Z", "losses": 56, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-49b3c6006a3b9fcc", "rated_matches": 84, "raw_elo_rating": 1380.0275715590533, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 33.86744888185659, "uncertainty": 10.482614454664043, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 73, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 37, "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": 73, "raw_elo_rating": 1586.2542378517353, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 56.741633620377705, "uncertainty": 14.373819371909642, "unilateral_faults": 0, "wins": 38 }, { "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": 50, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-6c37eeef15b82287", "rated_matches": 68, "raw_elo_rating": 1255.8506947784497, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 19.345953732481064, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 51, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-83cfa14483bf0d43", "rated_matches": 64, "raw_elo_rating": 1245.267602758152, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 17.98973957943594, "uncertainty": 18.26736729460423, "unilateral_faults": 2, "wins": 13 }, { "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": 17, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-8e40431df091d53f", "rated_matches": 74, "raw_elo_rating": 1754.4732503803718, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 75.72108883514751, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 57 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 0, "generated_at": "2026-07-09T17:30:50Z", "losses": 44, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-a0d8c8fd6b01598c", "rated_matches": 72, "raw_elo_rating": 1401.8017054794216, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 35.93328048880792, "uncertainty": 14.770573598065289, "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": "2026-07-09T17:30:50Z", "losses": 27, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-b05a7e0987de9967", "rated_matches": 72, "raw_elo_rating": 1685.5719142551734, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 67.89081020463259, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 45 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "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-ff2b4db95370e3d6", "rated_matches": 68, "raw_elo_rating": 1303.70499708439, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 24.73519206926743, "uncertainty": 16.4429265428846, "unilateral_faults": 2, "wins": 22 }, { "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": 31, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-6f42dbbf02274b56", "rated_matches": 74, "raw_elo_rating": 1594.0645150033788, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 57.656236468847425, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 43 }, { "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": 17, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-762e9d80a60b41ed", "rated_matches": 72, "raw_elo_rating": 1833.5200064511591, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 84.55237440881977, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 55 }, { "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": 27, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-ffa82d1e96e897ab", "rated_matches": 70, "raw_elo_rating": 1666.0116361417768, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 65.61423508293475, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 43 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 33, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-25a83ddaeb1268a4", "rated_matches": 72, "raw_elo_rating": 1586.9806489073471, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 56.78769509728259, "uncertainty": 14.770573598065289, "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": "2026-07-10T05:30:29Z", "losses": 61, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-59156a669808a24f", "rated_matches": 66, "raw_elo_rating": 1084.779723090878, "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": 17.33472217815261, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 33, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-e917387a1c57aa23", "rated_matches": 62, "raw_elo_rating": 1580.9116397569835, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 55.70118117875034, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 37, "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": 74, "raw_elo_rating": 1611.7895712923712, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 59.65239038336131, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 49 }, { "admitted_plugin_count": 1, "attempted_matches": 80, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 40, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 25, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-af9c2c2998294ad0", "rated_matches": 80, "raw_elo_rating": 1726.1579161055558, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 72.72864039076802, "uncertainty": 11.805555555555554, "unilateral_faults": 0, "wins": 55 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 37, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 29, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-d61f8454991c5422", "rated_matches": 74, "raw_elo_rating": 1637.7720719272563, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 62.57847814892709, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 45 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 26, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-012ecb9ce0709c05", "rated_matches": 72, "raw_elo_rating": 1634.0374245901774, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 62.08711787214945, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 46 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 37, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 27, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-1f00b423eab1c19d", "rated_matches": 74, "raw_elo_rating": 1599.653295433683, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 58.28563170186785, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 47 }, { "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-terra", "point_rating_method": "sequential_elo", "public_id": "E-9664e98d37ece097", "rated_matches": 66, "raw_elo_rating": 1556.1844675568093, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 53.08848731670678, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 35 }, { "admitted_plugin_count": 1, "attempted_matches": 78, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 39, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 62, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-067ab716d64e3e9a", "rated_matches": 78, "raw_elo_rating": 1239.039256360454, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 17.80752778276196, "uncertainty": 12.5043950463012, "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": 82, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 37, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 46, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-8cc657b7db4428cb", "rated_matches": 74, "raw_elo_rating": 1344.4909352072373, "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": 29.549850224043485, "uncertainty": 13.985026918962571, "unilateral_faults": 4, "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": "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": 94, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 47, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 42, "model": "minimax/minimax-m3", "point_rating_method": "sequential_elo", "public_id": "E-33797d7b77c7800c", "rated_matches": 94, "raw_elo_rating": 1478.69665172829, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 45.24363611055831, "uncertainty": 7.54891760425771, "unilateral_faults": 0, "wins": 52 }, { "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": "minimax/minimax-m3", "point_rating_method": "sequential_elo", "public_id": "E-fb8ac45946e32e22", "rated_matches": 38, "raw_elo_rating": 1224.8792762545324, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 14.067752272340876, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 4 }, { "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": "mistralai/mistral-medium-3-5", "point_rating_method": "sequential_elo", "public_id": "E-1954b83d439b455c", "rated_matches": 42, "raw_elo_rating": 1179.3522444981809, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 9.284295898021144, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 94, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 47, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 53, "model": "mistralai/mistral-medium-3-5", "point_rating_method": "sequential_elo", "public_id": "E-4a7d37b86196302f", "rated_matches": 94, "raw_elo_rating": 1414.8804142848849, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 38.05680239306483, "uncertainty": 7.54891760425771, "unilateral_faults": 0, "wins": 41 }, { "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": "moonshotai/kimi-k2.7-code", "point_rating_method": "sequential_elo", "public_id": "E-952fba19b28982d5", "rated_matches": 38, "raw_elo_rating": 1549.3907801120831, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 50.61347027563539, "uncertainty": 36.31407690254356, "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": "2026-07-18T00:14:00Z", "losses": 27, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-288f9a63e6b6cae3", "rated_matches": 56, "raw_elo_rating": 1515.7955265246053, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "score": 48.07672580576763, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 24, "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": 48, "raw_elo_rating": 1695.0977713005702, "reasoning": "low", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "low", "repair_status": "first_pass", "score": 67.80065514605346, "uncertainty": 27.67857142857143, "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": "2026-07-21T14:43:57Z", "losses": 19, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-4a1443311507f194", "rated_matches": 38, "raw_elo_rating": 1552.219483093816, "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": 50.93203211475854, "uncertainty": 36.31407690254356, "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": "2026-07-21T14:20:15Z", "losses": 14, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-91be72471ad409b6", "rated_matches": 48, "raw_elo_rating": 1664.197870454584, "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": 64.32078139975053, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 47, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 0, "generated_at": "2026-07-17T22:08:39Z", "losses": 21, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-95ac38f534c0080f", "rated_matches": 47, "raw_elo_rating": 1509.7234507830926, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "score": 46.85754887233867, "uncertainty": 28.418783648703226, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 30, "model": "nex-agi/nex-n2-pro", "point_rating_method": "sequential_elo", "public_id": "E-5f76f577111bee8d", "rated_matches": 38, "raw_elo_rating": 1286.863854304965, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 21.048308841388355, "uncertainty": 36.31407690254356, "unilateral_faults": 2, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 90, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 45, "draws": 0, "generated_at": "2026-07-11T17:22:09Z", "losses": 47, "model": "nex-agi/nex-n2-pro", "point_rating_method": "sequential_elo", "public_id": "E-962a9da8812a74d4", "rated_matches": 90, "raw_elo_rating": 1460.6854546643076, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 43.1147735572218, "uncertainty": 8.664241836095918, "unilateral_faults": 0, "wins": 43 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 17, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-4477e0de2e04aad4", "rated_matches": 54, "raw_elo_rating": 1547.5175821569976, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 51.541673218867665, "uncertainty": 23.66998624632421, "unilateral_faults": 2, "wins": 37 }, { "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": 34, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-48ed5c5e00ef38fb", "rated_matches": 42, "raw_elo_rating": 1277.3343405722885, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 20.31880780262193, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 0, "generated_at": "2026-07-11T17:22:09Z", "losses": 28, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-da3b98638ff53ea9", "rated_matches": 42, "raw_elo_rating": 1340.928743214023, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 27.48065900945308, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 14 }, { "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": 1511.7322847617274, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 48.16273316433884, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 36 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 0, "generated_at": "2026-07-03T16:00:00Z", "losses": 28, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-4fc62dc65156d576", "rated_matches": 52, "raw_elo_rating": 1450.5284147399018, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 40.5054373719154, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 0, "generated_at": "2026-07-21T14:20:15Z", "losses": 12, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-b556333d605791f4", "rated_matches": 48, "raw_elo_rating": 1672.7981964551377, "reasoning": "low", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "low", "repair_status": "first_pass", "score": 65.28932977173861, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 36 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 0, "generated_at": "2026-07-21T14:20:15Z", "losses": 27, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-172336d3fd38632a", "rated_matches": 48, "raw_elo_rating": 1361.7503235309423, "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": 30.259854038877847, "uncertainty": 27.67857142857143, "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": "2026-07-02T16:51:45Z", "losses": 35, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-5ef540286ecbb63d", "rated_matches": 68, "raw_elo_rating": 1423.8445683656728, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 38.26502642302819, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 33 }, { "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": 21, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-1ca53619662c7f6f", "rated_matches": 74, "raw_elo_rating": 1717.6790913377977, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 71.57741767232629, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 53 }, { "admitted_plugin_count": 1, "attempted_matches": 76, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 37, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-21623e96b2b104e9", "rated_matches": 72, "raw_elo_rating": 1397.8682571935017, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 35.49030484656112, "uncertainty": 14.770573598065289, "unilateral_faults": 2, "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": "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": 48, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 29, "model": "qwen/qwen3.7-max", "point_rating_method": "sequential_elo", "public_id": "E-435ec29661cdc285", "rated_matches": 48, "raw_elo_rating": 1509.8875319944243, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 46.94271606979717, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 19 }, { "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": 38, "model": "qwen/qwen3.7-max", "point_rating_method": "sequential_elo", "public_id": "E-c577c41440c17864", "rated_matches": 76, "raw_elo_rating": 1546.3265864598327, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 52.348101378726525, "uncertainty": 13.230288229818967, "unilateral_faults": 0, "wins": 38 }, { "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": 22, "model": "qwen/qwen3.7-plus", "point_rating_method": "sequential_elo", "public_id": "E-6cc7454f585005c4", "rated_matches": 50, "raw_elo_rating": 1498.8448079056152, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 45.82655477428856, "uncertainty": 26.26400420140049, "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": "2026-07-02T16:51:45Z", "losses": 41, "model": "qwen/qwen3.7-plus", "point_rating_method": "sequential_elo", "public_id": "E-94daaf1196d89c6c", "rated_matches": 78, "raw_elo_rating": 1403.12799966028, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 36.28681393707585, "uncertainty": 12.5043950463012, "unilateral_faults": 0, "wins": 37 }, { "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": 24, "model": "stepfun/step-3.7-flash", "point_rating_method": "sequential_elo", "public_id": "E-358338a9fbdbcb6a", "rated_matches": 42, "raw_elo_rating": 1468.455994851599, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 41.84247645099394, "uncertainty": 32.49928516630233, "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": "2026-07-21T14:20:15Z", "losses": 30, "model": "stepfun/step-3.7-flash", "point_rating_method": "sequential_elo", "public_id": "E-386b7a319dfe25ad", "rated_matches": 48, "raw_elo_rating": 1356.3943755691175, "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": 29.656679847743195, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 18 }, { "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": 26, "model": "stepfun/step-3.7-flash", "point_rating_method": "sequential_elo", "public_id": "E-7b9b33921ba865f5", "rated_matches": 66, "raw_elo_rating": 1583.6391550622056, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 56.18036928549278, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 40 }, { "admitted_plugin_count": 1, "attempted_matches": 102, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 51, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 69, "model": "tencent/hy3-preview", "point_rating_method": "sequential_elo", "public_id": "E-1bb81f8a4ae78954", "rated_matches": 102, "raw_elo_rating": 1351.9190552018522, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 31.14935515682644, "uncertainty": 5.516463908214657, "unilateral_faults": 0, "wins": 33 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 0, "generated_at": "2026-07-03T19:10:00Z", "losses": 23, "model": "tencent/hy3-preview", "point_rating_method": "sequential_elo", "public_id": "E-92dc0ac61d798488", "rated_matches": 52, "raw_elo_rating": 1489.1164768211524, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 44.85113365186623, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 37, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-01a1df4eac0e6aef", "rated_matches": 70, "raw_elo_rating": 1348.1334066224467, "reasoning": "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": 29.815540746047837, "uncertainty": 15.58908290969266, "unilateral_faults": 2, "wins": 33 }, { "admitted_plugin_count": 1, "attempted_matches": 76, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 38, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 44, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-0f05573125dedc2b", "rated_matches": 76, "raw_elo_rating": 1430.9712174685433, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 39.357052570878395, "uncertainty": 13.230288229818967, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugin_count": 1, "attempted_matches": 76, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 38, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 43, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-ae60ed096a69eeff", "rated_matches": 76, "raw_elo_rating": 1391.529556899853, "reasoning": "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": 34.91522604827307, "uncertainty": 13.230288229818967, "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": "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": 76, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 38, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 50, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-f7a1d86c7e241f8d", "rated_matches": 76, "raw_elo_rating": 1462.3133546536524, "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": 42.886729927679795, "uncertainty": 13.230288229818967, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 90, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 