{ "benchmark_line": "gamebench2", "generated_at": "2026-07-27T19:45:01Z", "public_release_id": "gb2-20260727-4d94e2ae1be2", "results_cut_id": "gb2-20260727-4d94e2ae1be2", "schema_version": 2, "snapshot_id": "20260727_194501", "tracks": { "full_freedom/balanced": { "GB2-01": [ { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 20, "model": "claude-fable-5", "point_rating_method": "sequential_elo", "public_id": "E-2dbc6efbd7db03b5", "rated_matches": 56, "raw_elo_rating": 1665.451007353691, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 68.96939634840618, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 36 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 9, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 9, "generated_at": "2026-07-02T16:51:45Z", "losses": 23, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-13ec9509bc80f2bf", "rated_matches": 52, "raw_elo_rating": 1484.8070614799876, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 45.42169278538346, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 5, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 5, "generated_at": "2026-07-25T15:48:00Z", "losses": 16, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-0437af9582860271", "rated_matches": 50, "raw_elo_rating": 1555.183876640609, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 54.35940383926061, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 2, "coverage_status": "rated", "distinct_rated_opponents": 25, "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": 50, "raw_elo_rating": 1689.9192786895337, "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": 71.73393735110122, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 30 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 8, "coverage_status": "rated", "distinct_rated_opponents": 31, "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": 62, "raw_elo_rating": 1452.0417343596705, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 41.78310808513646, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 24, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 24, "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": 46, "raw_elo_rating": 1358.062733964776, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 28.638963702727548, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 6, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 6, "generated_at": "2026-07-01T00:15:48Z", "losses": 20, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-fd9da5310ad15cac", "rated_matches": 44, "raw_elo_rating": 1603.8559723664998, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 60.16935773866531, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 29, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 29, "generated_at": "2026-07-02T16:51:45Z", "losses": 16, "model": "google/gemini-3.1-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-7669b8a03ef19548", "rated_matches": 58, "raw_elo_rating": 1455.3793905117934, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 41.996828952531544, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 9, "model": "google/gemini-3.5-flash", "point_rating_method": "sequential_elo", "public_id": "E-22f31826bcf76511", "rated_matches": 56, "raw_elo_rating": 1823.1594383472432, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 89.30637072728769, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 47 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 20, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 20, "generated_at": "2026-07-24T13:40:00Z", "losses": 23, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-77d8df8cd762fd09", "rated_matches": 68, "raw_elo_rating": 1487.8622040397863, "reasoning": "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": 46.69123848223904, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 11, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 11, "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": 62, "raw_elo_rating": 1516.2643236863769, "reasoning": "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": 50.06480327070365, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 33, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 33, "generated_at": "2026-07-24T13:40:00Z", "losses": 18, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-4b36631072d1c39e", "rated_matches": 62, "raw_elo_rating": 1326.375382396334, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 25.57805573590371, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 2, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 2, "generated_at": "2026-07-24T13:40:00Z", "losses": 8, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-7484f4e7d8863a3b", "rated_matches": 62, "raw_elo_rating": 1844.595746189268, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 92.40412327507312, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 52 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 17, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 17, "generated_at": "2026-07-02T16:51:45Z", "losses": 25, "model": "gpt-5", "point_rating_method": "sequential_elo", "public_id": "E-adee794ecd761044", "rated_matches": 56, "raw_elo_rating": 1358.9198897376532, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 29.44129093251917, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 26, "coverage_status": "rated", "distinct_rated_opponents": 31, "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": 62, "raw_elo_rating": 1645.4310233167598, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 66.72123593215844, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 5, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 5, "generated_at": "2026-07-02T16:51:45Z", "losses": 24, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-62424dfd649cbac9", "rated_matches": 60, "raw_elo_rating": 1588.6473905325695, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 59.29314091807598, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 31 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 16, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 16, "generated_at": "2026-07-01T00:15:48Z", "losses": 34, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-aa899d4eca8a2891", "rated_matches": 58, "raw_elo_rating": 1312.380356821258, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 23.556675397975365, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 76, "capped_draws": 11, "coverage_status": "rated", "distinct_rated_opponents": 38, "draws": 11, "generated_at": "2026-07-02T06:10:40Z", "losses": 30, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-c675a6c67536654d", "rated_matches": 76, "raw_elo_rating": 1503.5911773559517, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 49.05096014988609, "uncertainty": 13.230288229818967, "unilateral_faults": 0, "wins": 35 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 17, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 17, "generated_at": "2026-07-02T06:10:40Z", "losses": 21, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-22c14c8deb751cb3", "rated_matches": 54, "raw_elo_rating": 1396.077491107873, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 34.109764142612626, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 15, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 15, "generated_at": "2026-07-02T16:51:45Z", "losses": 26, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-9257cc1e94bf4b17", "rated_matches": 62, "raw_elo_rating": 1423.032941291813, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 38.04233736243864, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 10, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 10, "generated_at": "2026-07-01T00:15:48Z", "losses": 45, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-98c36ba5e36ecf75", "rated_matches": 56, "raw_elo_rating": 1130.609635080802, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 0.0, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 9, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 9, "generated_at": "2026-07-09T17:30:50Z", "losses": 46, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-c48c1aed1cdecc72", "rated_matches": 56, "raw_elo_rating": 1163.6421749792917, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 4.259644924198314, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 38, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 38, "generated_at": "2026-07-02T16:51:45Z", "losses": 3, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-e4496be687faac9d", "rated_matches": 56, "raw_elo_rating": 1579.6537688986575, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 57.905585560065134, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 8, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 8, "generated_at": "2026-07-10T05:30:29Z", "losses": 23, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-4f775a5b7b265dae", "rated_matches": 62, "raw_elo_rating": 1633.9498843243437, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 65.24070868286577, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 31 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 25, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-bc834303cebba06a", "rated_matches": 54, "raw_elo_rating": 1590.5607673020877, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 59.188964919420734, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 20, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 20, "generated_at": "2026-07-10T05:30:29Z", "losses": 18, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-46de264ad4571b48", "rated_matches": 56, "raw_elo_rating": 1501.322471283357, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 47.80453019713377, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "inclusionai/ling-3.0-flash", "point_rating_method": "sequential_elo", "public_id": "E-47f813dcedb11262", "rated_matches": 0, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-5e8d45873865cc93", "rated_matches": 0, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 1, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 1, "generated_at": "2026-07-02T16:51:45Z", "losses": 17, "model": "minimax/minimax-m3", "point_rating_method": "sequential_elo", "public_id": "E-e0a841a9daa66219", "rated_matches": 34, "raw_elo_rating": 1461.0913426668806, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 40.72988850257243, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 30, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 15, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 14, "model": "moonshotai/kimi-k2.7-code", "point_rating_method": "sequential_elo", "public_id": "E-4935e918b1e70ea1", "rated_matches": 30, "raw_elo_rating": 1510.753247793639, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 46.5884970123769, "uncertainty": 46.05265101338746, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 30, "capped_draws": 19, "coverage_status": "under_covered", "distinct_rated_opponents": 15, "draws": 19, "generated_at": "2026-07-24T14:00:00Z", "losses": 6, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-6cc4477cf8936e55", "rated_matches": 30, "raw_elo_rating": 1505.7500994571997, "reasoning": "high", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 45.94332605423027, "uncertainty": 46.05265101338746, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 30, "capped_draws": 11, "coverage_status": "under_covered", "distinct_rated_opponents": 15, "draws": 11, "generated_at": "2026-07-21T14:43:57Z", "losses": 6, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-ee608da1db5fc482", "rated_matches": 30, "raw_elo_rating": 1590.3751112138789, "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": 56.85597469999918, "uncertainty": 46.05265101338746, "unilateral_faults": 0, "wins": 13 }, { "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": 26, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-b851008baae8f441", "rated_matches": 66, "raw_elo_rating": 1514.38343795476, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 50.01923123018594, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 7, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 7, "generated_at": "2026-07-02T16:51:45Z", "losses": 21, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-428923c2eb87dc7a", "rated_matches": 54, "raw_elo_rating": 1522.6714120111717, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 50.4344292839315, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 18, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 18, "generated_at": "2026-07-02T16:51:45Z", "losses": 22, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-a3e0c8f8ea39b5ec", "rated_matches": 56, "raw_elo_rating": 1405.3393264056997, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 35.427216277491794, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-ffd72d2c5c11728a", "rated_matches": 0, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "first_pass", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 30, "capped_draws": 7, "coverage_status": "under_covered", "distinct_rated_opponents": 15, "draws": 7, "generated_at": "2026-07-02T16:51:45Z", "losses": 14, "model": "qwen/qwen3.7-max", "point_rating_method": "sequential_elo", "public_id": "E-24581eb49b81bf8f", "rated_matches": 30, "raw_elo_rating": 1453.9243685520637, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 39.26024288014395, "uncertainty": 46.05265101338746, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 3, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 3, "generated_at": "2026-07-02T16:51:45Z", "losses": 18, "model": "qwen/qwen3.7-plus", "point_rating_method": "sequential_elo", "public_id": "E-1e5dceaf2ba3ca9a", "rated_matches": 40, "raw_elo_rating": 1494.5247005260037, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 45.70440415487458, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 13, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 13, "generated_at": "2026-07-24T13:40:00Z", "losses": 22, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-7382cf954e1b755d", "rated_matches": 62, "raw_elo_rating": 1458.1721573044606, "reasoning": "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": 42.57364447925613, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 27 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 22, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 22, "generated_at": "2026-07-24T13:40:00Z", "losses": 27, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-c9890f6abafaf54f", "rated_matches": 62, "raw_elo_rating": 