45, "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-824ec3caceabd338", "rated_matches": 90, "raw_elo_rating": 1651.5268455955904, "reasoning": "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": 64.60687961024074, "uncertainty": 8.664241836095918, "unilateral_faults": 0, "wins": 56 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 0, "generated_at": "2026-07-18T00:06:00Z", "losses": 21, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-87d1c39ddc685d7b", "rated_matches": 42, "raw_elo_rating": 1549.543321271408, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 50.97433935801821, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "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": 70, "raw_elo_rating": 1777.9603866057128, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 78.22163856984506, "uncertainty": 15.58908290969266, "unilateral_faults": 2, "wins": 52 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 0, "generated_at": "2026-07-18T00:06:00Z", "losses": 25, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-bd7fcc801178eba2", "rated_matches": 54, "raw_elo_rating": 1518.5692090151308, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 48.28157590668977, "uncertainty": 23.66998624632421, "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": "2026-07-18T00:06:00Z", "losses": 27, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-c0bc4ff29a3cbf96", "rated_matches": 72, "raw_elo_rating": 1728.9654475477987, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 72.777687286115, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 45 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 25, "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": 50, "raw_elo_rating": 1615.4876782359684, "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": 58.96259893763863, "uncertainty": 26.26400420140049, "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": "2026-07-21T14:20:15Z", "losses": 3, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-fcfafa8fb4ccd299", "rated_matches": 46, "raw_elo_rating": 1849.6069103410052, "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": 85.06561420733325, "uncertainty": 29.182495748947275, "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": 17, "model": "x-ai/grok-build-0.1", "point_rating_method": "sequential_elo", "public_id": "E-4aac1b6621aeae38", "rated_matches": 38, "raw_elo_rating": 1590.3330337676452, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 55.224290042358746, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 21 }, { "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": 30, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-09d406abc15f7c9a", "rated_matches": 76, "raw_elo_rating": 1612.214190816547, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 59.768207538630506, "uncertainty": 13.230288229818967, "unilateral_faults": 0, "wins": 46 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 37, "draws": 0, "generated_at": "2026-07-01T00:15:48Z", "losses": 47, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-9490f08c56c27d13", "rated_matches": 74, "raw_elo_rating": 1305.8159334017118, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 25.194362997981777, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 27 }, { "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": 20, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-ad48cf51fe7da3cc", "rated_matches": 40, "raw_elo_rating": 1449.1737668928254, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 39.50540099410975, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 82, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 39, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 43, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-be8fc9653466bbe1", "rated_matches": 78, "raw_elo_rating": 1403.3936759128974, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 36.316733768246415, "uncertainty": 12.5043950463012, "unilateral_faults": 2, "wins": 35 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 24, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-faaa866ee28d6401", "rated_matches": 38, "raw_elo_rating": 1396.9773694745934, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 33.44903247030231, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 14 }, { "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": "xiaomi/mimo-v2.5-pro", "point_rating_method": "sequential_elo", "public_id": "E-9c228ad72a159b33", "rated_matches": 38, "raw_elo_rating": 1439.2285062039607, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 38.20725555292037, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 98, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 49, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 55, "model": "xiaomi/mimo-v2.5-pro", "point_rating_method": "sequential_elo", "public_id": "E-af55f57b03605914", "rated_matches": 98, "raw_elo_rating": 1350.1016690927315, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 30.855904278592035, "uncertainty": 6.501890762960602, "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": "2026-07-01T00:15:48Z", "losses": 25, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-1a8c2012f200fd88", "rated_matches": 56, "raw_elo_rating": 1639.7406049749611, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 62.035127375812706, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 31 }, { "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": 42, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-235e4beedf22bc99", "rated_matches": 76, "raw_elo_rating": 1576.055795890647, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 55.69613462686788, "uncertainty": 13.230288229818967, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 0, "generated_at": "2026-07-11T14:00:45Z", "losses": 26, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-38e323f4ce233fa1", "rated_matches": 52, "raw_elo_rating": 1444.743330661769, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 39.85393488638997, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 0, "generated_at": "2026-07-11T17:22:09Z", "losses": 27, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-3916ba303b2ff700", "rated_matches": 52, "raw_elo_rating": 1545.7295977101912, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 51.22676942040723, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 25 }, { "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": 43, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-503ecd021099d8f9", "rated_matches": 70, "raw_elo_rating": 1411.5878999859724, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 36.96163570089199, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 27 }, { "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": 33, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-51c8f79c1671819e", "rated_matches": 76, "raw_elo_rating": 1570.0501335274976, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 55.01979113661367, "uncertainty": 13.230288229818967, "unilateral_faults": 0, "wins": 43 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 0, "generated_at": "2026-07-01T00:15:48Z", "losses": 29, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-6370c4b68d38a97e", "rated_matches": 52, "raw_elo_rating": 1368.3671536085135, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 31.252630477831257, "uncertainty": 24.930281974344517, "unilateral_faults": 2, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 32, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-a6655b3c71893984", "rated_matches": 52, "raw_elo_rating": 1406.828924920958, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 35.584104190112406, "uncertainty": 24.930281974344517, "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": "2026-07-02T16:51:45Z", "losses": 22, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-d8655d29a4806df8", "rated_matches": 52, "raw_elo_rating": 1593.3125482263345, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 56.58544876045006, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 30 } ], "GB2-06": [ { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "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": 60, "raw_elo_rating": 1718.7719507864515, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 81.83872215206208, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 40 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "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": 56, "raw_elo_rating": 1680.7525107491392, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 76.68664750233343, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 36 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 4, "losses": 20, "model": "claude-opus-4-5", "point_rating_method": "sequential_elo", "public_id": "E-1ff6d6f973c7157d", "rated_matches": 50, "raw_elo_rating": 1495.5978004143442, "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": 52.317732875616365, "uncertainty": 26.26400420140049, "unilateral_faults": 1, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 78, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 39, "draws": 3, "generated_at": "2026-07-02T16:51:45Z", "losses": 36, "model": "claude-opus-4-5", "point_rating_method": "sequential_elo", "public_id": "E-40a259ca8a40b5b4", "rated_matches": 78, "raw_elo_rating": 1491.4086342006274, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 53.20069535861266, "uncertainty": 12.5043950463012, "unilateral_faults": 0, "wins": 39 }, { "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": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 6, "losses": 27, "model": "claude-opus-4-5", "point_rating_method": "sequential_elo", "public_id": "E-df9bde92610963b7", "rated_matches": 54, "raw_elo_rating": 1452.1410674136998, "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": 46.95904470055364, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "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": 64, "raw_elo_rating": 1707.1649512901192, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 80.54297967705504, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 42 }, { "admitted_plugin_count": 1, "attempted_matches": 82, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 41, "draws": 5, "generated_at": "2026-07-02T16:51:45Z", "losses": 33, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-db414178442322d3", "rated_matches": 82, "raw_elo_rating": 1514.105193415293, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 56.281940805437515, "uncertainty": 11.132129994845172, "unilateral_faults": 0, "wins": 44 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "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": 58, "raw_elo_rating": 1716.028915302819, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 81.37204287643961, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 39 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 13, "generated_at": "2026-07-25T10:50:00Z", "losses": 8, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-ca8985adf5006428", "rated_matches": 60, "raw_elo_rating": 1785.4552045796995, "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": 90.4738514404464, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 39 }, { "admitted_plugin_count": 1, "attempted_matches": 76, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 38, "draws": 3, "generated_at": "2026-07-02T16:51:45Z", "losses": 33, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-01597b81edc004dd", "rated_matches": 76, "raw_elo_rating": 1485.0135108536388, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 52.29736118277051, "uncertainty": 13.230288229818967, "unilateral_faults": 0, "wins": 40 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 2, "generated_at": "2026-07-02T16:51:45Z", "losses": 23, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-500304c7462c6005", "rated_matches": 46, "raw_elo_rating": 1516.9982745147104, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 54.78663788327743, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 90, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 45, "draws": 10, "generated_at": "2026-07-03T16:50:00Z", "losses": 39, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-51f3682dc3b76107", "rated_matches": 90, "raw_elo_rating": 1502.9657308011708, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 55.09510200081964, "uncertainty": 8.664241836095918, "unilateral_faults": 0, "wins": 41 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 1, "generated_at": "2026-07-02T16:51:45Z", "losses": 29, "model": "cohere/north-mini-code", "point_rating_method": "sequential_elo", "public_id": "E-78dfcb6ce8b3efaa", "rated_matches": 36, "raw_elo_rating": 1259.9497701926696, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "first_pass", "score": 20.540191912025133, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 6 }, { "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": 48, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-5f5fd61f4544b8d7", "rated_matches": 70, "raw_elo_rating": 1304.3081774256607, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 28.65261343605491, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 22 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 2, "generated_at": "2026-07-02T06:10:40Z", "losses": 26, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-6f20412107151172", "rated_matches": 46, "raw_elo_rating": 1368.8044629251704, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 35.5963217241142, "uncertainty": 29.182495748947275, "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": "2026-07-01T00:15:48Z", "losses": 39, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-8daa317358045ed1", "rated_matches": 62, "raw_elo_rating": 1342.4504929366262, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 33.21319976929683, "uncertainty": 19.244078834871203, "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": "2026-07-01T00:15:48Z", "losses": 34, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-d8ca2fcf88af96c7", "rated_matches": 48, "raw_elo_rating": 1254.222955779497, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 20.914421729563475, "uncertainty": 27.67857142857143, "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": "2026-07-02T16:51:45Z", "losses": 50, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-db0efb02339d9e80", "rated_matches": 64, "raw_elo_rating": 1184.1074694015106, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 12.80979743959458, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 14 }, { "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": 45, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-f527097ad30176f4", "rated_matches": 62, "raw_elo_rating": 1329.244669375893, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 31.50311534300162, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 6, "generated_at": "2026-07-02T16:51:45Z", "losses": 14, "model": "deepseek/deepseek-v4-pro", "point_rating_method": "sequential_elo", "public_id": "E-945bebaa34963e03", "rated_matches": 68, "raw_elo_rating": 1694.0603780225329, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 79.03501098478921, "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": 2, "generated_at": "2026-07-02T16:51:45Z", "losses": 36, "model": "deepseek/deepseek-v4-pro", "point_rating_method": "sequential_elo", "public_id": "E-c9778645f1bbd12c", "rated_matches": 64, "raw_elo_rating": 1411.0223538755488, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 42.19407690153233, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 37, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 32, "model": "google/gemini-3.1-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-6238c7d8dc9e77d9", "rated_matches": 37, "raw_elo_rating": 1259.0217150803967, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 20.53280700393271, "uncertainty": 37.360710565381275, "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": "2026-07-02T16:51:45Z", "losses": 41, "model": "google/gemini-3.1-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-a10101fbca309818", "rated_matches": 64, "raw_elo_rating": 1393.3523465645424, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 39.905904249814974, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 1, "generated_at": "2026-07-02T16:51:45Z", "losses": 21, "model": "google/gemini-3.1-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-dc1c0f46738d1091", "rated_matches": 46, "raw_elo_rating": 1412.2766689959317, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 41.225742883378615, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 12, "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": 56, "raw_elo_rating": 1754.720265023284, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 86.26508114189525, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 35 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "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": 38, "raw_elo_rating": 1632.226637510412, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 68.96930081774572, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 21 }, { "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": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 1, "generated_at": "2026-07-24T13:40:00Z", "losses": 39, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-100ff33157ca87e5", "rated_matches": 66, "raw_elo_rating": 1322.0096348955046, "reasoning": "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": 30.76401786245334, "uncertainty": 17.33472217815261, "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": "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": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 1, "generated_at": "2026-07-24T13:40:00Z", "losses": 37, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-92d447632fa55355", "rated_matches": 68, "raw_elo_rating": 1478.9003989696714, "reasoning": "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": 51.17292971070997, "uncertainty": 16.4429265428846, "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-3.5-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": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 10, "generated_at": "2026-07-24T13:40:00Z", "losses": 29, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-aa5fab059f4d0186", "rated_matches": 70, "raw_elo_rating": 1538.8753432667752, "reasoning": "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": 59.02782293210099, "uncertainty": 15.58908290969266, "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-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": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 6, "generated_at": "2026-07-24T13:40:00Z", "losses": 15, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-dd9886be3d9e45b5", "rated_matches": 70, "raw_elo_rating": 1855.2757109550505, "reasoning": "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": 15.58908290969266, "unilateral_faults": 0, "wins": 49 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 29, "model": "google/gemma-4-31b-it", "point_rating_method": "sequential_elo", "public_id": "E-41987f96551bf9d3", "rated_matches": 38, "raw_elo_rating": 1306.0485900110548, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 26.73096583903303, "uncertainty": 36.31407690254356, "unilateral_faults": 1, "wins": 9 }, { "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": 46, "model": "google/gemma-4-31b-it", "point_rating_method": "sequential_elo", "public_id": "E-da266f7bbd330107", "rated_matches": 70, "raw_elo_rating": 1369.8707689668845, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 37.14262287973516, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 9, "generated_at": "2026-07-02T16:51:45Z", "losses": 17, "model": "gpt-4.1", "point_rating_method": "sequential_elo", "public_id": "E-4dcd6d3653c67437", "rated_matches": 48, "raw_elo_rating": 1509.3680825685708, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 53.954368519741806, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 22 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 23, "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": 46, "raw_elo_rating": 1599.685910965938, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 65.49425022506708, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 78, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 39, "draws": 8, "generated_at": "2026-07-02T16:51:45Z", "losses": 