1301.5360292948533, "reasoning": "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": 22.3749467807873, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 76, "capped_draws": 7, "coverage_status": "rated", "distinct_rated_opponents": 38, "draws": 7, "generated_at": "2026-07-17T22:36:00Z", "losses": 37, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-abb31ae26e404d88", "rated_matches": 76, "raw_elo_rating": 1466.268081692571, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 44.23803521324939, "uncertainty": 13.230288229818967, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 6, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 6, "generated_at": "2026-07-24T14:00:00Z", "losses": 10, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-d709aeb6802f9289", "rated_matches": 72, "raw_elo_rating": 1812.526480046139, "reasoning": "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": 88.73019290150756, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 56 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 12, "coverage_status": "rated", "distinct_rated_opponents": 31, "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": 62, "raw_elo_rating": 1625.8640214601994, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 64.19801245627039, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 30 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 5, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 5, "generated_at": "2026-07-02T16:51:45Z", "losses": 16, "model": "x-ai/grok-build-0.1", "point_rating_method": "sequential_elo", "public_id": "E-f1ded648f3ab17dc", "rated_matches": 40, "raw_elo_rating": 1516.557076145994, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 48.545544959248915, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 3, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 3, "generated_at": "2026-07-02T16:51:45Z", "losses": 16, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-1208f50b0908ecb4", "rated_matches": 38, "raw_elo_rating": 1508.73482689852, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 47.33287022675642, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 4, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 4, "generated_at": "2026-07-02T06:10:40Z", "losses": 18, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-2a71bee21bd7c0b9", "rated_matches": 36, "raw_elo_rating": 1488.9872818158133, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 44.56607045433817, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 34, "coverage_status": "rated", "distinct_rated_opponents": 23, "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": 46, "raw_elo_rating": 1468.3050824237796, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 42.85504461833912, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 3, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 3, "generated_at": "2026-07-11T17:22:09Z", "losses": 18, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-f889d782e3cce209", "rated_matches": 46, "raw_elo_rating": 1449.2185211300243, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 40.39377539153461, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 25 } ], "GB2-02": [ { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 30, "generated_at": "2026-07-02T16:51:45Z", "losses": 9, "model": "claude-fable-5", "point_rating_method": "sequential_elo", "public_id": "E-cd3608270e8c00fd", "rated_matches": 60, "raw_elo_rating": 1624.69812777023, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 63.452640140055266, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 41, "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": 46, "raw_elo_rating": 1476.4547971192335, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 26.35973023478462, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 22, "generated_at": "2026-07-25T10:50:00Z", "losses": 10, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-50b401cafe71e710", "rated_matches": 52, "raw_elo_rating": 1643.4265617903695, "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": 67.0333745447079, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 25, "generated_at": "2026-07-25T10:50:00Z", "losses": 7, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-8a5bf2e23121edf6", "rated_matches": 50, "raw_elo_rating": 1624.2203382943308, "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": 62.19350916040092, "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": 52, "generated_at": "2026-07-02T16:51:45Z", "losses": 3, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-a1a16bb5799cfdbe", "rated_matches": 56, "raw_elo_rating": 1489.0475371244402, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 30.6467494525862, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 32, "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": 38, "raw_elo_rating": 1450.9053103013168, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 18.89821545113325, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 38, "generated_at": "2026-07-01T00:15:48Z", "losses": 0, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-1e168b9e73c26073", "rated_matches": 38, "raw_elo_rating": 1493.436723483075, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 29.05183211899724, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 47, "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": 56, "raw_elo_rating": 1497.501056091277, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 32.664876400707286, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 57, "generated_at": "2026-07-24T13:40:00Z", "losses": 3, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-60dfb882a81b3944", "rated_matches": 64, "raw_elo_rating": 1490.4414707801473, "reasoning": "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": 31.783433086846944, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 63, "generated_at": "2026-07-24T13:40:00Z", "losses": 1, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-f2b9f6de4830b5f8", "rated_matches": 64, "raw_elo_rating": 1482.1184189823184, "reasoning": "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": 29.79645284942148, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 62, "generated_at": "2026-07-24T13:40:00Z", "losses": 4, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-62275b0c39dda32a", "rated_matches": 66, "raw_elo_rating": 1470.8519879795908, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 27.284915215803313, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 61, "generated_at": "2026-07-24T13:40:00Z", "losses": 1, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-e49b9c0097a352eb", "rated_matches": 62, "raw_elo_rating": 1481.8613724353104, "reasoning": "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": 29.548549594502184, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 59, "generated_at": "2026-07-02T16:51:45Z", "losses": 6, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-f4948a32cdd115a9", "rated_matches": 68, "raw_elo_rating": 1461.361568758212, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 25.189567064800336, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 49, "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": 56, "raw_elo_rating": 1495.695527099591, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 32.233838542032025, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 54, "generated_at": "2026-07-01T00:15:48Z", "losses": 4, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-4f2717a1b63468f4", "rated_matches": 58, "raw_elo_rating": 1481.5576254050702, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 29.074893420469955, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 48, "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": 50, "raw_elo_rating": 1479.6499174077858, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 27.67989850465793, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 59, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 51, "generated_at": "2026-07-01T00:15:48Z", "losses": 6, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-6a4ccfcf11c5e3f3", "rated_matches": 59, "raw_elo_rating": 1480.6077266300342, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 28.95215826651564, "uncertainty": 20.79972243679028, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 45, "generated_at": "2026-07-02T06:10:40Z", "losses": 2, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-a92f8113f0090156", "rated_matches": 48, "raw_elo_rating": 1476.1930545086254, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 26.58447194893014, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 57, "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": 60, "raw_elo_rating": 1484.5501961174168, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 29.99481994688565, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 31, "generated_at": "2026-07-02T16:51:45Z", "losses": 12, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-8460841e3919c568", "rated_matches": 58, "raw_elo_rating": 1535.714251788026, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 42.00382249149155, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 52, "generated_at": "2026-07-10T05:30:29Z", "losses": 0, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-e2dda893ae4363f2", "rated_matches": 52, "raw_elo_rating": 1491.189585591546, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 30.68951048376554, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 0 }, { "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": 11, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-087d760c91df7f17", "rated_matches": 60, "raw_elo_rating": 1552.434703520284, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 46.201035877446856, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 22 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 52, "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": 54, "raw_elo_rating": 1487.5622315860544, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 30.06424289135372, "uncertainty": 23.66998624632421, "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": 28, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 14, "draws": 26, "generated_at": "2026-07-02T16:51:45Z", "losses": 2, "model": "minimax/minimax-m3", "point_rating_method": "sequential_elo", "public_id": "E-cad87bcb23d33fef", "rated_matches": 28, "raw_elo_rating": 1466.6107290752293, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 20.206120407054794, "uncertainty": 49.09766908852594, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 25, "generated_at": "2026-07-02T16:51:45Z", "losses": 5, "model": "moonshotai/kimi-k2.7-code", "point_rating_method": "sequential_elo", "public_id": "E-85c8a9372a607001", "rated_matches": 32, "raw_elo_rating": 1459.7262189302294, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 19.671972150014987, "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": 1478.1200909901734, "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": 26.123829983792792, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 30, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 15, "draws": 24, "generated_at": "2026-07-21T14:43:57Z", "losses": 3, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-be8e56a3b58c5bcc", "rated_matches": 30, "raw_elo_rating": 1513.5650622210796, "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": 31.99718539096118, "uncertainty": 46.05265101338746, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 54, "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": 56, "raw_elo_rating": 1478.792058417232, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 28.19843674091044, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 50, "generated_at": "2026-07-02T16:51:45Z", "losses": 3, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-8f0c6569aa132f8e", "rated_matches": 54, "raw_elo_rating": 1485.1407076693067, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 29.486147225977007, "uncertainty": 23.66998624632421, "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": 1503.013853532559, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 30.93036703796877, "uncertainty": 38.449493652678655, "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": "2026-07-02T16:51:45Z", "losses": 2, "model": "qwen/qwen3.7-plus", "point_rating_method": "sequential_elo", "public_id": "E-57293d5b71f14882", "rated_matches": 32, "raw_elo_rating": 1497.9406642377191, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 28.794989698694177, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 51, "generated_at": "2026-07-02T16:51:45Z", "losses": 4, "model": "stepfun/step-3.7-flash", "point_rating_method": "sequential_elo", "public_id": "E-0ccea44addccfff0", "rated_matches": 56, "raw_elo_rating": 1495.901542637513, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 32.28302107896658, "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": 63, "generated_at": "2026-07-24T13:40:00Z", "losses": 5, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-63e0985794df5d5b", "rated_matches": 68, "raw_elo_rating": 1476.6106392697473, "reasoning": "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": 28.830010796441194, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 30, "generated_at": "2026-07-17T22:36:00Z", "losses": 8, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-081ac2f1dd1c34b2", "rated_matches": 56, "raw_elo_rating": 1582.8999468560062, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 53.052339121032695, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 78, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 39, "draws": 52, "generated_at": "2026-07-24T14:00:00Z", "losses": 13, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-da5ea0258e71b6ab", "rated_matches": 78, "raw_elo_rating": 1506.035891887915, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 36.60696862445656, "uncertainty": 12.5043950463012, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 28, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 14, "draws": 25, "generated_at": "2026-07-02T16:51:45Z", "losses": 2, "model": "x-ai/grok-build-0.1", "point_rating_method": "sequential_elo", "public_id": "E-99592fa0331c6679", "rated_matches": 28, "raw_elo_rating": 1495.6428182083175, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 27.13701411766091, "uncertainty": 49.09766908852594, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 28, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 14, "draws": 26, "generated_at": "2026-07-02T16:51:45Z", "losses": 1, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-5b213ae773e821cc", "rated_matches": 28, "raw_elo_rating": 1492.9613856719243, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 26.49686990286792, "uncertainty": 49.09766908852594, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 28, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 14, "draws": 25, "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": 28, "raw_elo_rating": 1464.5709945048668, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 19.71917014177337, "uncertainty": 49.09766908852594, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 27, "generated_at": "2026-07-02T06:10:40Z", "losses": 3, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-c37f25e181320efb", "rated_matches": 32, "raw_elo_rating": 1484.681792494128, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 25.629670442607463, "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": 38, "generated_at": "2026-07-11T17:22:09Z", "losses": 2, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-32435b01ac08ed41", "rated_matches": 40, "raw_elo_rating": 1470.374121179378, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 23.923663197046043, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 0 } ], "GB2-03": [ { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 5, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 23, "generated_at": "2026-07-02T16:51:45Z", "losses": 10, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-823b961281482cd1", "rated_matches": 40, "raw_elo_rating": 1460.7826005116174, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 38.6391638686108, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 0, "generated_at": "2026-07-25T15:48:00Z", "losses": 9, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-bd02f4c2907d0a7c", "rated_matches": 40, "raw_elo_rating": 1762.0128566539547, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 89.35930678511835, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 31 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "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": 42, "raw_elo_rating": 1798.366804655625, "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": 95.72798953026684, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 36 }, { "admitted_plugin_count": 1, "attempted_matches": 22, "capped_draws": 1, "coverage_status": "under_covered", "distinct_rated_opponents": 11, "draws": 11, "generated_at": "2026-07-02T16:51:45Z", "losses": 8, "model": "cohere/north-mini-code", "point_rating_method": "sequential_elo", "public_id": "E-0f669ae82234cf76", "rated_matches": 22, "raw_elo_rating": 1447.213610903655, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 32.829285213351575, "uncertainty": 60.5072070285374, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 30, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 15, "draws": 9, "generated_at": "2026-07-01T00:15:48Z", "losses": 9, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-32e04fe5ad231857", "rated_matches": 30, "raw_elo_rating": 1546.3471653061004, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 51.468109335875496, "uncertainty": 46.05265101338746, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 14, "generated_at": "2026-07-02T16:51:45Z", "losses": 13, "model": "google/gemini-3.5-flash", "point_rating_method": "sequential_elo", "public_id": "E-8ed795ea8fd1e0aa", "rated_matches": 50, "raw_elo_rating": 1585.7951447614212, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 60.77578508926699, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 3, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 21, "generated_at": "2026-07-24T13:40:00Z", "losses": 16, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-36e89f1dca2cd568", "rated_matches": 52, "raw_elo_rating": 1536.9370245972011, "reasoning": "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": 52.728872395868734, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 17, "generated_at": "2026-07-24T13:40:00Z", "losses": 16, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-e51f710b50e975e5", "rated_matches": 50, "raw_elo_rating": 1500.157339213247, "reasoning": "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": 46.35637784882347, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 2, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 24, "generated_at": "2026-07-24T13:40:00Z", "losses": 12, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-9b5d467ecf278026", "rated_matches": 50, "raw_elo_rating": 1564.288669917894, "reasoning": "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": 57.154596794096086, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 3, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 13, "generated_at": "2026-07-24T13:40:00Z", "losses": 18, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-f44c7c8e627e08cd", "rated_matches": 54, "raw_elo_rating": 1551.625363472671, "reasoning": "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": 55.37180926655133, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 26, "generated_at": "2026-07-02T16:51:45Z", "losses": 11, "model": "gpt-5", "point_rating_method": "sequential_elo", "public_id": "E-e724ba162431d43a", "rated_matches": 42, "raw_elo_rating": 1434.6445964503675, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 34.485660760472555, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 2, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 24, "generated_at": "2026-07-02T16:51:45Z", "losses": 19, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-496f83ad0bd69447", "rated_matches": 54, "raw_elo_rating": 1401.825348329168, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 30.14898379651178, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 7, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 18, "generated_at": "2026-07-01T00:15:48Z", "losses": 12, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-3e164d6fc6c16cbb", "rated_matches": 44, "raw_elo_rating": 1548.3116113141386, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 53.855368269859, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 13, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 25, "generated_at": "2026-07-02T06:10:40Z", "losses": 9, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-7cbcc752e71e2d3b", "rated_matches": 40, "raw_elo_rating": 1467.46537218358, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 39.764386608919374, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 9, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 34, "generated_at": "2026-07-02T16:51:45Z", "losses": 7, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-9e39bdd48b7328c7", "rated_matches": 52, "raw_elo_rating": 1526.9921431629089, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 51.054386525509535, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 4, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 24, "generated_at": "2026-07-01T00:15:48Z", "losses": 15, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-0ad5302188ed9e2f", "rated_matches": 48, "raw_elo_rating": 1410.3860603587646, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 31.050446121101896, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 2, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 19, "generated_at": "2026-07-02T16:51:45Z", "losses": 13, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-c002b0ea38b845f8", "rated_matches": 40, "raw_elo_rating": 1470.0062111246496, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 40.192204570731214, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 15, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 32, "generated_at": "2026-07-10T05:30:29Z", "losses": 4, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-0300c20cb034e3a4", "rated_matches": 40, "raw_elo_rating": 1488.4273983408475, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 43.29390245547429, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 2, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 12, "generated_at": "2026-07-10T05:30:29Z", "losses": 11, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-b741de451c385e8e", "rated_matches": 46, "raw_elo_rating": 1581.5282621482136, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 59.66421699198599, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 24, "generated_at": "2026-07-10T05:30:29Z", "losses": 8, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-e44c62bb88a3042a", "rated_matches": 38, "raw_elo_rating": 1503.8716525415657, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 45.62802340349199, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-3dc5f5cc9bb215b7", "rated_matches": 0, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 20, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 10, "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": 20, "raw_elo_rating": 1635.9359536874997, "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": 63.95218647222154, "uncertainty": 65.3589451179962, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugin_count": 1, "attempted_matches": 20, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 10, "draws": 4, "generated_at": "2026-07-24T14:00:00Z", "losses": 8, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-b97350a867368460", "rated_matches": 20, "raw_elo_rating": 1515.946833497835, "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": 43.748819777309976, "uncertainty": 65.3589451179962, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 26, "capped_draws": 2, "coverage_status": "under_covered", "distinct_rated_opponents": 13, "draws": 16, "generated_at": "2026-07-02T16:51:45Z", "losses": 7, "model": "nex-agi/nex-n2-pro", "point_rating_method": "sequential_elo", "public_id": "E-57ad2863cbf32d58", "rated_matches": 26, "raw_elo_rating": 1476.4776317441515, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 38.8386060326366, "uncertainty": 52.475044864937615, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 4, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 28, "generated_at": "2026-07-02T16:51:45Z", "losses": 11, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-87b4bd61da369b42", "rated_matches": 46, "raw_elo_rating": 1431.1372881816976, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 34.34188785207999, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-08762a3df1a52f6b", "rated_matches": 0, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "first_pass", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-936fb7956df3d03b", "rated_matches": 0, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 5, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 31, "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": 56, "raw_elo_rating": 1491.9596146765782, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 45.48623836828051, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 4, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 22, "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": 62, "raw_elo_rating": 1535.7451687642574, "reasoning": "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": 53.29413078892297, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 7, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 19, "generated_at": "2026-07-17T22:36:00Z", "losses": 9, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-d5ed477108214e1c", "rated_matches": 42, "raw_elo_rating": 1542.785659806102, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 52.69409127734003, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 20, "capped_draws": 1, "coverage_status": "under_covered", "distinct_rated_opponents": 10, "draws": 10, "generated_at": "2026-07-02T16:51:45Z", "losses": 5, "model": "x-ai/grok-build-0.1", "point_rating_method": "sequential_elo", "public_id": "E-2a93343a8a88fd59", "rated_matches": 20, "raw_elo_rating": 1528.5673152215754, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 45.87381427454535, "uncertainty": 65.3589451179962, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 30, "capped_draws": 6, "coverage_status": "under_covered", "distinct_rated_opponents": 15, "draws": 19, "generated_at": "2026-07-11T17:22:09Z", "losses": 6, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-40aa28533b1afda1", "rated_matches": 30, "raw_elo_rating": 1484.357755308563, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 41.03053983455878, "uncertainty": 46.05265101338746, "unilateral_faults": 0, "wins": 5 } ], "GB2-04": [ { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "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": 58, "raw_elo_rating": 1570.2329284352627, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 50.169539127004974, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 43, "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": 54, "raw_elo_rating": 1469.453330167729, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 29.732078673060073, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 29, "generated_at": "2026-07-25T15:48:00Z", "losses": 11, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-048d3dcf802043b4", "rated_matches": 54, "raw_elo_rating": 1540.3795707782112, "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": 43.854759056984896, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 18, "generated_at": "2026-07-25T15:48:00Z", "losses": 14, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-d0f0a2b1c4bbddae", "rated_matches": 50, "raw_elo_rating": 1535.2546073345477, "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": 42.42107514802987, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 36, "generated_at": "2026-07-02T16:51:45Z", "losses": 7, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-b1fc5b99a5deb881", "rated_matches": 52, "raw_elo_rating": 1492.460996966201, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 34.11255787082396, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 20, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 10, "draws": 14, "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": 20, "raw_elo_rating": 1479.6801213452768, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 25.127602707860607, "uncertainty": 65.3589451179962, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 34, "generated_at": "2026-07-01T00:15:48Z", "losses": 4, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-5d143d6301429619", "rated_matches": 40, "raw_elo_rating": 1474.9614593543852, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 