36, "model": "gpt-5", "point_rating_method": "sequential_elo", "public_id": "E-816d262cd933cdb9", "rated_matches": 78, "raw_elo_rating": 1505.6333421063478, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 55.04271992802316, "uncertainty": 12.5043950463012, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "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": 63, "raw_elo_rating": 1654.8715395144725, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 73.72126024399091, "uncertainty": 18.75, "unilateral_faults": 1, "wins": 42 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "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": 58, "raw_elo_rating": 1815.6398626593548, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 94.2711346278566, "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": 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": 56, "raw_elo_rating": 1795.1084078077092, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 91.4951323889829, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 39 }, { "admitted_plugin_count": 1, "attempted_matches": 82, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 41, "draws": 5, "generated_at": "2026-07-01T00:15:48Z", "losses": 42, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-050fceb6ddf16bc3", "rated_matches": 82, "raw_elo_rating": 1422.45955765613, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 44.41431485019834, "uncertainty": 11.132129994845172, "unilateral_faults": 0, "wins": 35 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 9, "generated_at": "2026-07-02T06:10:40Z", "losses": 17, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-0b7e07d12feb8fb5", "rated_matches": 70, "raw_elo_rating": 1658.2754812633734, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 74.48951038736966, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 44 }, { "admitted_plugin_count": 1, "attempted_matches": 80, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 40, "draws": 4, "generated_at": "2026-07-02T16:51:45Z", "losses": 41, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-144154b792c9e9a6", "rated_matches": 80, "raw_elo_rating": 1422.0682161048328, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 44.29387414191289, "uncertainty": 11.805555555555554, "unilateral_faults": 0, "wins": 35 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 7, "generated_at": "2026-07-02T16:51:45Z", "losses": 23, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-3ccfe46cbdc271eb", "rated_matches": 66, "raw_elo_rating": 1495.052182852292, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 53.17211418347611, "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": "2026-07-01T00:15:48Z", "losses": 33, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-ac7c887de3c2e7af", "rated_matches": 70, "raw_elo_rating": 1591.0072908848572, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 65.77863489957281, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 37 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 1, "generated_at": "2026-07-02T06:10:40Z", "losses": 37, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-e726e4bfd20b0da9", "rated_matches": 70, "raw_elo_rating": 1340.587052453575, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 33.35053620500806, "uncertainty": 15.58908290969266, "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": "2026-07-02T16:51:45Z", "losses": 44, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-eca073d7ce610515", "rated_matches": 68, "raw_elo_rating": 1442.576048285256, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 46.46911808434478, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 2, "generated_at": "2026-07-02T06:10:40Z", "losses": 23, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-3d7e23d6ea4c2792", "rated_matches": 68, "raw_elo_rating": 1625.0398154861382, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 70.09721255481617, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 43 }, { "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": 1583.9245150143784, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 64.14793329235812, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 5, "generated_at": "2026-07-02T06:10:40Z", "losses": 36, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-962a93f9cc008820", "rated_matches": 72, "raw_elo_rating": 1495.5982818808066, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 53.50846608657866, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 31 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 10, "generated_at": "2026-07-01T00:15:48Z", "losses": 35, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-9b6b064b63e4164b", "rated_matches": 68, "raw_elo_rating": 1513.2031076340502, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 55.61494936945502, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 88, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 41, "draws": 2, "generated_at": "2026-07-09T17:30:50Z", "losses": 39, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-9c5263dcfd4c2ec7", "rated_matches": 82, "raw_elo_rating": 1493.0082221112164, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 53.54999441048698, "uncertainty": 11.132129994845172, "unilateral_faults": 3, "wins": 41 }, { "admitted_plugin_count": 1, "attempted_matches": 80, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 40, "draws": 0, "generated_at": "2026-07-09T17:30:50Z", "losses": 49, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-a1fb59d78d39d217", "rated_matches": 77, "raw_elo_rating": 1375.5414747998316, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 38.159271786120144, "uncertainty": 12.86385170722978, "unilateral_faults": 1, "wins": 28 }, { "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": 18, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-d5866895bf388f66", "rated_matches": 66, "raw_elo_rating": 1667.896647873528, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 75.55455981019395, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 48 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "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": 58, "raw_elo_rating": 1706.2621455889364, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 80.10729776560946, "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": 38, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-1ea2c2c23d752166", "rated_matches": 64, "raw_elo_rating": 1439.3647361655196, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 45.864265764444326, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 8, "generated_at": "2026-07-02T16:51:45Z", "losses": 20, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-4175a77ccf4c269b", "rated_matches": 70, "raw_elo_rating": 1740.1552092126217, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 85.09250284379188, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 42 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 13, "generated_at": "2026-07-10T05:30:29Z", "losses": 16, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-9eafeacabdedfdba", "rated_matches": 60, "raw_elo_rating": 1693.5550142801062, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 78.57326201623226, "uncertainty": 20.268439966447993, "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": "2026-07-10T05:30:29Z", "losses": 52, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-ae522f9c5c491f57", "rated_matches": 62, "raw_elo_rating": 1151.0525414647095, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 8.428175606914639, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "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": 64, "raw_elo_rating": 1618.383682351255, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 69.04627410160604, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 86, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 43, "draws": 1, "generated_at": "2026-07-10T05:30:29Z", "losses": 51, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-992b9a5ebbb74c80", "rated_matches": 86, "raw_elo_rating": 1400.8514714375945, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 41.748422117643045, "uncertainty": 9.855626741889738, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 10, "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": 60, "raw_elo_rating": 1699.206178915541, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 79.30505799919712, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 37 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "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": 58, "raw_elo_rating": 1692.6757781194096, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 78.34793491234177, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 31 }, { "admitted_plugin_count": 1, "attempted_matches": 78, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 39, "draws": 1, "generated_at": "2026-07-10T05:30:29Z", "losses": 47, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-22ffdca36d9bac9c", "rated_matches": 78, "raw_elo_rating": 1345.2675207188454, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 34.27619276645788, "uncertainty": 12.5043950463012, "unilateral_faults": 0, "wins": 30 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 12, "generated_at": "2026-07-10T05:30:29Z", "losses": 20, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-a3722334e358f0fe", "rated_matches": 66, "raw_elo_rating": 1504.8244147827002, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 54.43756662250657, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 34 }, { "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": 1645.4373743096698, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 73.14660395348105, "uncertainty": 12.5043950463012, "unilateral_faults": 0, "wins": 49 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 3, "generated_at": "2026-07-24T13:40:00Z", "losses": 40, "model": "inclusionai/ling-3.0-flash", "point_rating_method": "sequential_elo", "public_id": "E-6807fffacebac165", "rated_matches": 70, "raw_elo_rating": 1368.0002176088735, "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": 36.90039635511072, "uncertainty": 15.58908290969266, "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-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": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 63, "model": "inclusionai/ling-3.0-flash", "point_rating_method": "sequential_elo", "public_id": "E-9bde0475193e2c4a", "rated_matches": 66, "raw_elo_rating": 1084.4399654313177, "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": 17.33472217815261, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 2, "generated_at": "2026-07-24T13:40:00Z", "losses": 43, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-3e8b2d11481a50d7", "rated_matches": 70, "raw_elo_rating": 1449.8704786885137, "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": 47.502162901902345, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 25 }, { "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": 72, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 14, "generated_at": "2026-07-24T13:40:00Z", "losses": 29, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-e3023ff7ecf82fc4", "rated_matches": 72, "raw_elo_rating": 1529.236235750301, "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": 57.86440350919441, "uncertainty": 14.770573598065289, "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": "2026-07-02T16:51:45Z", "losses": 28, "model": "minimax/minimax-m3", "point_rating_method": "sequential_elo", "public_id": "E-ef8c1a9fa3580f83", "rated_matches": 38, "raw_elo_rating": 1304.7191377341055, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 26.55880878848199, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 10 }, { "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": 31, "model": "mistralai/mistral-medium-3-5", "point_rating_method": "sequential_elo", "public_id": "E-6c35f5ff426e7ada", "rated_matches": 38, "raw_elo_rating": 1276.7474041824191, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 22.93661698020659, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 5, "generated_at": "2026-07-02T16:51:45Z", "losses": 37, "model": "mistralai/mistral-medium-3-5", "point_rating_method": "sequential_elo", "public_id": "E-cf0bc4a1e7a8d72a", "rated_matches": 68, "raw_elo_rating": 1319.423486454839, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 30.52151155484641, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "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": 38, "raw_elo_rating": 1688.0709353285413, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "score": 76.20084253545677, "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": 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": 36, "raw_elo_rating": 1761.865034837106, "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": 85.53556864418464, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 3, "generated_at": "2026-07-24T14:00:00Z", "losses": 25, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-1640f1438f9390d7", "rated_matches": 54, "raw_elo_rating": 1495.0343771699572, "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": 52.51350184357782, "uncertainty": 23.66998624632421, "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": "2026-07-21T14:20:15Z", "losses": 5, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-2f8c760ee4329d00", "rated_matches": 41, "raw_elo_rating": 1793.063355178339, "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": 90.0985190987841, "uncertainty": 33.40167498104595, "unilateral_faults": 1, "wins": 36 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 4, "generated_at": "2026-07-17T22:36:00Z", "losses": 13, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-3f2124a8621f4c67", "rated_matches": 40, "raw_elo_rating": 1603.2184180725008, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "score": 65.41771870952734, "uncertainty": 34.33688094430304, "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": "2026-07-24T14:00:00Z", "losses": 22, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-95a5c0e17cd4b70a", "rated_matches": 58, "raw_elo_rating": 1523.8597797113378, "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": 56.48715444231329, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 3, "generated_at": "2026-07-02T16:51:45Z", "losses": 27, "model": "nex-agi/nex-n2-pro", "point_rating_method": "sequential_elo", "public_id": "E-209380b737b62580", "rated_matches": 38, "raw_elo_rating": 1288.6932218313036, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 24.483537293564577, "uncertainty": 36.31407690254356, "unilateral_faults": 1, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 2, "generated_at": "2026-07-11T17:22:09Z", "losses": 47, "model": "nex-agi/nex-n2-pro", "point_rating_method": "sequential_elo", "public_id": "E-973417dedd770061", "rated_matches": 70, "raw_elo_rating": 1316.479215503516, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 30.228698605833657, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 5, "generated_at": "2026-07-02T16:51:45Z", "losses": 28, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-1ea0c8193f35ca72", "rated_matches": 70, "raw_elo_rating": 1566.120201385086, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 62.55588820955038, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 37 }, { "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": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-6e76a1c11ba24bc6", "rated_matches": 46, "raw_elo_rating": 1359.117852968085, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 34.3419568785575, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 37, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 2, "generated_at": "2026-07-11T17:22:09Z", "losses": 21, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-ba2fb1c121873708", "rated_matches": 37, "raw_elo_rating": 1419.633107652117, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 41.331134337274186, "uncertainty": 37.360710565381275, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 4, "generated_at": "2026-07-03T16:00:00Z", "losses": 17, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-4162fe183e6383e1", "rated_matches": 38, "raw_elo_rating": 1458.9852716129876, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 46.53545862314014, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugin_count": 1, "attempted_matches": 76, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 38, "draws": 12, "generated_at": "2026-07-02T16:51:45Z", "losses": 30, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-69e964db7b91b1bb", "rated_matches": 76, "raw_elo_rating": 1538.5869987807794, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 59.23484500914308, "uncertainty": 13.230288229818967, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 1, "generated_at": "2026-07-21T14:20:15Z", "losses": 4, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-e4a4a86669325de4", "rated_matches": 41, "raw_elo_rating": 1801.1941168780218, "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": 91.1514098096587, "uncertainty": 33.40167498104595, "unilateral_faults": 0, "wins": 36 }, { "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": 1545.5402070118414, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 59.053740144696384, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 1, "generated_at": "2026-07-21T14:20:15Z", "losses": 33, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-b75de88bfc62ab22", "rated_matches": 60, "raw_elo_rating": 1489.4394058512037, "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": 52.1413684252918, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 1, "generated_at": "2026-07-02T16:51:45Z", "losses": 44, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-f225b6990e542d31", "rated_matches": 66, "raw_elo_rating": 1349.1726611844706, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 34.28148635006266, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 2, "generated_at": "2026-07-24T13:40:00Z", "losses": 34, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-a29031412bc33c39", "rated_matches": 68, "raw_elo_rating": 1339.4494417733786, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 33.11476703447791, "uncertainty": 16.4429265428846, "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": "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": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 41, "model": "qwen/qwen3.7-max", "point_rating_method": "sequential_elo", "public_id": "E-0c7e9f6c7d4cb892", "rated_matches": 66, "raw_elo_rating": 1331.436946958018, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 31.98480499971793, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 4, "generated_at": "2026-07-02T16:51:45Z", "losses": 23, "model": "qwen/qwen3.7-max", "point_rating_method": "sequential_elo", "public_id": "E-8283efe6f68a787e", "rated_matches": 44, "raw_elo_rating": 1497.2982048390093, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 52.06950812237848, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 17 }, { "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": 59, "model": "qwen/qwen3.7-plus", "point_rating_method": "sequential_elo", "public_id": "E-2fb82a23fdec2792", "rated_matches": 78, "raw_elo_rating": 1329.0543202231288, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 32.17666890559334, "uncertainty": 12.5043950463012, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 6, "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": 38, "raw_elo_rating": 1586.5622739195126, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 63.05600683389494, "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": "2026-07-02T16:51:45Z", "losses": 26, "model": "stepfun/step-3.7-flash", "point_rating_method": "sequential_elo", "public_id": "E-2d684425ca56be18", "rated_matches": 38, "raw_elo_rating": 1364.8232167706008, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 34.341969682948694, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 1, "generated_at": "2026-07-02T16:51:45Z", "losses": 43, "model": "stepfun/step-3.7-flash", "point_rating_method": "sequential_elo", "public_id": "E-6526762dce98da7c", "rated_matches": 66, "raw_elo_rating": 1358.4283980930004, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 35.48005541077814, "uncertainty": 17.33472217815261, "unilateral_faults": 1, "wins": 22 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 0, "generated_at": "2026-07-21T14:20:15Z", "losses": 28, "model": "stepfun/step-3.7-flash", "point_rating_method": "sequential_elo", "public_id": "E-8a88dceef8a0239c", "rated_matches": 42, "raw_elo_rating": 1341.761233690627, "reasoning": "low", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "low", "repair_status": "repaired", "score": 31.75076094863466, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 14 }, { "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": 33, "model": "tencent/hy3-preview", "point_rating_method": "sequential_elo", "public_id": "E-3627e3dbf7a48738", "rated_matches": 38, "raw_elo_rating": 1240.6039192958517, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 18.256226519717732, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 5 }, { "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": 40, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-02be9616e86c7055", "rated_matches": 70, "raw_elo_rating": 1419.683927091336, "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": 43.593163850651706, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 30 }, { "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": 39, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-0825a2443d50c563", "rated_matches": 68, "raw_elo_rating": 1343.2749498156031, "reasoning": "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": 33.61015012782225, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 29 }, { "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": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "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": 62, "raw_elo_rating": 1738.0636778057162, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 84.44301843000522, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 43 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 3, "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": 42, "raw_elo_rating": 1588.4968458398534, "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": 63.70171999396187, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 94, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 47, "draws": 9, "generated_at": "2026-07-24T14:00:00Z", "losses": 46, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-3baaff3521870bef", "rated_matches": 94, "raw_elo_rating": 1479.471903029175, "reasoning": "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": 52.16831822774484, "uncertainty": 7.54891760425771, "unilateral_faults": 0, "wins": 39 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 4, "generated_at": "2026-07-24T14:00:00Z", "losses": 25, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-5a1e23bce371a184", "rated_matches": 48, "raw_elo_rating": 1466.526062035418, "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": 48.40655306031008, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "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": 56, "raw_elo_rating": 1572.8669502398702, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 62.71603703638642, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 31 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 5, "generated_at": "2026-07-17T22:36:00Z", "losses": 35, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-8cb8510a257ade6a", "rated_matches": 72, "raw_elo_rating": 1520.051662375247, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 56.67504975033097, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 1, "generated_at": "2026-07-21T14:20:15Z", "losses": 16, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-9eb453b88beb68a4", "rated_matches": 42, "raw_elo_rating": 1597.027458180251, "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": 64.80638925165604, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 25 }, { "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": 1479.2712311236176, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 49.55757958350315, "uncertainty": 32.49928516630233, "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": 23, "model": "x-ai/grok-build-0.1", "point_rating_method": "sequential_elo", "public_id": "E-133675db0ee21fd5", "rated_matches": 38, "raw_elo_rating": 1373.8468233302583, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 35.51047908909959, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 7, "generated_at": "2026-07-02T06:10:40Z", "losses": 20, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-51421c7ae2af8f7b", "rated_matches": 46, "raw_elo_rating": 1510.9452000729912, "reasoning": "highest", "reasoning_bracket": "highest", "reasoning_setting": "highest", "repair_status": "repaired", "score": 54.00279670242382, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 4, "generated_at": "2026-07-02T16:51:45Z", "losses": 27, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-7b4c450b6850f156", "rated_matches": 38, "raw_elo_rating": 1291.006145934247, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 24.783048752994254, "uncertainty": 36.31407690254356, "unilateral_faults": 1, "wins": 7 }, { "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": 35, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-d572bc902e0e416b", "rated_matches": 58, "raw_elo_rating": 1357.045266862595, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 34.885555784666536, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 22 }, { "admitted_plugin_count": 1, "attempted_matches": 76, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 38, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 51, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-d79ad8bc05d1b933", "rated_matches": 76, "raw_elo_rating": 1394.8106074391387, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 40.61656144874905, "uncertainty": 13.230288229818967, "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": "2026-07-01T00:15:48Z", "losses": 22, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-ff7683792b6b3363", "rated_matches": 66, "raw_elo_rating": 1622.5314133163806, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 69.68000145685647, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 44 }, { "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": "xiaomi/mimo-v2.5-pro", "point_rating_method": "sequential_elo", "public_id": "E-530f82d65699c577", "rated_matches": 38, "raw_elo_rating": 1577.5838949262898, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 61.893354158802424, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 84, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 42, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 41, "model": "xiaomi/mimo-v2.5-pro", "point_rating_method": "sequential_elo", "public_id": "E-6b662c734cdcff91", "rated_matches": 84, "raw_elo_rating": 1470.1028400149814, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 50.65115543258182, "uncertainty": 10.482614454664043, "unilateral_faults": 0, "wins": 43 }, { "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": 38, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-18454080fac44f8c", "rated_matches": 46, "raw_elo_rating": 1171.824448870106, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 10.08844992968959, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 4, "generated_at": "2026-07-11T14:00:45Z", "losses": 21, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-657c61c9039ce566", "rated_matches": 46, "raw_elo_rating": 1472.5353616420934, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 49.02892542395991, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 6, "generated_at": "2026-07-02T06:10:40Z", "losses": 21, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-6954e92d5890c32a", "rated_matches": 46, "raw_elo_rating": 1511.653239266157, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 54.094484039595265, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 7, "generated_at": "2026-07-02T06:10:40Z", "losses": 16, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-72584b5bdb2d01e3", "rated_matches": 46, "raw_elo_rating": 1684.8010698527362, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 76.51621390529917, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 23, "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": 46, "raw_elo_rating": 1621.1969574486914, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 68.27981716939979, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 27 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 3, "generated_at": "2026-07-02T16:51:45Z", "losses": 19, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-ec1479c855f477b4", "rated_matches": 46, "raw_elo_rating": 1607.0088479011472, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 66.44253189413912, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "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": 56, "raw_elo_rating": 1641.3436578799765, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 71.58340912876453, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 33 } ], "GB2-07": [ { "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": 26, "model": "claude-fable-5", "point_rating_method": "sequential_elo", "public_id": "E-babd82321b910e7b", "rated_matches": 66, "raw_elo_rating": 1607.2707269530913, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 61.74570340856937, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 40 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 16, "model": "claude-fable-5", "point_rating_method": "sequential_elo", "public_id": "E-bc12a8303ec2def7", "rated_matches": 62, "raw_elo_rating": 1732.9026765072072, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 76.98200491889094, "uncertainty": 19.244078834871203, "unilateral_faults": 2, "wins": 46 }, { "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": 34, "model": "claude-opus-4-5", "point_rating_method": "sequential_elo", "public_id": "E-ca22621c58b6f244", "rated_matches": 68, "raw_elo_rating": 1503.5474590816427, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 49.099189369518875, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 0, "losses": 28, "model": "claude-opus-4-5", "point_rating_method": "sequential_elo", "public_id": "E-e7848fdc8b4ffd95", "rated_matches": 56, "raw_elo_rating": 1514.3526890353978, "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": 49.833142253565896, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 0, "losses": 24, "model": "claude-opus-4-5", "point_rating_method": "sequential_elo", "public_id": "E-e8719bed57f17312", "rated_matches": 44, "raw_elo_rating": 1460.922068025896, "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": 42.45739172020174, "uncertainty": 30.785599249992988, "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": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 21, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-0bf7b9ed307db853", "rated_matches": 64, "raw_elo_rating": 1663.2800319802798, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 68.53036352739291, "uncertainty": 18.26736729460423, "unilateral_faults": 1, "wins": 43 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 0, "generated_at": "2026-07-03T17:20:00Z", "losses": 21, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-5e09cecd1172d99b", "rated_matches": 60, "raw_elo_rating": 1641.587990360725, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 65.67069489296186, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 39 }, { "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": 25, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-76804598cce96e62", "rated_matches": 70, "raw_elo_rating": 1632.6918398913665, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 65.03810238045806, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 45 }, { "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": 1916.2342017734409, "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": 98.00725670704736, "uncertainty": 34.33688094430304, "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": "2026-07-25T10:50:00Z", "losses": 4, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-54bca3ce32fa85ae", "rated_matches": 58, "raw_elo_rating": 1922.0717818058629, "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": 21.344455490411935, "unilateral_faults": 0, "wins": 54 }, { "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": 20, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-914b104a64ab3110", "rated_matches": 58, "raw_elo_rating": 1760.002791541305, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 80.1027947182233, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 38 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 0, "generated_at": "2026-07-25T10:50:00Z", "losses": 21, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-de5e72176c4f0dc9", "rated_matches": 60, "raw_elo_rating": 1775.6096922481513, "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": 82.12453538591619, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 39 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 0, "generated_at": "2026-07-03T16:50:00Z", "losses": 42, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-2146a36b46e938d6", "rated_matches": 70, "raw_elo_rating": 1408.057840072436, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 37.459792671933386, "uncertainty": 15.58908290969266, "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": "2026-07-02T16:51:45Z", "losses": 33, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-9e40526fba9fa8b9", "rated_matches": 78, "raw_elo_rating": 1495.9673153967922, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 48.555402065964, "uncertainty": 12.5043950463012, "unilateral_faults": 0, "wins": 45 }, { "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": 22, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-cd6f193a087d8c8d", "rated_matches": 48, "raw_elo_rating": 1573.5069374964892, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 56.58459268593973, "uncertainty": 27.67857142857143, "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": "2026-07-02T16:51:45Z", "losses": 23, "model": "cohere/north-mini-code", "point_rating_method": "sequential_elo", "public_id": "E-1c961fde1b53f0eb", "rated_matches": 48, "raw_elo_rating": 1483.908738760916, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 45.58462439953901, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 25 }, { "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": 44, "model": "cohere/north-mini-code", "point_rating_method": "sequential_elo", "public_id": "E-3b908f26a42804a4", "rated_matches": 80, "raw_elo_rating": 1472.3535265304024, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 45.72497508816168, "uncertainty": 11.805555555555554, "unilateral_faults": 0, "wins": 36 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 0, "generated_at": "2026-07-11T17:22:09Z", "losses": 60, "model": "cohere/north-mini-code", "point_rating_method": "sequential_elo", "public_id": "E-c7f5dc6d5d3c2a8d", "rated_matches": 74, "raw_elo_rating": 1198.2973912049488, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 11.8650523130411, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 14 }, { "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": 40, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-20285efe5ad468c1", "rated_matches": 68, "raw_elo_rating": 1403.9709488893493, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 36.87418407205407, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 0, "generated_at": "2026-07-01T00:15:48Z", "losses": 37, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-8f2f6c973751f183", "rated_matches": 48, "raw_elo_rating": 1368.9649637776126, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 31.4729804448763, "uncertainty": 27.67857142857143, "unilateral_faults": 1, "wins": 11 }, { "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": 43, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-8f6a725b68dde85b", "rated_matches": 68, "raw_elo_rating": 1389.6727978939712, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 35.11880048485162, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugin_count": 1, "attempted_matches": 80, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 39, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 46, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-c394c0713cfcfaa4", "rated_matches": 80, "raw_elo_rating": 1404.5796614045998, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 37.40437961245555, "uncertainty": 11.805555555555554, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 82, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 41, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 43, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-c8fd55a5d257c569", "rated_matches": 82, "raw_elo_rating": 1420.6304474348074, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 39.4410753019693, "uncertainty": 11.132129994845172, "unilateral_faults": 0, "wins": 39 }, { "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": 27, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-ecf2a6ea6f9fe06c", "rated_matches": 64, "raw_elo_rating": 1602.0602420013795, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 61.01441166930439, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 37 }, { "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": 29, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-edc2d085c4253ed3", "rated_matches": 48, "raw_elo_rating": 1475.8883667633174, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 44.59996355965882, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 86, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 43, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 46, "model": "deepseek/deepseek-v4-pro", "point_rating_method": "sequential_elo", "public_id": "E-f398fd6ac8c8bada", "rated_matches": 86, "raw_elo_rating": 1579.7533840085564, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 59.10196667088018, "uncertainty": 9.855626741889738, "unilateral_faults": 0, "wins": 40 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 32, "model": "deepseek/deepseek-v4-pro", "point_rating_method": "sequential_elo", "public_id": "E-f76d96b0f3163d4b", "rated_matches": 72, "raw_elo_rating": 1455.8188321632083, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 43.40379899145002, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 40 }, { "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": 30, "model": "google/gemini-3.1-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-0d43f308cfa4da52", "rated_matches": 42, "raw_elo_rating": 1371.4066804602294, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 31.29927882215666, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 12 }, { "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": 52, "model": "google/gemini-3.1-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-1b3c52da51dfbdd4", "rated_matches": 62, "raw_elo_rating": 1146.8224295367877, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 5.028949824704899, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 10 }, { "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": 44, "model": "google/gemini-3.1-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-3d6a15fe821fe6ad", "rated_matches": 48, "raw_elo_rating": 1112.6076468036076, "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": 27.67857142857143, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 88, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 42, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 41, "model": "google/gemini-3.5-flash", "point_rating_method": "sequential_elo", "public_id": "E-5447c508e2b0ab6c", "rated_matches": 84, "raw_elo_rating": 1491.1934866603465, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 48.1678904051992, "uncertainty": 10.482614454664043, "unilateral_faults": 2, "wins": 43 }, { "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": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 21, "model": "google/gemini-3.5-flash", "point_rating_method": "sequential_elo", "public_id": "E-f7f306cca2bb9532", "rated_matches": 42, "raw_elo_rating": 1620.9930296932216, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 61.9409877518634, "uncertainty": 32.49928516630233, "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": "2026-07-24T13:40:00Z", "losses": 39, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-2950a4947ff48aa6", "rated_matches": 68, "raw_elo_rating": 