29.129670210091273, "uncertainty": 34.33688094430304, "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": 2, "model": "google/gemini-3.1-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-860c31323fa5eda7", "rated_matches": 44, "raw_elo_rating": 1496.4002724512168, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 33.96421938799026, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 33, "generated_at": "2026-07-02T16:51:45Z", "losses": 8, "model": "google/gemini-3.5-flash", "point_rating_method": "sequential_elo", "public_id": "E-32cfa6c9dfb1d16f", "rated_matches": 54, "raw_elo_rating": 1537.8145480172825, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 43.34401724523379, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 52, "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": 63, "raw_elo_rating": 1504.0838388637048, "reasoning": "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": 37.4113566914359, "uncertainty": 18.75, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 50, "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": 65, "raw_elo_rating": 1471.9723967515329, "reasoning": "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": 31.169402731335655, "uncertainty": 17.79574548966636, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 65, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 39, "generated_at": "2026-07-24T13:40:00Z", "losses": 10, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-1ff96286ae16ecd4", "rated_matches": 64, "raw_elo_rating": 1498.584656594851, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 36.39325198178922, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 48, "generated_at": "2026-07-24T13:40:00Z", "losses": 8, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-d109ab12db58a65f", "rated_matches": 64, "raw_elo_rating": 1476.6296215757122, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 32.02161266008875, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 24, "generated_at": "2026-07-02T16:51:45Z", "losses": 4, "model": "google/gemma-4-31b-it", "point_rating_method": "sequential_elo", "public_id": "E-62ca2464f2212fc9", "rated_matches": 32, "raw_elo_rating": 1518.6101743659633, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 36.3949144614059, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 4 }, { "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": 8, "model": "gpt-5", "point_rating_method": "sequential_elo", "public_id": "E-6f1aae863396df76", "rated_matches": 68, "raw_elo_rating": 1551.1716734247516, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 47.15488856869603, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 40, "generated_at": "2026-07-02T16:51:45Z", "losses": 7, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-0b4132559ee98caf", "rated_matches": 58, "raw_elo_rating": 1514.0229127508078, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 38.977121778303186, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 37, "generated_at": "2026-07-01T00:15:48Z", "losses": 5, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-6d633c9c2680eb32", "rated_matches": 54, "raw_elo_rating": 1554.76847532534, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 46.71984676281586, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 31, "generated_at": "2026-07-02T16:51:45Z", "losses": 7, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-74f5bcc8ad3796a5", "rated_matches": 56, "raw_elo_rating": 1565.524282873785, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 49.05161677023061, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 18 }, { "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": 1531.2344187539643, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 43.185025327321505, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 34, "generated_at": "2026-07-09T17:30:50Z", "losses": 8, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-a32cb67d48c62b3b", "rated_matches": 58, "raw_elo_rating": 1559.5720195351737, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 48.04676189107393, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 43, "generated_at": "2026-07-01T00:15:48Z", "losses": 13, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-fd2be90162c92ecf", "rated_matches": 70, "raw_elo_rating": 1532.8060282037686, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 43.63397322386019, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 40, "generated_at": "2026-07-02T16:51:45Z", "losses": 13, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-9e7bdad81107b7e4", "rated_matches": 62, "raw_elo_rating": 1453.9356837685343, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 27.3472600456232, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 59, "generated_at": "2026-07-10T05:30:29Z", "losses": 1, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-5389e160269f5ceb", "rated_matches": 62, "raw_elo_rating": 1512.8853854171534, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 39.08519776719661, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 50, "generated_at": "2026-07-10T05:30:29Z", "losses": 4, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-c81bf4d15f3d48f1", "rated_matches": 58, "raw_elo_rating": 1490.518146546648, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 34.29690331835047, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 4 }, { "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": 5, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-89c18d144e85d89f", "rated_matches": 64, "raw_elo_rating": 1509.8215591763649, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 38.630719839920246, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "inclusionai/ling-3.0-flash", "point_rating_method": "sequential_elo", "public_id": "E-20e94e7276184071", "rated_matches": 0, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-46a1c9f4e3ff6058", "rated_matches": 0, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-4ccf296e55b59be3", "rated_matches": 0, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 20, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 10, "draws": 19, "generated_at": "2026-07-02T16:51:45Z", "losses": 1, "model": "minimax/minimax-m3", "point_rating_method": "sequential_elo", "public_id": "E-c60620c3c72a6064", "rated_matches": 20, "raw_elo_rating": 1485.6322009222465, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 26.312767983246804, "uncertainty": 65.3589451179962, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 24, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 12, "draws": 19, "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": 24, "raw_elo_rating": 1478.974085801931, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 26.438021268193044, "uncertainty": 56.25, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 20, "generated_at": "2026-07-21T14:43:57Z", "losses": 8, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-0f7ca9245c7db7c7", "rated_matches": 40, "raw_elo_rating": 1503.8515619886705, "reasoning": "high", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 34.88220526976701, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 27, "generated_at": "2026-07-24T14:00:00Z", "losses": 6, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-35e5c9532c697b2c", "rated_matches": 36, "raw_elo_rating": 1479.9548503177186, "reasoning": "high", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 29.46882779889735, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 44, "generated_at": "2026-07-02T16:51:45Z", "losses": 7, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-7e92e17a121661f4", "rated_matches": 54, "raw_elo_rating": 1459.8799045162689, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 27.82583876113024, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 38, "generated_at": "2026-07-02T16:51:45Z", "losses": 4, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-f1288f2abfdbbfe4", "rated_matches": 46, "raw_elo_rating": 1479.5119436507632, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 30.856816919223707, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-e996fd38983e3b7f", "rated_matches": 0, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 24, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 12, "draws": 14, "generated_at": "2026-07-02T16:51:45Z", "losses": 6, "model": "qwen/qwen3.7-max", "point_rating_method": "sequential_elo", "public_id": "E-ea08328e287de1ad", "rated_matches": 24, "raw_elo_rating": 1495.2123365460154, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "first_pass", "score": 29.67134680862549, "uncertainty": 56.25, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 42, "generated_at": "2026-07-02T16:51:45Z", "losses": 3, "model": "stepfun/step-3.7-flash", "point_rating_method": "sequential_elo", "public_id": "E-25e56c6bfae33c62", "rated_matches": 50, "raw_elo_rating": 1527.025896067843, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 40.78259187031759, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 50, "generated_at": "2026-07-24T13:40:00Z", "losses": 6, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-7ca32267720b2e1a", "rated_matches": 60, "raw_elo_rating": 1497.2594850671685, "reasoning": "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": 35.81062725222203, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 40, "generated_at": "2026-07-24T13:40:00Z", "losses": 12, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-d9e91f86e4e39739", "rated_matches": 58, "raw_elo_rating": 1444.8493223540486, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 25.20342533290631, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 52, "generated_at": "2026-07-17T22:36:00Z", "losses": 6, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-1a7064508fe2a12f", "rated_matches": 68, "raw_elo_rating": 1507.4097653694373, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 38.441111620470615, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 42, "generated_at": "2026-07-17T22:36:00Z", "losses": 9, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-83f4cc0ffc20bde5", "rated_matches": 58, "raw_elo_rating": 1505.116815543511, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 37.20375886996048, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 82, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 41, "draws": 58, "generated_at": "2026-07-24T14:00:00Z", "losses": 12, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-ba6a8e6d7fc9a48d", "rated_matches": 82, "raw_elo_rating": 1502.9746588577696, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 38.40398226010029, "uncertainty": 11.132129994845172, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugin_count": 1, "attempted_matches": 26, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 13, "draws": 21, "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": 26, "raw_elo_rating": 1490.591586720057, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 29.35260180166352, "uncertainty": 52.475044864937615, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 25, "generated_at": "2026-07-02T06:10:40Z", "losses": 5, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-00e6914e513b1656", "rated_matches": 32, "raw_elo_rating": 1470.073185800368, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 26.730333758832895, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 30, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 15, "draws": 19, "generated_at": "2026-07-01T00:15:48Z", "losses": 10, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-23e877112cb95491", "rated_matches": 30, "raw_elo_rating": 1420.5057556493118, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 16.42031254980346, "uncertainty": 46.05265101338746, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 28, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 14, "draws": 22, "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": 28, "raw_elo_rating": 1445.8371871373347, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 20.979198713214263, "uncertainty": 49.09766908852594, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 30, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 15, "draws": 13, "generated_at": "2026-07-02T16:51:45Z", "losses": 8, "model": "xiaomi/mimo-v2.5-pro", "point_rating_method": "sequential_elo", "public_id": "E-ffdebde8a72ed049", "rated_matches": 30, "raw_elo_rating": 1489.877627090251, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 30.233490289979848, "uncertainty": 46.05265101338746, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 26, "generated_at": "2026-07-11T17:22:09Z", "losses": 8, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-912f31ad14c4bf0a", "rated_matches": 40, "raw_elo_rating": 1466.3555284012216, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 27.416075760258096, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 11, "generated_at": "2026-07-01T00:15:48Z", "losses": 12, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-947248ef34168cde", "rated_matches": 34, "raw_elo_rating": 1520.1832423700175, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 37.11010395761048, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 11 } ], "GB2-05": [ { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 24, "model": "claude-fable-5", "point_rating_method": "sequential_elo", "public_id": "E-ad7cf41c05ec3f64", "rated_matches": 54, "raw_elo_rating": 1563.8549313784958, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 52.92663955035931, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 30 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 28, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-924d7e6ee41b562e", "rated_matches": 60, "raw_elo_rating": 1526.9858286719375, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 48.94334155048709, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 0, "generated_at": "2026-07-25T10:50:00Z", "losses": 17, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-32c377b229530444", "rated_matches": 58, "raw_elo_rating": 1769.415445775125, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 77.12198514337373, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 41 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 0, "generated_at": "2026-07-25T10:50:00Z", "losses": 11, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-d7111b534ebcaba2", "rated_matches": 58, "raw_elo_rating": 1828.2244902143957, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 83.98197315159396, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 47 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 27, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-e0a09b1ea3f11175", "rated_matches": 62, "raw_elo_rating": 1521.6286930837043, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 48.414031779727786, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 35 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 16, "model": "cohere/north-mini-code", "point_rating_method": "sequential_elo", "public_id": "E-a0518a43c688d1e2", "rated_matches": 38, "raw_elo_rating": 1495.5568486203565, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "first_pass", "score": 43.77983769266278, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 22 }, { "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": 28, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-06a41d0e11b18b77", "rated_matches": 48, "raw_elo_rating": 1413.4014704079275, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 35.00238954548179, "uncertainty": 27.67857142857143, "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": "2026-07-02T06:10:40Z", "losses": 28, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-2c1cbd253f3a9d69", "rated_matches": 48, "raw_elo_rating": 1361.191173568771, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 28.912135679988577, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 37, "model": "google/gemini-3.1-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-7603462aff103041", "rated_matches": 64, "raw_elo_rating": 1318.8709361070892, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 24.85378503399073, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 27 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 37, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 40, "model": "google/gemini-3.5-flash", "point_rating_method": "sequential_elo", "public_id": "E-a7ce764239377b3f", "rated_matches": 74, "raw_elo_rating": 1471.8580015094933, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 43.09912275717949, "uncertainty": 13.985026918962571, "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": "2026-07-24T13:40:00Z", "losses": 36, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-c311887ca24f8a76", "rated_matches": 70, "raw_elo_rating": 1370.5699340132535, "reasoning": "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": 31.134330963710465, "uncertainty": 15.58908290969266, "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": "2026-07-24T13:40:00Z", "losses": 34, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-e3c1bc55ae62b8db", "rated_matches": 66, "raw_elo_rating": 1368.7640467794815, "reasoning": "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": 30.760775900267603, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 37, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 15, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-9e479871cca0aeaa", "rated_matches": 74, "raw_elo_rating": 1815.797658505252, "reasoning": "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": 83.21917478384927, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 59 }, { "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": 40, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-c7d3f2597dfefeb3", "rated_matches": 76, "raw_elo_rating": 1600.5420889346544, "reasoning": "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": 58.18036244960011, "uncertainty": 13.230288229818967, "unilateral_faults": 0, "wins": 36 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 18, "model": "google/gemma-4-31b-it", "point_rating_method": "sequential_elo", "public_id": "E-fd1bc1e2e6ac48fb", "rated_matches": 32, "raw_elo_rating": 1490.7546387691116, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 42.568791506466454, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 31, "model": "gpt-5", "point_rating_method": "sequential_elo", "public_id": "E-9e5b308c41a36374", "rated_matches": 58, "raw_elo_rating": 1570.3013243910782, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 53.89561753299053, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 27 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 32, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-cafab3c275850d3b", "rated_matches": 64, "raw_elo_rating": 1528.5904299300091, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 49.31725364553898, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 30, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-0791f6b66243ec1a", "rated_matches": 58, "raw_elo_rating": 1469.5509985868252, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 42.143241118250984, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 33, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-539afc540807da47", "rated_matches": 58, "raw_elo_rating": 1384.0918030499022, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 32.17455242138175, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 0, "generated_at": "2026-07-01T00:15:48Z", "losses": 32, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-ce84b7a3c6105fb2", "rated_matches": 56, "raw_elo_rating": 1414.7593062675958, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 35.646219238554934, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 45, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-83cfa14483bf0d43", "rated_matches": 58, "raw_elo_rating": 1261.1637541853777, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 17.835177430254863, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 16, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-8e40431df091d53f", "rated_matches": 68, "raw_elo_rating": 1741.5666304104925, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 74.33086692052227, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 52 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 0, "generated_at": "2026-07-09T17:30:50Z", "losses": 40, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-a0d8c8fd6b01598c", "rated_matches": 66, "raw_elo_rating": 1403.2268012896968, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 34.78080521590199, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 0, "generated_at": "2026-07-01T00:15:48Z", "losses": 40, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-ff2b4db95370e3d6", "rated_matches": 62, "raw_elo_rating": 1324.2741283816072, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 25.392913852502083, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 22 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 23, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-ffa82d1e96e897ab", "rated_matches": 60, "raw_elo_rating": 1648.4542713590818, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 63.11245564094769, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 37 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 29, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-e917387a1c57aa23", "rated_matches": 54, "raw_elo_rating": 1567.9046996706184, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 53.39903902878851, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 20, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-d61f8454991c5422", "rated_matches": 60, "raw_elo_rating": 1642.6315145680098, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 62.43323967778432, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 40 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 28, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-9664e98d37ece097", "rated_matches": 60, "raw_elo_rating": 1552.729583417106, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 51.946312445904134, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-52b991e608dc1672", "rated_matches": 0, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-9061c6162106c911", "rated_matches": 0, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 28, "model": "minimax/minimax-m3", "point_rating_method": "sequential_elo", "public_id": "E-fb8ac45946e32e22", "rated_matches": 32, "raw_elo_rating": 1259.3102294143223, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 15.571143646654498, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 17, "model": "moonshotai/kimi-k2.7-code", "point_rating_method": "sequential_elo", "public_id": "E-952fba19b28982d5", "rated_matches": 32, "raw_elo_rating": 1544.7036702952114, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 48.86186620021212, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 0, "generated_at": "2026-07-21T14:43:57Z", "losses": 18, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-4a1443311507f194", "rated_matches": 36, "raw_elo_rating": 1546.5622745419068, "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": 49.53027058545425, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 24, "model": "nex-agi/nex-n2-pro", "point_rating_method": "sequential_elo", "public_id": "E-5f76f577111bee8d", "rated_matches": 32, "raw_elo_rating": 1337.024714262499, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 24.63642330230389, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 32, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-343b92f3dda3dcb5", "rated_matches": 68, "raw_elo_rating": 1502.312238039986, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 46.42219609913933, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 36 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 29, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-5ef540286ecbb63d", "rated_matches": 62, "raw_elo_rating": 1444.0802873129855, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 39.3681250027, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 33 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-53ce0020411c86d4", "rated_matches": 0, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "first_pass", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-62e15a037ee860c1", "rated_matches": 0, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 19, "model": "qwen/qwen3.7-max", "point_rating_method": "sequential_elo", "public_id": "E-435ec29661cdc285", "rated_matches": 34, "raw_elo_rating": 1513.158475478824, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 45.41764683991974, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 20, "model": "qwen/qwen3.7-plus", "point_rating_method": "sequential_elo", "public_id": "E-6cc7454f585005c4", "rated_matches": 44, "raw_elo_rating": 1492.0034128052926, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 43.881245652912995, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 24, "model": "stepfun/step-3.7-flash", "point_rating_method": "sequential_elo", "public_id": "E-7b9b33921ba865f5", "rated_matches": 56, "raw_elo_rating": 1572.4768033532573, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 54.04373188325387, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 36, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-01a1df4eac0e6aef", "rated_matches": 66, "raw_elo_rating": 1350.1703423314248, "reasoning": "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": 28.591847791364597, "uncertainty": 17.33472217815261, "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": "2026-07-24T13:40:00Z", "losses": 42, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-ae60ed096a69eeff", "rated_matches": 70, "raw_elo_rating": 1390.450499005188, "reasoning": "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": 33.453369450760626, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 84, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 42, "draws": 0, "generated_at": "2026-07-24T14:00:00Z", "losses": 31, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-824ec3caceabd338", "rated_matches": 84, "raw_elo_rating": 1649.6080495823956, "reasoning": "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": 64.16024381524471, "uncertainty": 10.482614454664043, "unilateral_faults": 0, "wins": 53 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 0, "generated_at": "2026-07-18T00:06:00Z", "losses": 18, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-9f28818a3063ee74", "rated_matches": 64, "raw_elo_rating": 1752.648082819719, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 75.45324729462128, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 46 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 0, "generated_at": "2026-07-18T00:06:00Z", "losses": 26, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-c0bc4ff29a3cbf96", "rated_matches": 66, "raw_elo_rating": 1704.7531988551875, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 69.95341329317, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 40 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 17, "model": "x-ai/grok-build-0.1", "point_rating_method": "sequential_elo", "public_id": "E-4aac1b6621aeae38", "rated_matches": 38, "raw_elo_rating": 1586.0835428623882, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 54.33964261459866, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 18, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-ad48cf51fe7da3cc", "rated_matches": 38, "raw_elo_rating": 1474.0777369811203, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 41.27433110473413, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 20, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-faaa866ee28d6401", "rated_matches": 34, "raw_elo_rating": 1432.5369643456804, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 36.01326686994626, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 22, "model": "xiaomi/mimo-v2.5-pro", "point_rating_method": "sequential_elo", "public_id": "E-9c228ad72a159b33", "rated_matches": 36, "raw_elo_rating": 1436.26694114023, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 36.66448315917693, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 0, "generated_at": "2026-07-01T00:15:48Z", "losses": 19, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-1a8c2012f200fd88", "rated_matches": 48, "raw_elo_rating": 1641.0847219724617, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 61.56130391482155, "uncertainty": 27.67857142857143, "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": "2026-07-11T17:22:09Z", "losses": 25, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-3916ba303b2ff700", "rated_matches": 48, "raw_elo_rating": 1541.8603284877404, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 49.98692524708084, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 23 } ], "GB2-06": [ { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 25, "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": 50, "raw_elo_rating": 