1296.472599345917, "reasoning": "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": 23.676614784886056, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 29 }, { "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": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 45, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-42943e41c64d22d2", "rated_matches": 70, "raw_elo_rating": 1215.7211439442203, "reasoning": "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": 13.846622010261695, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 25 }, { "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": 72, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 33, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-5f208f03ea700603", "rated_matches": 72, "raw_elo_rating": 1497.5221396698407, "reasoning": "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": 48.52371285673669, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 39 }, { "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": 29, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-65c6c8e09fe2c210", "rated_matches": 74, "raw_elo_rating": 1437.6843580559512, "reasoning": "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": 41.25458336053536, "uncertainty": 13.985026918962571, "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": "2026-07-24T13:40:00Z", "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": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 41, "model": "google/gemma-4-31b-it", "point_rating_method": "sequential_elo", "public_id": "E-3f820f7e8ff15839", "rated_matches": 66, "raw_elo_rating": 1341.3548030169743, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 29.09921306138233, "uncertainty": 17.33472217815261, "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": 17, "model": "google/gemma-4-31b-it", "point_rating_method": "sequential_elo", "public_id": "E-f417d302c870dfa6", "rated_matches": 38, "raw_elo_rating": 1465.5446251098992, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 42.481918086546386, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 21 }, { "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": 22, "model": "gpt-4.1", "point_rating_method": "sequential_elo", "public_id": "E-fcfa606d3cbb0ba0", "rated_matches": 48, "raw_elo_rating": 1491.4730488103537, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 46.513294527136985, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 26 }, { "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": 29, "model": "gpt-5", "point_rating_method": "sequential_elo", "public_id": "E-15dad0db253c0497", "rated_matches": 56, "raw_elo_rating": 1513.9390847536845, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 49.78236406777454, "uncertainty": 22.47661785325219, "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": "2026-07-02T16:51:45Z", "losses": 27, "model": "gpt-5", "point_rating_method": "sequential_elo", "public_id": "E-4d8b4cfcff519db6", "rated_matches": 68, "raw_elo_rating": 1569.3972507863089, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 57.18356640655226, "uncertainty": 16.4429265428846, "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": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "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": 60, "raw_elo_rating": 1590.5823542815288, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 59.4087344158915, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 36 }, { "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": 6, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-80aa3ec3ac4ad97f", "rated_matches": 68, "raw_elo_rating": 1856.3853633771, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 92.41708874989084, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 62 }, { "admitted_plugin_count": 1, "attempted_matches": 84, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 42, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 49, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-c8176c382cf75e88", "rated_matches": 84, "raw_elo_rating": 1377.5240664717653, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 34.212698952097796, "uncertainty": 10.482614454664043, "unilateral_faults": 0, "wins": 35 }, { "admitted_plugin_count": 1, "attempted_matches": 78, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 37, "draws": 0, "generated_at": "2026-07-01T00:15:48Z", "losses": 45, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-022243613d51f0fb", "rated_matches": 78, "raw_elo_rating": 1349.6658377833614, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 30.593973859680652, "uncertainty": 12.5043950463012, "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": "2026-07-02T06:10:40Z", "losses": 22, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-1b33882368041bb3", "rated_matches": 66, "raw_elo_rating": 1626.8346327510485, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 64.14756356170453, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 44 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 52, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-6a87ebc54bdde781", "rated_matches": 68, "raw_elo_rating": 1229.885941388591, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 15.50177269916906, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 71, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 36, "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": 71, "raw_elo_rating": 1456.3300135701293, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 43.42678008215959, "uncertainty": 15.175565098878964, "unilateral_faults": 0, "wins": 31 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 37, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 43, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-b96fbceba82aa188", "rated_matches": 74, "raw_elo_rating": 1467.8534887025785, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 44.958446663865594, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 31 }, { "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": 50, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-c2ab31787514c10c", "rated_matches": 66, "raw_elo_rating": 1233.8027831068532, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 15.895054664836817, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 16 }, { "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": 31, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-e453890c6dd35fa3", "rated_matches": 70, "raw_elo_rating": 1673.8683195169865, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 70.0933376019181, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 39 }, { "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": 34, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-f4d7ac8a0f5d2974", "rated_matches": 68, "raw_elo_rating": 1497.7232695380007, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 48.38415378645852, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 82, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 41, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 47, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-4e14ae758717169e", "rated_matches": 82, "raw_elo_rating": 1466.9726248764337, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 45.13050309599317, "uncertainty": 11.132129994845172, "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": "2026-07-02T06:10:40Z", "losses": 53, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-acb1779a65c941b4", "rated_matches": 60, "raw_elo_rating": 1156.9962119959694, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 6.177376175757823, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 7 }, { "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": 32, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-b9e3f57bc887c6ae", "rated_matches": 70, "raw_elo_rating": 1621.1065450200133, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 63.61577606171604, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 38 }, { "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": 55, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-bea6d7d9558897f9", "rated_matches": 64, "raw_elo_rating": 1157.3137747604587, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 6.412900654814086, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 76, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 0, "generated_at": "2026-07-01T00:15:48Z", "losses": 57, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-c4ad375a0a870e69", "rated_matches": 72, "raw_elo_rating": 1263.1233843711118, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 19.74658439830341, "uncertainty": 14.770573598065289, "unilateral_faults": 2, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 65, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 0, "generated_at": "2026-07-09T17:30:50Z", "losses": 31, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-ce04fd14b6f43868", "rated_matches": 65, "raw_elo_rating": 1588.4151682571646, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 59.38552715383896, "uncertainty": 17.79574548966636, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 41, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-ce2925d9379d2a5d", "rated_matches": 72, "raw_elo_rating": 1327.8725244447637, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 27.69583446619687, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 31 }, { "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": 43, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-e0e874b71d913c12", "rated_matches": 68, "raw_elo_rating": 1351.6091494472687, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 30.445727457857856, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 29, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-4edfe4117ad3e936", "rated_matches": 72, "raw_elo_rating": 1492.1662742344863, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 47.8661734110052, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 43 }, { "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": 8, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-6201278165db862a", "rated_matches": 70, "raw_elo_rating": 1830.6078371029448, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 89.33624367595237, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 62 }, { "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": 29, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-640b3078b8bce40e", "rated_matches": 66, "raw_elo_rating": 1671.308501921656, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 69.6076192029346, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 37 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 40, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-45c76cf9faaba10a", "rated_matches": 72, "raw_elo_rating": 1495.1492778934935, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 48.232396684579456, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 23, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-73a7b73c1df452ad", "rated_matches": 60, "raw_elo_rating": 1633.1851088462413, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 64.63907337067556, "uncertainty": 20.268439966447993, "unilateral_faults": 1, "wins": 37 }, { "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": 53, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-ea529147555b5f2e", "rated_matches": 68, "raw_elo_rating": 1213.9388734979989, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 13.543951632081598, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 92, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 46, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 30, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-1b522c9c14f3860c", "rated_matches": 92, "raw_elo_rating": 1579.5870696464758, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 59.254216074642976, "uncertainty": 8.09758473652126, "unilateral_faults": 0, "wins": 62 }, { "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": 31, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-bef852aad169a609", "rated_matches": 68, "raw_elo_rating": 1611.5214513976898, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 62.35515330622509, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 37 }, { "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": 25, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-cc78d54d18d4c3f1", "rated_matches": 60, "raw_elo_rating": 1620.732869774357, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 63.110312337324274, "uncertainty": 20.268439966447993, "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": "2026-07-10T05:30:29Z", "losses": 28, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-65bf9818e3e1b632", "rated_matches": 72, "raw_elo_rating": 1698.0816425356322, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 73.14639726550367, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 44 }, { "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": 41, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-8ebe8776c7d44d46", "rated_matches": 78, "raw_elo_rating": 1494.0340188618018, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 48.318051305868195, "uncertainty": 12.5043950463012, "unilateral_faults": 0, "wins": 37 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 30, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-aca193dd2a8774fb", "rated_matches": 62, "raw_elo_rating": 1415.0011967486844, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 37.95324937589321, "uncertainty": 19.244078834871203, "unilateral_faults": 1, "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": "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": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 34, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-c1f595f47c71e648", "rated_matches": 70, "raw_elo_rating": 1354.8088835261667, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 30.922419805526225, "uncertainty": 15.58908290969266, "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": 38, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-e2db910734ca5315", "rated_matches": 70, "raw_elo_rating": 1496.5580733489744, "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": 48.32496377045103, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 32 }, { "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": 43, "model": "minimax/minimax-m3", "point_rating_method": "sequential_elo", "public_id": "E-24e15c4d7490cdf3", "rated_matches": 76, "raw_elo_rating": 1411.2345057212497, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 38.08146314653779, "uncertainty": 13.230288229818967, "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": "2026-07-02T16:51:45Z", "losses": 22, "model": "minimax/minimax-m3", "point_rating_method": "sequential_elo", "public_id": "E-4547f4cedca403f9", "rated_matches": 40, "raw_elo_rating": 1491.106649402965, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 45.81435930794232, "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": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 42, "model": "mistralai/mistral-medium-3-5", "point_rating_method": "sequential_elo", "public_id": "E-d0d0df9d83b6e37e", "rated_matches": 42, "raw_elo_rating": 1137.8670302315995, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 2.6276226685145265, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 0 }, { "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": 21, "model": "moonshotai/kimi-k2.7-code", "point_rating_method": "sequential_elo", "public_id": "E-d35e87ebfc251f60", "rated_matches": 40, "raw_elo_rating": 1513.8720710304185, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 48.609269467549154, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 25, "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": 50, "raw_elo_rating": 1584.61656565071, "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": 58.08745451776987, "uncertainty": 26.26400420140049, "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": "2026-07-21T14:43:57Z", "losses": 14, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-3d2d4c8b0819b60b", "rated_matches": 38, "raw_elo_rating": 1630.5068984993, "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": 62.73433165449384, "uncertainty": 36.31407690254356, "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": "2026-07-17T22:36:00Z", "losses": 27, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-49105fbc7f72e6fe", "rated_matches": 54, "raw_elo_rating": 1544.0348616044523, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "score": 53.36001388500844, "uncertainty": 23.66998624632421, "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": "2026-07-24T14:00:00Z", "losses": 17, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-4cc8f48bf8bccc77", "rated_matches": 38, "raw_elo_rating": 1512.5751169614134, "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": 48.25585022091068, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 0, "generated_at": "2026-07-24T14:00:00Z", "losses": 31, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-4d8815930b656774", "rated_matches": 52, "raw_elo_rating": 1412.2381481716995, "reasoning": "low", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "low", "repair_status": "first_pass", "score": 37.055553984478195, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 0, "generated_at": "2026-07-17T22:36:00Z", "losses": 21, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-77d9c422124dcbfe", "rated_matches": 48, "raw_elo_rating": 1479.9441320255862, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "score": 45.09788974446648, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 27 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 0, "generated_at": "2026-07-21T14:20:15Z", "losses": 16, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-c00660d2a8eb25c9", "rated_matches": 44, "raw_elo_rating": 1588.5127334969732, "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": 58.12169405695604, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 37, "draws": 0, "generated_at": "2026-07-11T17:22:09Z", "losses": 23, "model": "nex-agi/nex-n2-pro", "point_rating_method": "sequential_elo", "public_id": "E-1006c453b0c3a745", "rated_matches": 74, "raw_elo_rating": 1677.0084877720944, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 70.63639989478703, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 51 }, { "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": "nex-agi/nex-n2-pro", "point_rating_method": "sequential_elo", "public_id": "E-d1f432cda667f27f", "rated_matches": 38, "raw_elo_rating": 1459.0637934091908, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 41.68626656471518, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 0, "generated_at": "2026-07-03T18:15:00Z", "losses": 36, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-0e1c7f89e1c19b69", "rated_matches": 48, "raw_elo_rating": 1325.8842408601347, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 26.183961329145713, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 12 }, { "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": 51, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-459f395cc0af6d2e", "rated_matches": 68, "raw_elo_rating": 1139.144947953933, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 4.361503540371355, "uncertainty": 16.4429265428846, "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": "2026-07-03T16:00:00Z", "losses": 30, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-312d25e3a9eeeee3", "rated_matches": 42, "raw_elo_rating": 1333.288936469953, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 26.619564486831397, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 0, "generated_at": "2026-07-21T14:20:15Z", "losses": 26, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-3fae70801895971d", "rated_matches": 50, "raw_elo_rating": 1384.6707866645224, "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": 33.54011697208183, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 24 }, { "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": "o3", "point_rating_method": "sequential_elo", "public_id": "E-f1e3e54a3d40556f", "rated_matches": 66, "raw_elo_rating": 1570.054537336516, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 57.17667287781976, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 36 }, { "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": 30, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-29bc7f4fdf0f7b14", "rated_matches": 