1656.6232412385289, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 73.07850759598226, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 30 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 1, "generated_at": "2026-07-02T16:51:45Z", "losses": 21, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-39e283268f14261d", "rated_matches": 58, "raw_elo_rating": 1683.650875040015, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 77.20302117516688, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 36 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 3, "generated_at": "2026-07-02T16:51:45Z", "losses": 32, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-01597b81edc004dd", "rated_matches": 68, "raw_elo_rating": 1477.208213223521, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 50.22582047612717, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 33 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 1, "generated_at": "2026-07-02T16:51:45Z", "losses": 25, "model": "cohere/north-mini-code", "point_rating_method": "sequential_elo", "public_id": "E-78dfcb6ce8b3efaa", "rated_matches": 32, "raw_elo_rating": 1301.5429160745794, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "first_pass", "score": 23.96519429729421, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 2, "generated_at": "2026-07-02T06:10:40Z", "losses": 24, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-6f20412107151172", "rated_matches": 42, "raw_elo_rating": 1378.06013360163, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 35.30758687991579, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 0, "generated_at": "2026-07-01T00:15:48Z", "losses": 31, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-d8ca2fcf88af96c7", "rated_matches": 44, "raw_elo_rating": 1268.5345160222116, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 20.90066666774462, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 35, "model": "google/gemini-3.1-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-a10101fbca309818", "rated_matches": 58, "raw_elo_rating": 1407.6659693492472, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 40.43999875124963, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "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": 52, "raw_elo_rating": 1734.2297854950075, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 83.55834325082338, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 31 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 1, "generated_at": "2026-07-24T13:40:00Z", "losses": 38, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-100ff33157ca87e5", "rated_matches": 64, "raw_elo_rating": 1330.8077323554674, "reasoning": "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": 30.52988198835926, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 1, "generated_at": "2026-07-24T13:40:00Z", "losses": 34, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-92d447632fa55355", "rated_matches": 64, "raw_elo_rating": 1486.224379305521, "reasoning": "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": 51.2324115798752, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 10, "generated_at": "2026-07-24T13:40:00Z", "losses": 26, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-aa5fab059f4d0186", "rated_matches": 66, "raw_elo_rating": 1548.9340975746195, "reasoning": "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": 59.68515016624557, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 30 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 4, "generated_at": "2026-07-24T13:40:00Z", "losses": 14, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-dd9886be3d9e45b5", "rated_matches": 66, "raw_elo_rating": 1851.5830446880557, "reasoning": "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": 17.33472217815261, "unilateral_faults": 0, "wins": 48 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 23, "model": "google/gemma-4-31b-it", "point_rating_method": "sequential_elo", "public_id": "E-41987f96551bf9d3", "rated_matches": 32, "raw_elo_rating": 1347.8582691700228, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 30.134706938421203, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 7, "generated_at": "2026-07-02T16:51:45Z", "losses": 25, "model": "gpt-5", "point_rating_method": "sequential_elo", "public_id": "E-816d262cd933cdb9", "rated_matches": 54, "raw_elo_rating": 1499.5581163462753, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 52.43282213007789, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 22 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "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": 54, "raw_elo_rating": 1795.322614521401, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 91.83061764137966, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 39 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 5, "generated_at": "2026-07-02T16:51:45Z", "losses": 19, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-3ccfe46cbdc271eb", "rated_matches": 54, "raw_elo_rating": 1502.0217575555882, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 52.76099550171851, "uncertainty": 23.66998624632421, "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": "2026-07-01T00:15:48Z", "losses": 33, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-ac7c887de3c2e7af", "rated_matches": 70, "raw_elo_rating": 1582.8885785230168, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 64.39413713675378, "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": 1574.870566908514, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 62.59211241806533, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 5, "generated_at": "2026-07-02T06:10:40Z", "losses": 34, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-962a93f9cc008820", "rated_matches": 70, "raw_elo_rating": 1498.7809459308949, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 53.190441864841645, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 31 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 8, "generated_at": "2026-07-01T00:15:48Z", "losses": 29, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-9b6b064b63e4164b", "rated_matches": 56, "raw_elo_rating": 1502.5118592815368, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 52.95345198336451, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 78, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 39, "draws": 2, "generated_at": "2026-07-09T17:30:50Z", "losses": 35, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-9c5263dcfd4c2ec7", "rated_matches": 78, "raw_elo_rating": 1498.797118661646, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 53.52131690856485, "uncertainty": 12.5043950463012, "unilateral_faults": 0, "wins": 41 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 32, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-1ea2c2c23d752166", "rated_matches": 58, "raw_elo_rating": 1450.542154271933, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 46.151391350129174, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 6, "generated_at": "2026-07-10T10:07:13Z", "losses": 24, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-f4c50b1a9cf2c2e6", "rated_matches": 58, "raw_elo_rating": 1593.8608666300522, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 65.24239570415726, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 9, "generated_at": "2026-07-10T10:07:13Z", "losses": 13, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-acdece52463a2698", "rated_matches": 54, "raw_elo_rating": 1677.6556396548986, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 76.15659509023824, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 9, "generated_at": "2026-07-10T05:30:29Z", "losses": 19, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-a3722334e358f0fe", "rated_matches": 56, "raw_elo_rating": 1498.4965294796054, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 52.41858338546655, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "inclusionai/ling-3.0-flash", "point_rating_method": "sequential_elo", "public_id": "E-6c37c8c2b8e19c4c", "rated_matches": 0, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "inclusionai/ling-3.0-flash", "point_rating_method": "sequential_elo", "public_id": "E-7f02a37922fd94e7", "rated_matches": 0, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-9b849343b9780ba9", "rated_matches": 0, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-a9bdeb6a9326ac2d", "rated_matches": 0, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 23, "model": "minimax/minimax-m3", "point_rating_method": "sequential_elo", "public_id": "E-ef8c1a9fa3580f83", "rated_matches": 32, "raw_elo_rating": 1327.362474639063, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 27.40453098168996, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "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": 32, "raw_elo_rating": 1731.7390831320631, "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": 81.270180947318, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 3, "generated_at": "2026-07-24T14:00:00Z", "losses": 16, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-1640f1438f9390d7", "rated_matches": 36, "raw_elo_rating": 1487.165419107651, "reasoning": "high", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 49.20704971327303, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 3, "generated_at": "2026-07-02T16:51:45Z", "losses": 21, "model": "nex-agi/nex-n2-pro", "point_rating_method": "sequential_elo", "public_id": "E-209380b737b62580", "rated_matches": 32, "raw_elo_rating": 1333.7245417304796, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 28.25200057267649, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 4, "generated_at": "2026-07-02T16:51:45Z", "losses": 26, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-1ea0c8193f35ca72", "rated_matches": 62, "raw_elo_rating": 1556.571475807063, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 60.49902848103273, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 10, "generated_at": "2026-07-02T16:51:45Z", "losses": 24, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-69e964db7b91b1bb", "rated_matches": 60, "raw_elo_rating": 1533.5732183679058, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 57.32634647961873, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 26 }, { "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": 37, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-f225b6990e542d31", "rated_matches": 58, "raw_elo_rating": 1362.013744309396, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 34.35881917136978, "uncertainty": 21.344455490411935, "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": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-b582570ce841ee30", "rated_matches": 0, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "first_pass", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 2, "generated_at": "2026-07-02T16:51:45Z", "losses": 17, "model": "qwen/qwen3.7-max", "point_rating_method": "sequential_elo", "public_id": "E-8283efe6f68a787e", "rated_matches": 34, "raw_elo_rating": 1497.2801393778354, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 50.307599631372334, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 5, "generated_at": "2026-07-02T16:51:45Z", "losses": 12, "model": "qwen/qwen3.7-plus", "point_rating_method": "sequential_elo", "public_id": "E-b6dd11ebe2b80c7b", "rated_matches": 32, "raw_elo_rating": 1552.0019476545383, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 57.328000756584736, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 1, "generated_at": "2026-07-02T16:51:45Z", "losses": 35, "model": "stepfun/step-3.7-flash", "point_rating_method": "sequential_elo", "public_id": "E-6526762dce98da7c", "rated_matches": 56, "raw_elo_rating": 1384.0385830541572, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 37.17202473580983, "uncertainty": 22.47661785325219, "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": "2026-07-24T13:40:00Z", "losses": 37, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-0825a2443d50c563", "rated_matches": 64, "raw_elo_rating": 1353.884883080069, "reasoning": "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": 33.60391173446151, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 27 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 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": 58, "raw_elo_rating": 1715.3059958637307, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 81.41969351005898, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 39 }, { "admitted_plugin_count": 1, "attempted_matches": 80, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 40, "draws": 7, "generated_at": "2026-07-24T14:00:00Z", "losses": 41, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-3baaff3521870bef", "rated_matches": 80, "raw_elo_rating": 1482.1377042576466, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 51.37664431378333, "uncertainty": 11.805555555555554, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 3, "generated_at": "2026-07-17T22:36:00Z", "losses": 33, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-8cb8510a257ade6a", "rated_matches": 66, "raw_elo_rating": 1509.8353687552262, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 54.476939808739395, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 30 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 21, "model": "x-ai/grok-build-0.1", "point_rating_method": "sequential_elo", "public_id": "E-133675db0ee21fd5", "rated_matches": 36, "raw_elo_rating": 1401.8647815875509, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 37.84443826147298, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 3, "generated_at": "2026-07-02T16:51:45Z", "losses": 22, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-7b4c450b6850f156", "rated_matches": 32, "raw_elo_rating": 1337.069511253292, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 28.697572729119944, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 17, "model": "xiaomi/mimo-v2.5-pro", "point_rating_method": "sequential_elo", "public_id": "E-530f82d65699c577", "rated_matches": 34, "raw_elo_rating": 1536.234900827742, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 55.49663257908679, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 6, "generated_at": "2026-07-02T06:10:40Z", "losses": 15, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-72584b5bdb2d01e3", "rated_matches": 44, "raw_elo_rating": 1678.108239443182, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 