42, "raw_elo_rating": 1331.052671295428, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 26.3450182755582, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 0, "generated_at": "2026-07-21T14:20:15Z", "losses": 28, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-759d747bb732d949", "rated_matches": 44, "raw_elo_rating": 1347.04247733592, "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": 28.47639764067811, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 16 }, { "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": 42, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-069a963abdd14cdf", "rated_matches": 70, "raw_elo_rating": 1496.6901741690908, "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": 48.3411817843441, "uncertainty": 15.58908290969266, "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": 30, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-d8e68d23876f6d21", "rated_matches": 72, "raw_elo_rating": 1591.0944960346465, "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": 60.01158836118017, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 42 }, { "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": 22, "model": "qwen/qwen3.7-max", "point_rating_method": "sequential_elo", "public_id": "E-3142a09c7f192060", "rated_matches": 72, "raw_elo_rating": 1780.423050630861, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 83.25544957333192, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 50 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 8, "model": "qwen/qwen3.7-max", "point_rating_method": "sequential_elo", "public_id": "E-59c7745eb1e91d63", "rated_matches": 38, "raw_elo_rating": 1713.3149966509693, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 72.90067948715259, "uncertainty": 36.31407690254356, "unilateral_faults": 2, "wins": 30 }, { "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": 43, "model": "qwen/qwen3.7-plus", "point_rating_method": "sequential_elo", "public_id": "E-737a66790985a5e6", "rated_matches": 68, "raw_elo_rating": 1226.7047132781258, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 15.111213415380366, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 25, "model": "qwen/qwen3.7-plus", "point_rating_method": "sequential_elo", "public_id": "E-9d091700cb41ece2", "rated_matches": 52, "raw_elo_rating": 1469.7323982620346, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 44.11412141740787, "uncertainty": 24.930281974344517, "unilateral_faults": 6, "wins": 27 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 0, "generated_at": "2026-07-21T14:20:15Z", "losses": 33, "model": "stepfun/step-3.7-flash", "point_rating_method": "sequential_elo", "public_id": "E-1140a7c92290e8f4", "rated_matches": 58, "raw_elo_rating": 1387.7648759569868, "reasoning": "low", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "low", "repair_status": "repaired", "score": 34.40315650889252, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 25 }, { "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": 34, "model": "stepfun/step-3.7-flash", "point_rating_method": "sequential_elo", "public_id": "E-6a5e44fe2dde4257", "rated_matches": 42, "raw_elo_rating": 1270.3439970507015, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 18.891816081480037, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 8 }, { "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": 31, "model": "tencent/hy3-preview", "point_rating_method": "sequential_elo", "public_id": "E-dfed1e345a939bcd", "rated_matches": 42, "raw_elo_rating": 1312.6965015166088, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 24.09143183881845, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 11 }, { "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": 45, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-062d41f517db2ccb", "rated_matches": 72, "raw_elo_rating": 1355.947726299098, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 31.142626191814056, "uncertainty": 14.770573598065289, "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-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": 76, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 37, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 36, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-6df2b00898e4ba3c", "rated_matches": 74, "raw_elo_rating": 1636.4932548974812, "reasoning": "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": 65.66234591796368, "uncertainty": 13.985026918962571, "unilateral_faults": 1, "wins": 38 }, { "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": 34, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-8ad2285ad59d87bf", "rated_matches": 66, "raw_elo_rating": 1437.950468340537, "reasoning": "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": 40.9582601198932, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 32 }, { "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": 18, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-0929811cef80813b", "rated_matches": 42, "raw_elo_rating": 1486.9924022493417, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 45.48973456773819, "uncertainty": 32.49928516630233, "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": "2026-07-17T22:36:00Z", "losses": 27, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-3cfeaacb3dbbab07", "rated_matches": 64, "raw_elo_rating": 1571.2333001327654, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 57.22978890113659, "uncertainty": 18.26736729460423, "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": "2026-07-24T14:00:00Z", "losses": 28, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-436a3933a93e10cd", "rated_matches": 54, "raw_elo_rating": 1579.7204087357854, "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": 57.74112748178963, "uncertainty": 23.66998624632421, "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": "2026-07-21T14:20:15Z", "losses": 7, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-7e2507a947914c49", "rated_matches": 44, "raw_elo_rating": 1716.430482163852, "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": 73.82615238826833, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 37 }, { "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": 14, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-8e7f3829f3e45642", "rated_matches": 42, "raw_elo_rating": 1695.9832479560628, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 71.14753469502215, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 76, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 0, "generated_at": "2026-07-17T22:36:00Z", "losses": 19, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-a1728c5ac67e11f3", "rated_matches": 72, "raw_elo_rating": 1707.131329228841, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 74.25742704101226, "uncertainty": 14.770573598065289, "unilateral_faults": 2, "wins": 53 }, { "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": 5, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-ca54791ad3682b4f", "rated_matches": 46, "raw_elo_rating": 1780.9617876853945, "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": 81.90610929109198, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 41 }, { "admitted_plugin_count": 1, "attempted_matches": 86, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 43, "draws": 0, "generated_at": "2026-07-24T14:00:00Z", "losses": 35, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-e58f3df122cf1d29", "rated_matches": 86, "raw_elo_rating": 1660.323910306573, "reasoning": "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": 68.9936078713067, "uncertainty": 9.855626741889738, "unilateral_faults": 0, "wins": 51 }, { "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": "x-ai/grok-build-0.1", "point_rating_method": "sequential_elo", "public_id": "E-37ae0129627ee16f", "rated_matches": 38, "raw_elo_rating": 1294.048013413273, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 21.42728399222184, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 11 }, { "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": 40, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-0984b025e9005f5b", "rated_matches": 70, "raw_elo_rating": 1306.2839817049132, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 24.965019002081572, "uncertainty": 15.58908290969266, "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": "2026-07-01T00:15:48Z", "losses": 18, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-345a5b25cbac7f3b", "rated_matches": 40, "raw_elo_rating": 1490.6626325299442, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "first_pass", "score": 45.75984736918924, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 22 }, { "admitted_plugin_count": 1, "attempted_matches": 82, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 41, "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": 82, "raw_elo_rating": 1480.5760444250511, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 46.80059452342257, "uncertainty": 11.132129994845172, "unilateral_faults": 0, "wins": 38 }, { "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": 23, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-fa1a93f7e4d57000", "rated_matches": 38, "raw_elo_rating": 1388.9895983217118, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 33.08325964565655, "uncertainty": 36.31407690254356, "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": 24, "model": "xiaomi/mimo-v2.5-pro", "point_rating_method": "sequential_elo", "public_id": "E-3b160130ae038271", "rated_matches": 44, "raw_elo_rating": 1493.8041478238345, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 46.49432371294967, "uncertainty": 30.785599249992988, "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": 22, "model": "xiaomi/mimo-v2.5-pro", "point_rating_method": "sequential_elo", "public_id": "E-83580d03385c6759", "rated_matches": 64, "raw_elo_rating": 1672.9945867330275, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 69.72301913548274, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 42 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 20, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-1d66fd51bbcbb370", "rated_matches": 50, "raw_elo_rating": 1671.561473858593, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 68.76167840226208, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 30 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 0, "generated_at": "2026-07-11T14:00:45Z", "losses": 21, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-62e8714f035ebc68", "rated_matches": 48, "raw_elo_rating": 1537.5715700070969, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 52.17280865097196, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 27 }, { "admitted_plugin_count": 1, "attempted_matches": 82, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 41, "draws": 0, "generated_at": "2026-07-11T14:00:45Z", "losses": 32, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-c81741d135c9dc9c", "rated_matches": 82, "raw_elo_rating": 1578.724896071838, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 58.85032622224363, "uncertainty": 11.132129994845172, "unilateral_faults": 0, "wins": 50 }, { "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": 29, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-cb438d112c0ea172", "rated_matches": 64, "raw_elo_rating": 1539.7607316995222, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 53.36590257816522, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 35 }, { "admitted_plugin_count": 1, "attempted_matches": 92, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 46, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 43, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-d96269dd04d644e0", "rated_matches": 92, "raw_elo_rating": 1604.195460142954, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 62.27538746938836, "uncertainty": 8.09758473652126, "unilateral_faults": 0, "wins": 49 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 0, "generated_at": "2026-07-01T00:15:48Z", "losses": 21, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-e10fd023695e8b0a", "rated_matches": 48, "raw_elo_rating": 1666.6515999245044, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 68.01996021804254, "uncertainty": 27.67857142857143, "unilateral_faults": 1, "wins": 27 }, { "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": 25, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-e31f275ab7ef3741", "rated_matches": 48, "raw_elo_rating": 1539.433180620169, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 52.401358532491955, "uncertainty": 27.67857142857143, "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": "2026-07-11T17:22:09Z", "losses": 20, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-ecd98326faa92bf4", "rated_matches": 48, "raw_elo_rating": 1505.709024570307, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 48.261044862471415, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 28 }, { "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": 20, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-f7579fbfcb1dcbb9", "rated_matches": 48, "raw_elo_rating": 1568.8284110167365, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 56.01021012434106, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 28 } ], "GB2-08": [ { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 35, "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": 70, "raw_elo_rating": 1927.1900602587184, "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": 15.58908290969266, "unilateral_faults": 0, "wins": 65 }, { "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": 12, "model": "claude-fable-5", "point_rating_method": "sequential_elo", "public_id": "E-9ccf296d44d35675", "rated_matches": 66, "raw_elo_rating": 1763.0396484548678, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 75.70490277082847, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 54 }, { "admitted_plugin_count": 1, "attempted_matches": 82, "capped_draws": 6, "coverage_status": "rated", "distinct_rated_opponents": 41, "draws": 6, "generated_at": "2026-07-02T16:51:45Z", "losses": 20, "model": "claude-opus-4-5", "point_rating_method": "sequential_elo", "public_id": "E-01b57d5e6655f927", "rated_matches": 82, "raw_elo_rating": 1661.7483294998035, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 61.56795396592303, "uncertainty": 11.132129994845172, "unilateral_faults": 0, "wins": 56 }, { "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": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 0, "losses": 11, "model": "claude-opus-4-5", "point_rating_method": "sequential_elo", "public_id": "E-72233463ddce5549", "rated_matches": 40, "raw_elo_rating": 1685.2932750025354, "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": 62.298969641085826, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 29 }, { "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": 1437.9330328144251, "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": 27.883876285156568, "uncertainty": 18.26736729460423, "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": "2026-07-03T17:20:00Z", "losses": 20, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-22dc6fe5ae5fb8b1", "rated_matches": 70, "raw_elo_rating": 1701.9428640249134, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 66.94349597864887, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 50 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 51, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 51, "generated_at": "2026-07-02T16:51:45Z", "losses": 9, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-c2dade0b97891d8a", "rated_matches": 64, "raw_elo_rating": 1443.6592609728195, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 28.724237840417203, "uncertainty": 18.26736729460423, "unilateral_faults": 1, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 82, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 41, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 23, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-c9d7578e8375d994", "rated_matches": 82, "raw_elo_rating": 1670.7429079994065, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 62.88796737924806, "uncertainty": 11.132129994845172, "unilateral_faults": 0, "wins": 59 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 0, "generated_at": "2026-07-25T10:50:00Z", "losses": 25, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-35a5bf9b35d5e1e8", "rated_matches": 62, "raw_elo_rating": 1698.3996599576496, "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": 65.99439182520574, "uncertainty": 19.244078834871203, "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": "2026-07-25T10:50:00Z", "losses": 27, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-5a7942274854aaa6", "rated_matches": 62, "raw_elo_rating": 1573.2699692206909, "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": 47.63078866300169, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 35 }, { "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": 1802.7270448826368, "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": 79.53314592026378, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 30 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "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": 64, "raw_elo_rating": 1799.0191312173206, "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": 80.8756305155602, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 48 }, { "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": 1590.1043440935753, "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": 48.32936944187184, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 55, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 55, "generated_at": "2026-07-02T16:51:45Z", "losses": 10, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-130fb40b1c7a4d39", "rated_matches": 72, "raw_elo_rating": 1438.7650526278594, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 28.416522587653844, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 86, "capped_draws": 48, "coverage_status": "rated", "distinct_rated_opponents": 43, "draws": 48, "generated_at": "2026-07-03T16:50:00Z", "losses": 28, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-b5805acb90227d50", "rated_matches": 86, "raw_elo_rating": 1466.5948946196706, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 33.07777506796782, "uncertainty": 9.855626741889738, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 48, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 48, "generated_at": "2026-07-02T16:51:45Z", "losses": 2, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-cf0ed4bbe4aaadd7", "rated_matches": 50, "raw_elo_rating": 1437.362421007031, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 26.861288109097305, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 55, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 55, "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": 68, "raw_elo_rating": 1447.898423960942, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 29.56056174566684, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 30, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 30, "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": 38, "raw_elo_rating": 1428.7402146058764, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "first_pass", "score": 24.415991454087557, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 44, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 44, "generated_at": "2026-07-02T16:51:45Z", "losses": 18, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-4375cf96eeb624e2", "rated_matches": 70, "raw_elo_rating": 1423.4125728363276, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 26.06734815221141, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 46, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 46, "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": 50, "raw_elo_rating": 1436.914374262004, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 26.79553430937692, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 76, "capped_draws": 63, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 63, "generated_at": "2026-07-02T06:10:40Z", "losses": 9, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-95b070e1c29e44f0", "rated_matches": 72, "raw_elo_rating": 1408.6028863434017, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 23.990026774405592, "uncertainty": 14.770573598065289, "unilateral_faults": 2, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 50, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 50, "generated_at": "2026-07-02T16:51:45Z", "losses": 16, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-a7310645c3b96434", "rated_matches": 70, "raw_elo_rating": 1421.8047486009973, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 25.83138939583402, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 60, "coverage_status": "rated", "distinct_rated_opponents": 37, "draws": 60, "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": 74, "raw_elo_rating": 1438.9170506943865, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 28.531056604920728, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 43, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 43, "generated_at": "2026-07-01T00:15:48Z", "losses": 6, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-d28ef17ff6995c62", "rated_matches": 50, "raw_elo_rating": 1432.6903506163824, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 26.175631123177716, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 54, "coverage_status": "rated", "distinct_rated_opponents": 37, "draws": 54, "generated_at": "2026-07-02T16:51:45Z", "losses": 14, "model": "deepseek/deepseek-v4-pro", "point_rating_method": "sequential_elo", "public_id": "E-3a5b5c4507a989d3", "rated_matches": 74, "raw_elo_rating": 1431.6177940617447, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 27.45984279953629, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 80, "capped_draws": 67, "coverage_status": "rated", "distinct_rated_opponents": 40, "draws": 67, "generated_at": "2026-07-02T16:51:45Z", "losses": 9, "model": "deepseek/deepseek-v4-pro", "point_rating_method": "sequential_elo", "public_id": "E-c296a7abab6975d7", "rated_matches": 80, "raw_elo_rating": 1442.4017586919488, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 29.298341747357632, "uncertainty": 11.805555555555554, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 31, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 31, "generated_at": "2026-07-02T16:51:45Z", "losses": 8, "model": "google/gemini-3.1-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-b335c9f92035f80b", "rated_matches": 42, "raw_elo_rating": 1404.8828757455797, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 21.362647009504503, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 78, "capped_draws": 26, "coverage_status": "rated", "distinct_rated_opponents": 39, "draws": 26, "generated_at": "2026-07-02T16:51:45Z", "losses": 28, "model": "google/gemini-3.1-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-cc6fb78c96472032", "rated_matches": 78, "raw_elo_rating": 1451.3559728598718, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 30.530384005557536, "uncertainty": 12.5043950463012, "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": "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": 68, "capped_draws": 61, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 61, "generated_at": "2026-07-02T16:51:45Z", "losses": 7, "model": "google/gemini-3.5-flash", "point_rating_method": "sequential_elo", "public_id": "E-bd0bbefbbd252fc5", "rated_matches": 68, "raw_elo_rating": 1390.2358564476272, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 21.098201606423295, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 29, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 29, "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": 42, "raw_elo_rating": 1368.1960198159356, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 15.978610178652271, "uncertainty": 32.49928516630233, "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": 78, "capped_draws": 63, "coverage_status": "rated", "distinct_rated_opponents": 39, "draws": 63, "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": 78, "raw_elo_rating": 1426.8485145766456, "reasoning": "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": 26.93375369522216, "uncertainty": 12.5043950463012, "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": 76, "capped_draws": 56, "coverage_status": "rated", "distinct_rated_opponents": 38, "draws": 56, "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": 76, "raw_elo_rating": 1375.119567341035, "reasoning": "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": 19.25696759542373, "uncertainty": 13.230288229818967, "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": 76, "capped_draws": 45, "coverage_status": "rated", "distinct_rated_opponents": 38, "draws": 45, "generated_at": "2026-07-24T13:40:00Z", "losses": 17, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-679bf377de51ec1e", "rated_matches": 76, "raw_elo_rating": 1435.125394659315, "reasoning": "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": 28.063216486496604, "uncertainty": 13.230288229818967, "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-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": 84, "capped_draws": 59, "coverage_status": "rated", "distinct_rated_opponents": 40, "draws": 59, "generated_at": "2026-07-02T16:51:45Z", "losses": 18, "model": "google/gemma-4-31b-it", "point_rating_method": "sequential_elo", "public_id": "E-8546650b7690a81a", "rated_matches": 79, "raw_elo_rating": 1426.0434530743848, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 26.8570139531642, "uncertainty": 12.151699437494736, "unilateral_faults": 2, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 33, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 33, "generated_at": "2026-07-02T16:51:45Z", "losses": 14, "model": "gpt-4.1", "point_rating_method": "sequential_elo", "public_id": "E-eabc996d553eebe0", "rated_matches": 54, "raw_elo_rating": 1419.0289552749614, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 24.4752830412746, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 50, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 50, "generated_at": "2026-07-02T16:51:45Z", "losses": 12, "model": "gpt-5", "point_rating_method": "sequential_elo", "public_id": "E-04ae9f2b42e0e036", "rated_matches": 70, "raw_elo_rating": 1431.2215797734218, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 27.21337115953385, "uncertainty": 15.58908290969266, "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": 1418.548656749578, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 23.368190040746796, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 78, "capped_draws": 51, "coverage_status": "rated", "distinct_rated_opponents": 39, "draws": 51, "generated_at": "2026-07-02T16:51:45Z", "losses": 17, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-95f891d54f35bb4a", "rated_matches": 78, "raw_elo_rating": 1436.845557932157, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 28.40088540388973, "uncertainty": 12.5043950463012, "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": 1454.5300578111446, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 30.42909603823807, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 17, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 17, "generated_at": "2026-07-02T16:51:45Z", "losses": 28, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-ddc1f3e68bf1e74a", "rated_matches": 72, "raw_elo_rating": 1532.2005706493428, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 42.12879794049859, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 27 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 38, "coverage_status": "rated", "distinct_rated_opponents": 37, "draws": 38, "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": 74, "raw_elo_rating": 1436.7317351212178, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 28.210347205468835, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 11 }, { "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": 30, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-1e5d07fc67fd8710", "rated_matches": 70, "raw_elo_rating": 1547.462785687673, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 44.272530851637754, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 82, "capped_draws": 57, "coverage_status": "rated", "distinct_rated_opponents": 41, "draws": 57, "generated_at": "2026-07-01T00:15:48Z", "losses": 21, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-7ff0b78720f446ad", "rated_matches": 82, "raw_elo_rating": 1419.0534911448178, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 25.95089397945687, "uncertainty": 11.132129994845172, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 80, "capped_draws": 63, "coverage_status": "rated", "distinct_rated_opponents": 40, "draws": 63, "generated_at": "2026-07-02T06:10:40Z", "losses": 13, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-8cc872d6760c46c1", "rated_matches": 80, "raw_elo_rating": 1421.5989567986887, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 26.24539407059221, "uncertainty": 11.805555555555554, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 44, "coverage_status": "rated", "distinct_rated_opponents": 37, "draws": 44, "generated_at": "2026-07-01T00:15:48Z", "losses": 21, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-acdb5996d6e8fdfc", "rated_matches": 74, "raw_elo_rating": 1435.4514740395327, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 28.022460491215703, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 82, "capped_draws": 29, "coverage_status": "rated", "distinct_rated_opponents": 40, "draws": 29, "generated_at": "2026-07-02T16:51:45Z", "losses": 30, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-b5171a15f0048555", "rated_matches": 80, "raw_elo_rating": 1456.7268808782455, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 31.40064742341202, "uncertainty": 11.805555555555554, "unilateral_faults": 1, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 84, "capped_draws": 48, "coverage_status": "rated", "distinct_rated_opponents": 42, "draws": 48, "generated_at": "2026-07-02T06:10:40Z", "losses": 24, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-b63acb1096519102", "rated_matches": 84, "raw_elo_rating": 1430.2312733062938, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 27.667563389281582, "uncertainty": 10.482614454664043, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 63, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 63, "generated_at": "2026-07-02T16:51:45Z", "losses": 7, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-bb8ac98c284a38ce", "rated_matches": 70, "raw_elo_rating": 1427.6035082282665, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 26.68239542007192, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 100, "capped_draws": 73, "coverage_status": "rated", "distinct_rated_opponents": 42, "draws": 73, "generated_at": "2026-07-09T17:30:50Z", "losses": 11, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-024aff0a983df40d", "rated_matches": 84, "raw_elo_rating": 1403.53396138828, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 23.749557689174935, "uncertainty": 10.482614454664043, "unilateral_faults": 8, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 49, "coverage_status": "rated", "distinct_rated_opponents": 37, "draws": 49, "generated_at": "2026-07-02T16:51:45Z", "losses": 20, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-26fa12e871bd8f3a", "rated_matches": 74, "raw_elo_rating": 1386.3428002249889, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 20.815440379193305, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 80, "capped_draws": 64, "coverage_status": "rated", "distinct_rated_opponents": 40, "draws": 64, "generated_at": "2026-07-02T06:10:40Z", "losses": 14, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-814593575d73a7cd", "rated_matches": 80, "raw_elo_rating": 1413.551380104126, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 25.06435938597039, "uncertainty": 11.805555555555554, "unilateral_faults": 0, "wins": 2 }, { "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": 15, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-98e55f26cfe52488", "rated_matches": 74, "raw_elo_rating": 1764.5695291816269, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 76.32269461271417, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 59 }, { "admitted_plugin_count": 1, "attempted_matches": 84, "capped_draws": 66, "coverage_status": "rated", "distinct_rated_opponents": 42, "draws": 66, "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": 84, "raw_elo_rating": 1428.5388283371356, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 27.419185984970532, "uncertainty": 10.482614454664043, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 49, "coverage_status": "rated", "distinct_rated_opponents": 37, "draws": 49, "generated_at": "2026-07-09T17:30:50Z", "losses": 18, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-bb4437fab8180bfc", "rated_matches": 74, "raw_elo_rating": 1418.331238451975, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 25.509953583208976, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 84, "capped_draws": 61, "coverage_status": "rated", "distinct_rated_opponents": 40, "draws": 61, "generated_at": "2026-07-01T00:15:48Z", "losses": 14, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-c320ceaf4558afab", "rated_matches": 80, "raw_elo_rating": 1445.963699766453, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 29.821079971947757, "uncertainty": 11.805555555555554, "unilateral_faults": 2, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "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": 68, "raw_elo_rating": 1705.185174352874, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 67.31908056932906, "uncertainty": 16.4429265428846, "unilateral_faults": 1, "wins": 45 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 56, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 56, "generated_at": "2026-07-02T06:10:40Z", "losses": 9, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-f26c38927e48d019", "rated_matches": 70, "raw_elo_rating": 1457.613496954871, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 31.08655817818232, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 78, "capped_draws": 4, "coverage_status": "rated", "distinct_rated_opponents": 39, "draws": 4, "generated_at": "2026-07-02T16:51:45Z", "losses": 25, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-fd5a36e5fd795426", "rated_matches": 78, "raw_elo_rating": 1612.235845265633, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 54.14056090478664, "uncertainty": 12.5043950463012, "unilateral_faults": 0, "wins": 49 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 26, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 26, "generated_at": "2026-07-02T16:51:45Z", "losses": 23, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-0d83a3c5c5e66085", "rated_matches": 68, "raw_elo_rating": 1551.251508726565, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 44.7283050929694, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 11, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 11, "generated_at": "2026-07-02T16:51:45Z", "losses": 16, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-3e859a6b27767128", "rated_matches": 72, "raw_elo_rating": 1701.0119250403293, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 66.90297186399128, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 45 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 55, "coverage_status": "rated", "distinct_rated_opponents": 37, "draws": 55, "generated_at": "2026-07-02T16:51:45Z", "losses": 14, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-c42fbee03a029c83", "rated_matches": 74, "raw_elo_rating": 1435.4933507900123, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 28.028606179125585, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 5, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 5, "generated_at": "2026-07-10T05:30:29Z", "losses": 31, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-0fb7de4e8156a229", "rated_matches": 72, "raw_elo_rating": 1553.7066794269651, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 45.28496051733778, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 36 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 59, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 59, "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": 68, "raw_elo_rating": 1434.0824942540764, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 27.53298340706836, "uncertainty": 16.4429265428846, "unilateral_faults": 2, "wins": 2 }, { "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": 6, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-e6198d88365e0492", "rated_matches": 66, "raw_elo_rating": 1457.9749247725908, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 30.93465286854758, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 5, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 5, "generated_at": "2026-07-10T05:30:29Z", "losses": 19, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-0385f0602a8e29e2", "rated_matches": 68, "raw_elo_rating": 1669.960028561512, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 62.149559292375265, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 44 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 12, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 12, "generated_at": "2026-07-10T05:30:29Z", "losses": 36, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-3ae62f195160add3", "rated_matches": 68, "raw_elo_rating": 1353.9117026482218, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 15.76739369307706, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 7, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 7, "generated_at": "2026-07-10T05:30:29Z", "losses": 26, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-994624d0bc2e266d", "rated_matches": 70, "raw_elo_rating": 1514.8243499856248, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 39.48262625315627, "uncertainty": 15.58908290969266, "unilateral_faults": 2, "wins": 37 }, { "admitted_plugin_count": 1, "attempted_matches": 84, "capped_draws": 61, "coverage_status": "rated", "distinct_rated_opponents": 42, "draws": 61, "generated_at": "2026-07-10T05:30:29Z", "losses": 19, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-44cace55a6126cdf", "rated_matches": 84, "raw_elo_rating": 1431.615078138953, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 27.87064582839924, "uncertainty": 10.482614454664043, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 78, "capped_draws": 11, "coverage_status": "rated", "distinct_rated_opponents": 39, "draws": 11, "generated_at": "2026-07-10T05:30:29Z", "losses": 35, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-b061663dc342c859", "rated_matches": 78, "raw_elo_rating": 1553.7992605242216, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 45.56460865855579, "uncertainty": 12.5043950463012, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 35, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 35, "generated_at": "2026-07-10T05:30:29Z", "losses": 21, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-d004e78844cdd202", "rated_matches": 72, "raw_elo_rating": 1488.8573843513443, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 35.7679009521483, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 60, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 60, "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": 72, "raw_elo_rating": 1418.054546041148, "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": 25.377119852726032, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 78, "capped_draws": 63, "coverage_status": "rated", "distinct_rated_opponents": 39, "draws": 63, "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": 78, "raw_elo_rating": 1423.165394767332, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 26.39323169617664, "uncertainty": 12.5043950463012, "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": 72, "capped_draws": 61, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 61, "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": 72, "raw_elo_rating": 1419.4833709182178, "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": 25.58680927876285, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 60, "coverage_status": "rated", "distinct_rated_opponents": 37, "draws": 60, "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": 74, "raw_elo_rating": 1429.999497281636, "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": 27.222347128496388, "uncertainty": 13.985026918962571, "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": 52, "capped_draws": 33, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 33, "generated_at": "2026-07-02T16:51:45Z", "losses": 12, "model": "minimax/minimax-m3", "point_rating_method": "sequential_elo", "public_id": "E-d169e7b29be70652", "rated_matches": 50, "raw_elo_rating": 1453.3282140108763, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 29.204372992994628, "uncertainty": 26.26400420140049, "unilateral_faults": 1, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 78, "capped_draws": 7, "coverage_status": "rated", "distinct_rated_opponents": 39, "draws": 7, "generated_at": "2026-07-02T16:51:45Z", "losses": 35, "model": "minimax/minimax-m3", "point_rating_method": "sequential_elo", "public_id": "E-e67e41d4491d7ad3", "rated_matches": 78, "raw_elo_rating": 1523.287920626812, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 41.08686932648167, "uncertainty": 12.5043950463012, "unilateral_faults": 0, "wins": 36 }, { "admitted_plugin_count": 1, "attempted_matches": 92, "capped_draws": 61, "coverage_status": "rated", "distinct_rated_opponents": 40, "draws": 61, "generated_at": "2026-07-02T16:51:45Z", "losses": 18, "model": "mistralai/mistral-medium-3-5", "point_rating_method": "sequential_elo", "public_id": "E-ba85be2fa53925f5", "rated_matches": 80, "raw_elo_rating": 1416.3368045051216, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 25.473138693558756, "uncertainty": 11.805555555555554, "unilateral_faults": 6, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 2, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "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": 38, "raw_elo_rating": 1631.2691306737945, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 54.13843879363069, "uncertainty": 36.31407690254356, "unilateral_faults": 1, "wins": 22 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 27, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 27, "generated_at": "2026-07-18T00:14:00Z", "losses": 13, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-134262cb96978830", "rated_matches": 42, "raw_elo_rating": 1374.9431805127113, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "score": 16.968800282835204, "uncertainty": 32.49928516630233, "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": 1459.348117952713, "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": 29.355778680609212, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 2 }, { "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": 2, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-3e1be56b9d966ded", "rated_matches": 46, "raw_elo_rating": 1820.3922762390605, "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": 82.73078641197665, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 44 }, { "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": 1510.291605381818, "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": 37.221478218076655, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 33, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 33, "generated_at": "2026-07-17T22:36:00Z", "losses": 22, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-b06cbc77b01de3b3", "rated_matches": 58, "raw_elo_rating": 1406.253121311441, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "score": 22.873375095707896, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 16, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 16, "generated_at": "2026-07-21T14:20:15Z", "losses": 15, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-b88e77144afeb8fd", "rated_matches": 46, "raw_elo_rating": 1514.7954980475845, "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": 37.88245401936075, "uncertainty": 29.182495748947275, "unilateral_faults": 2, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 56, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 56, "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": 64, "raw_elo_rating": 1435.7725076009103, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 27.5668050336474, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 8, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 8, "generated_at": "2026-07-02T16:51:45Z", "losses": 27, "model": "nex-agi/nex-n2-pro", "point_rating_method": "sequential_elo", "public_id": "E-92332f4d765b2297", "rated_matches": 38, "raw_elo_rating": 1262.3695174883117, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 0.0, "uncertainty": 36.31407690254356, "unilateral_faults": 1, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 51, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 51, "generated_at": "2026-07-02T16:51:45Z", "losses": 14, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-15cf0dede27b7e1b", "rated_matches": 68, "raw_elo_rating": 1428.1113342083331, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 26.65667649020289, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 31, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 31, "generated_at": "2026-07-11T17:22:09Z", "losses": 19, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-2e3c01d0103fc439", "rated_matches": 56, "raw_elo_rating": 1409.4549137422746, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 23.210337339298093, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 6 }, { "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": 10, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-8c24e8bcbe9b1228", "rated_matches": 44, "raw_elo_rating": 1412.289677044104, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 22.650839422411963, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 44, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 44, "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": 50, "raw_elo_rating": 1448.227540293634, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 28.45581565658891, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 1, "generated_at": "2026-07-03T16:00:00Z", "losses": 15, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-1b6fc7dfefb8cea4", "rated_matches": 42, "raw_elo_rating": 1645.8312203928197, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 56.72339758462758, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 39, "coverage_status": "rated", "distinct_rated_opponents": 37, "draws": 39, "generated_at": "2026-07-02T16:51:45Z", "losses": 23, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-35de956c8305ff90", "rated_matches": 74, "raw_elo_rating": 1452.1756101546605, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 30.47683720261099, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 24, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 24, "generated_at": "2026-07-21T14:20:15Z", "losses": 13, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-cbb72b5e25b55cee", "rated_matches": 46, "raw_elo_rating": 1499.982489727866, "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": 35.70854785193036, "uncertainty": 29.182495748947275, "unilateral_faults": 2, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 33, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 33, "generated_at": "2026-07-02T16:51:45Z", "losses": 12, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-24a75273941e6ea3", "rated_matches": 50, "raw_elo_rating": 1408.5321189990236, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 22.630252117531743, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 54, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 54, "generated_at": "2026-07-02T16:51:45Z", "losses": 11, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-6e65dec497ff2de3", "rated_matches": 68, "raw_elo_rating": 1452.621919774562, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 30.253765749838735, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 37, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 37, "generated_at": "2026-07-21T14:20:15Z", "losses": 6, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-f6e9da46c61ad315", "rated_matches": 46, "raw_elo_rating": 1428.8001234106816, "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": 25.262068527185047, "uncertainty": 29.182495748947275, "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": 76, "capped_draws": 66, "coverage_status": "rated", "distinct_rated_opponents": 38, "draws": 66, "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": 76, "raw_elo_rating": 1416.5330777584284, "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": 25.334671986602174, "uncertainty": 13.230288229818967, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 76, "capped_draws": 59, "coverage_status": "rated", "distinct_rated_opponents": 38, "draws": 59, "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": 76, "raw_elo_rating": 1413.9390431952345, "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": 24.95398039352798, "uncertainty": 13.230288229818967, "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": 42, "capped_draws": 26, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 26, "generated_at": "2026-07-02T16:51:45Z", "losses": 13, "model": "qwen/qwen3.7-max", "point_rating_method": "sequential_elo", "public_id": "E-64624689e7cbd439", "rated_matches": 42, "raw_elo_rating": 1462.4364586987772, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 29.8090129494416, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 78, "capped_draws": 50, "coverage_status": "rated", "distinct_rated_opponents": 39, "draws": 50, "generated_at": "2026-07-02T16:51:45Z", "losses": 23, "model": "qwen/qwen3.7-max", "point_rating_method": "sequential_elo", "public_id": "E-a667eb7d15f7f43e", "rated_matches": 78, "raw_elo_rating": 1451.3049117986232, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 30.52289045977884, "uncertainty": 12.5043950463012, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 35, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 35, "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": 38, "raw_elo_rating": 1452.4213354706649, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "first_pass", "score": 27.89135132620079, "uncertainty": 36.31407690254356, "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": 1421.6753565476383, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 24.028249474298484, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 38, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 38, "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": 46, "raw_elo_rating": 1404.3431246021992, "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": 21.672843475861427, "uncertainty": 29.182495748947275, "unilateral_faults": 2, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 84, "capped_draws": 68, "coverage_status": "rated", "distinct_rated_opponents": 42, "draws": 68, "generated_at": "2026-07-02T16:51:45Z", "losses": 15, "model": "tencent/hy3-preview", "point_rating_method": "sequential_elo", "public_id": "E-56487337fad4192f", "rated_matches": 84, "raw_elo_rating": 1444.6787048624783, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 29.78781876790787, "uncertainty": 10.482614454664043, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 9, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 9, "generated_at": "2026-07-02T16:51:45Z", "losses": 24, "model": "tencent/hy3-preview", "point_rating_method": "sequential_elo", "public_id": "E-81a5e5ef15f371dc", "rated_matches": 48, "raw_elo_rating": 1406.755628453984, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 22.203462855600293, "uncertainty": 27.67857142857143, "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": 1642.069056814891, "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": 58.05637618014437, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugin_count": 1, "attempted_matches": 76, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 38, "draws": 1, "generated_at": "2026-07-24T13:40:00Z", "losses": 40, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-9c877cdf80f00ddf", "rated_matches": 76, "raw_elo_rating": 1614.2416876518455, "reasoning": "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": 54.34970776628676, "uncertainty": 13.230288229818967, "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": "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": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "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": 42, "raw_elo_rating": 1660.0254682005177, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 58.80649658688188, "uncertainty": 32.49928516630233, "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": "2026-07-17T22:36:00Z", "losses": 13, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-34ecad20175c262b", "rated_matches": 64, "raw_elo_rating": 1814.8608889517905, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 83.2005124098112, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 51 }, { "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": 10, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-60939cc4ea338b18", "rated_matches": 42, "raw_elo_rating": 1689.9450884674038, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 63.19739718057012, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 32 }, { "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": 4, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-707dd709e358a173", "rated_matches": 42, "raw_elo_rating": 1803.6901754826108, "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": 79.89023504579376, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 38 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 23, "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": 46, "raw_elo_rating": 1738.5892014713577, "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": 70.72564843365268, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 38 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "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": 64, "raw_elo_rating": 1864.1808157412113, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 90.43853528204684, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 57 }, { "admitted_plugin_count": 1, "attempted_matches": 78, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 39, "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": 78, "raw_elo_rating": 1830.6394574386093, "reasoning": "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": 86.19272406059183, "uncertainty": 12.5043950463012, "unilateral_faults": 0, "wins": 65 }, { "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": 7, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-b914d026c7631fcb", "rated_matches": 46, "raw_elo_rating": 1774.8087656357409, "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": 76.04110713178775, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 39 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 32, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 32, "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": 40, "raw_elo_rating": 1451.1013700464266, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 27.92977092345208, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 43, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 43, "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": 50, "raw_elo_rating": 1434.926356676387, "reasoning": "highest", "reasoning_bracket": "highest", "reasoning_setting": "highest", "repair_status": "repaired", "score": 26.503779684181723, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 19, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 19, "generated_at": "2026-07-03T19:35:00Z", "losses": 15, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-650d06103e7fa176", "rated_matches": 42, "raw_elo_rating": 1457.764628429521, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 29.12339120291192, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 25, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 25, "generated_at": "2026-07-02T06:10:40Z", "losses": 12, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-b5eb7da0f5021b69", "rated_matches": 38, "raw_elo_rating": 1378.9010503799364, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 17.101767081032705, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 76, "capped_draws": 52, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 52, "generated_at": "2026-07-02T16:51:45Z", "losses": 18, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-cabbf604f15eb575", "rated_matches": 72, "raw_elo_rating": 1366.1166145408445, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 17.7548876109612, "uncertainty": 14.770573598065289, "unilateral_faults": 2, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 62, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 62, "generated_at": "2026-07-01T00:15:48Z", "losses": 9, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-d51fce0298267f96", "rated_matches": 71, "raw_elo_rating": 1432.5748367505894, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 27.460519662064947, "uncertainty": 15.175565098878964, "unilateral_faults": 1, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 33, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 33, "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": 38, "raw_elo_rating": 1447.3428035769923, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 27.14604344768903, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 35, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 35, "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": 50, "raw_elo_rating": 1458.0937473201427, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 29.903746275484338, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 45, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 45, "generated_at": "2026-07-01T00:15:48Z", "losses": 4, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-18e15798a90b1d2f", "rated_matches": 50, "raw_elo_rating": 1454.5042225310565, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 29.376959959786937, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 40, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 40, "generated_at": "2026-07-11T14:00:45Z", "losses": 7, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-6a361d88d8c1fb48", "rated_matches": 50, "raw_elo_rating": 1459.5233969442024, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 30.113556738553537, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "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": 68, "raw_elo_rating": 1718.6715254627495, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 69.29829108626797, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 45 }, { "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": 17, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-97efd9455394f6d7", "rated_matches": 50, "raw_elo_rating": 1626.635475853018, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 54.63835083513168, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 33 }, { "admitted_plugin_count": 1, "attempted_matches": 76, "capped_draws": 62, "coverage_status": "rated", "distinct_rated_opponents": 38, "draws": 62, "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": 76, "raw_elo_rating": 1401.0941966464954, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 23.068914880209483, "uncertainty": 13.230288229818967, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 3, "coverage_status": "rated", "distinct_rated_opponents": 24, "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": 48, "raw_elo_rating": 1549.0618224868374, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 43.08783058121371, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 32, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 32, "generated_at": "2026-07-02T16:51:45Z", "losses": 32, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-bc28f817090c9f60", "rated_matches": 66, "raw_elo_rating": 1295.7349020863935, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 7.124864990950522, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 43, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 43, "generated_at": "2026-07-11T17:22:09Z", "losses": 6, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-da1e9a6be31e371f", "rated_matches": 50, "raw_elo_rating": 1445.4605497899704, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 28.049741644389226, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 1 } ] } } }