75.45860685902264, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 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": 42, "raw_elo_rating": 1600.9472964442882, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 64.99763730161912, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 23 } ], "GB2-07": [ { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 15, "model": "claude-fable-5", "point_rating_method": "sequential_elo", "public_id": "E-bc12a8303ec2def7", "rated_matches": 56, "raw_elo_rating": 1720.961634672591, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 75.98738578456185, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 41 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 20, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-0bf7b9ed307db853", "rated_matches": 58, "raw_elo_rating": 1658.4015620035889, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 68.09254323204925, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 38 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 0, "generated_at": "2026-07-25T10:50:00Z", "losses": 4, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-54bca3ce32fa85ae", "rated_matches": 54, "raw_elo_rating": 1909.441531822003, "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": 23.66998624632421, "unilateral_faults": 0, "wins": 50 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 0, "generated_at": "2026-07-25T10:50:00Z", "losses": 20, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-de5e72176c4f0dc9", "rated_matches": 56, "raw_elo_rating": 1765.129143808681, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 81.64303816605788, "uncertainty": 22.47661785325219, "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": 30, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-9e40526fba9fa8b9", "rated_matches": 66, "raw_elo_rating": 1489.3871953975538, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 46.86100001987165, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 36 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 18, "model": "cohere/north-mini-code", "point_rating_method": "sequential_elo", "public_id": "E-1c961fde1b53f0eb", "rated_matches": 36, "raw_elo_rating": 1490.8332481397597, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 44.88316889166992, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 0, "generated_at": "2026-07-01T00:15:48Z", "losses": 33, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-8f2f6c973751f183", "rated_matches": 44, "raw_elo_rating": 1386.7591014543962, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 32.341557460914714, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 27, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-edc2d085c4253ed3", "rated_matches": 46, "raw_elo_rating": 1482.2601478061813, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 44.73469458474547, "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": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 46, "model": "google/gemini-3.1-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-1b3c52da51dfbdd4", "rated_matches": 56, "raw_elo_rating": 1176.0530232290791, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 6.21180309294096, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 26, "model": "google/gemini-3.5-flash", "point_rating_method": "sequential_elo", "public_id": "E-5447c508e2b0ab6c", "rated_matches": 54, "raw_elo_rating": 1477.2974094270803, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 44.66391737325167, "uncertainty": 23.66998624632421, "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": "2026-07-24T13:40:00Z", "losses": 36, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-2950a4947ff48aa6", "rated_matches": 64, "raw_elo_rating": 1302.173020784396, "reasoning": "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": 22.792672723342108, "uncertainty": 18.26736729460423, "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": "2026-07-24T13:40:00Z", "losses": 43, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-42943e41c64d22d2", "rated_matches": 66, "raw_elo_rating": 1222.9692098369603, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 12.746159858375425, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 32, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-5f208f03ea700603", "rated_matches": 68, "raw_elo_rating": 1492.3363740837954, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 47.32999813075001, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 36 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 26, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-65c6c8e09fe2c210", "rated_matches": 70, "raw_elo_rating": 1442.8756213391898, "reasoning": "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": 41.084013350883716, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 44 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 17, "model": "google/gemma-4-31b-it", "point_rating_method": "sequential_elo", "public_id": "E-f417d302c870dfa6", "rated_matches": 36, "raw_elo_rating": 1459.4391274346103, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 40.86314971911562, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 25, "model": "gpt-5", "point_rating_method": "sequential_elo", "public_id": "E-4d8b4cfcff519db6", "rated_matches": 66, "raw_elo_rating": 1570.8705167678413, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 57.29494455453205, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 41 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 24, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-22466ae84d7027e5", "rated_matches": 58, "raw_elo_rating": 1565.920523238979, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 56.25034027872709, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 69, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 0, "generated_at": "2026-07-01T00:15:48Z", "losses": 40, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-946bc9bcbefb4ad1", "rated_matches": 69, "raw_elo_rating": 1448.845291037242, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 41.80516463367432, "uncertainty": 16.01143046671968, "unilateral_faults": 0, "wins": 29 }, { "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": 38, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-b96fbceba82aa188", "rated_matches": 68, "raw_elo_rating": 1511.1183237689709, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 49.73502799419104, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 30 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 28, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-f4d7ac8a0f5d2974", "rated_matches": 58, "raw_elo_rating": 1503.1946272282405, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 48.218285266036176, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 30 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 47, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-acb1779a65c941b4", "rated_matches": 54, "raw_elo_rating": 1180.574922681668, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 6.668583888759279, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 49, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-bea6d7d9558897f9", "rated_matches": 58, "raw_elo_rating": 1179.3520510017056, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 6.750222581722012, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 0, "generated_at": "2026-07-01T00:15:48Z", "losses": 51, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-c4ad375a0a870e69", "rated_matches": 66, "raw_elo_rating": 1286.244368785162, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 20.848548025484437, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 55, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 0, "generated_at": "2026-07-09T17:30:50Z", "losses": 28, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-ce04fd14b6f43868", "rated_matches": 55, "raw_elo_rating": 1568.9574262357626, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 56.46293142915195, "uncertainty": 23.065310478106092, "unilateral_faults": 0, "wins": 27 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 26, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-640b3078b8bce40e", "rated_matches": 58, "raw_elo_rating": 1638.802982390646, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 65.58294385391025, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 40, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-45c76cf9faaba10a", "rated_matches": 72, "raw_elo_rating": 1496.630215711361, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 48.05114074851961, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 25, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-cc78d54d18d4c3f1", "rated_matches": 58, "raw_elo_rating": 1613.041766542292, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 62.284218510036965, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 33 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 27, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-aca193dd2a8774fb", "rated_matches": 56, "raw_elo_rating": 1421.3527923761658, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 37.622454286388646, "uncertainty": 22.47661785325219, "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": "inclusionai/ling-3.0-flash", "point_rating_method": "sequential_elo", "public_id": "E-57b2b1d3b488c246", "rated_matches": 0, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "inclusionai/ling-3.0-flash", "point_rating_method": "sequential_elo", "public_id": "E-5e20a850f6c14680", "rated_matches": 0, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-0ad780cd41873f27", "rated_matches": 0, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 18, "model": "minimax/minimax-m3", "point_rating_method": "sequential_elo", "public_id": "E-4547f4cedca403f9", "rated_matches": 34, "raw_elo_rating": 1528.05635018843, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 49.41234532497391, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 18, "model": "moonshotai/kimi-k2.7-code", "point_rating_method": "sequential_elo", "public_id": "E-d35e87ebfc251f60", "rated_matches": 34, "raw_elo_rating": 1499.914270711031, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 45.80875024049249, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 0, "generated_at": "2026-07-21T14:43:57Z", "losses": 12, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-3d2d4c8b0819b60b", "rated_matches": 32, "raw_elo_rating": 1611.6429141200556, "reasoning": "high", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 59.85711272242997, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 0, "generated_at": "2026-07-24T14:00:00Z", "losses": 17, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-4cc8f48bf8bccc77", "rated_matches": 36, "raw_elo_rating": 1497.419808549579, "reasoning": "high", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 45.72657837516344, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 15, "model": "nex-agi/nex-n2-pro", "point_rating_method": "sequential_elo", "public_id": "E-d1f432cda667f27f", "rated_matches": 34, "raw_elo_rating": 1481.492286152561, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 43.449813934644574, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 45, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-459f395cc0af6d2e", "rated_matches": 62, "raw_elo_rating": 1169.348522168338, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 5.6844327646508575, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 30, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-f1e3e54a3d40556f", "rated_matches": 64, "raw_elo_rating": 1539.179287904116, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 53.14134044954261, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 7, "model": "qwen/qwen3.7-max", "point_rating_method": "sequential_elo", "public_id": "E-59c7745eb1e91d63", "rated_matches": 32, "raw_elo_rating": 1700.7910446154003, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 71.27253655781962, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 19, "model": "qwen/qwen3.7-plus", "point_rating_method": "sequential_elo", "public_id": "E-9d091700cb41ece2", "rated_matches": 44, "raw_elo_rating": 1492.425929607229, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 45.872201592244586, "uncertainty": 30.785599249992988, "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": "2026-07-24T13:40:00Z", "losses": 32, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-6df2b00898e4ba3c", "rated_matches": 70, "raw_elo_rating": 1639.8223969946982, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 66.30306062230608, "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": "2026-07-24T13:40:00Z", "losses": 33, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-8ad2285ad59d87bf", "rated_matches": 64, "raw_elo_rating": 1439.7429822122815, "reasoning": "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": 40.40851511949337, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 31 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 0, "generated_at": "2026-07-17T22:36:00Z", "losses": 24, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-3cfeaacb3dbbab07", "rated_matches": 58, "raw_elo_rating": 1573.4651002521898, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 57.216423849812585, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 0, "generated_at": "2026-07-17T22:36:00Z", "losses": 18, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-a1728c5ac67e11f3", "rated_matches": 66, "raw_elo_rating": 1689.9554461696157, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 72.54377741255473, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 48 }, { "admitted_plugin_count": 1, "attempted_matches": 82, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 41, "draws": 0, "generated_at": "2026-07-24T14:00:00Z", "losses": 34, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-e58f3df122cf1d29", "rated_matches": 82, "raw_elo_rating": 1653.7600244886946, "reasoning": "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": 68.54434520363635, "uncertainty": 11.132129994845172, "unilateral_faults": 0, "wins": 48 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 21, "model": "x-ai/grok-build-0.1", "point_rating_method": "sequential_elo", "public_id": "E-37ae0129627ee16f", "rated_matches": 32, "raw_elo_rating": 1338.8974387107648, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 24.93203707943055, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 0, "generated_at": "2026-07-01T00:15:48Z", "losses": 14, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-345a5b25cbac7f3b", "rated_matches": 32, "raw_elo_rating": 1498.5587594562753, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "first_pass", "score": 45.37667945500192, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 19, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-fa1a93f7e4d57000", "rated_matches": 32, "raw_elo_rating": 1398.5568164387994, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 32.571424229076754, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 21, "model": "xiaomi/mimo-v2.5-pro", "point_rating_method": "sequential_elo", "public_id": "E-3b160130ae038271", "rated_matches": 36, "raw_elo_rating": 1493.9649146612849, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 45.284178990879795, "uncertainty": 38.449493652678655, "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": "2026-07-02T06:10:40Z", "losses": 16, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-1d66fd51bbcbb370", "rated_matches": 44, "raw_elo_rating": 1675.4486719786005, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 69.30827550737436, "uncertainty": 30.785599249992988, "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": 21, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-e10fd023695e8b0a", "rated_matches": 48, "raw_elo_rating": 1659.926528762448, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 67.63894816131332, "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": "2026-07-11T17:22:09Z", "losses": 18, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-ecd98326faa92bf4", "rated_matches": 44, "raw_elo_rating": 1518.816948995505, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 49.25157331985353, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 26 } ], "GB2-08": [ { "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": 12, "model": "claude-fable-5", "point_rating_method": "sequential_elo", "public_id": "E-9ccf296d44d35675", "rated_matches": 62, "raw_elo_rating": 1748.30238195533, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 74.41108271929163, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 50 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 49, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 49, "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": 62, "raw_elo_rating": 1446.6514940291925, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 27.74641003392749, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 0, "generated_at": "2026-07-25T10:50:00Z", "losses": 24, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-35a5bf9b35d5e1e8", "rated_matches": 58, "raw_elo_rating": 1689.429497650715, "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": 65.04364936989096, "uncertainty": 21.344455490411935, "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": "2026-07-25T10:50:00Z", "losses": 16, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-e73b6fb78880341d", "rated_matches": 60, "raw_elo_rating": 1782.1362327088805, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 79.51832573176307, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 44 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 45, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 45, "generated_at": "2026-07-02T16:51:45Z", "losses": 9, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-130fb40b1c7a4d39", "rated_matches": 60, "raw_elo_rating": 1442.873384161387, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 27.035172472656587, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 24, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 24, "generated_at": "2026-07-02T16:51:45Z", "losses": 8, "model": "cohere/north-mini-code", "point_rating_method": "sequential_elo", "public_id": "E-efd7b75d5cd3b538", "rated_matches": 32, "raw_elo_rating": 1430.593099567464, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "first_pass", "score": 22.28648246143083, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 42, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 42, "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": 46, "raw_elo_rating": 1442.4608897065534, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 25.86817403465741, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 41, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 41, "generated_at": "2026-07-01T00:15:48Z", "losses": 4, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-d28ef17ff6995c62", "rated_matches": 46, "raw_elo_rating": 1444.0628033322878, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 26.11598625072297, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 76, "capped_draws": 25, "coverage_status": "rated", "distinct_rated_opponents": 38, "draws": 25, "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": 76, "raw_elo_rating": 1453.0417625819548, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 29.47922458032685, "uncertainty": 13.230288229818967, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 57, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 57, "generated_at": "2026-07-02T16:51:45Z", "losses": 5, "model": "google/gemini-3.5-flash", "point_rating_method": "sequential_elo", "public_id": "E-bd0bbefbbd252fc5", "rated_matches": 62, "raw_elo_rating": 1399.4738925482284, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 20.44814764085012, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 2, "attempted_matches": 72, "capped_draws": 57, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 57, "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": 72, "raw_elo_rating": 1428.8659054082534, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 25.548654376833127, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 52, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 52, "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": 72, "raw_elo_rating": 1377.0586399667216, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 17.534194014479326, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 41, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 41, "generated_at": "2026-07-24T13:40:00Z", "losses": 16, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-679bf377de51ec1e", "rated_matches": 70, "raw_elo_rating": 1436.078774527812, "reasoning": "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": 26.56317087103918, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 49, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 49, "generated_at": "2026-07-02T16:51:45Z", "losses": 11, "model": "gpt-5", "point_rating_method": "sequential_elo", "public_id": "E-04ae9f2b42e0e036", "rated_matches": 68, "raw_elo_rating": 1438.5140773232674, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 26.83423634499792, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 21, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 21, "generated_at": "2026-07-02T16:51:45Z", "losses": 26, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-b13a2be40d59c1ea", "rated_matches": 66, "raw_elo_rating": 1455.9222743715295, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 29.41687597028761, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 47, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 47, "generated_at": "2026-07-02T06:10:40Z", "losses": 7, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-8cc872d6760c46c1", "rated_matches": 56, "raw_elo_rating": 1433.0414693201265, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 25.240918822969498, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 40, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 40, "generated_at": "2026-07-01T00:15:48Z", "losses": 17, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-acdb5996d6e8fdfc", "rated_matches": 66, "raw_elo_rating": 1443.508756483802, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 27.496534369149785, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 25, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 25, "generated_at": "2026-07-02T16:51:45Z", "losses": 27, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-b5171a15f0048555", "rated_matches": 66, "raw_elo_rating": 1441.820798825804, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 27.23541134657634, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 45, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 45, "generated_at": "2026-07-02T16:51:45Z", "losses": 18, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-26fa12e871bd8f3a", "rated_matches": 68, "raw_elo_rating": 1393.6433229913866, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 19.89283770222214, "uncertainty": 16.4429265428846, "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": "2026-07-09T17:30:50Z", "losses": 23, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-e361d8cbba2abd67", "rated_matches": 62, "raw_elo_rating": 1682.4425779165422, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 64.22272816240137, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 39 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 48, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 48, "generated_at": "2026-07-02T06:10:40Z", "losses": 7, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-f26c38927e48d019", "rated_matches": 60, "raw_elo_rating": 1463.259224663276, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 30.188813361887515, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 25, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 25, "generated_at": "2026-07-02T16:51:45Z", "losses": 22, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-0d83a3c5c5e66085", "rated_matches": 62, "raw_elo_rating": 1541.9180516740412, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 42.483919215225825, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 49, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 49, "generated_at": "2026-07-10T05:30:29Z", "losses": 6, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-e6198d88365e0492", "rated_matches": 62, "raw_elo_rating": 1463.521515251263, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 30.356162068590265, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 5, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 5, "generated_at": "2026-07-10T05:30:29Z", "losses": 17, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-0385f0602a8e29e2", "rated_matches": 62, "raw_elo_rating": 1669.5691004601476, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 62.23123191335946, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 40 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 33, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 33, "generated_at": "2026-07-10T05:30:29Z", "losses": 14, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-d004e78844cdd202", "rated_matches": 60, "raw_elo_rating": 1492.409453460546, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 34.69828421039091, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-4289b162cf8180f0", "rated_matches": 0, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-fffc7436e4cd7fbe", "rated_matches": 0, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 29, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 29, "generated_at": "2026-07-02T16:51:45Z", "losses": 6, "model": "minimax/minimax-m3", "point_rating_method": "sequential_elo", "public_id": "E-d169e7b29be70652", "rated_matches": 38, "raw_elo_rating": 1460.665880280986, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 27.80185177118549, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 2, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "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": 32, "raw_elo_rating": 1581.6368914228988, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 45.65259670212887, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 16 }, { "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": 1465.6007059014808, "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": 29.037368865431898, "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": 1508.6650791446625, "reasoning": "high", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 36.109804191190086, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 8, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 8, "generated_at": "2026-07-02T16:51:45Z", "losses": 21, "model": "nex-agi/nex-n2-pro", "point_rating_method": "sequential_elo", "public_id": "E-92332f4d765b2297", "rated_matches": 32, "raw_elo_rating": 1309.805103448781, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 3.6008676371193116, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 42, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 42, "generated_at": "2026-07-02T16:51:45Z", "losses": 11, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-15cf0dede27b7e1b", "rated_matches": 56, "raw_elo_rating": 1432.7695118803483, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 25.19884765587022, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 38, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 38, "generated_at": "2026-07-02T16:51:45Z", "losses": 18, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-35de956c8305ff90", "rated_matches": 66, "raw_elo_rating": 1458.1375092603982, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 29.75956752250197, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 45, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 45, "generated_at": "2026-07-02T16:51:45Z", "losses": 10, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-6e65dec497ff2de3", "rated_matches": 58, "raw_elo_rating": 1462.8759114421637, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 29.996350093562853, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-0fab95afbec0dd98", "rated_matches": 0, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "first_pass", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-f72c72b8f264c57a", "rated_matches": 0, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "first_pass", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 20, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 20, "generated_at": "2026-07-02T16:51:45Z", "losses": 9, "model": "qwen/qwen3.7-max", "point_rating_method": "sequential_elo", "public_id": "E-64624689e7cbd439", "rated_matches": 32, "raw_elo_rating": 1474.3822256759502, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 29.060555798589352, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 29, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 29, "generated_at": "2026-07-02T16:51:45Z", "losses": 3, "model": "qwen/qwen3.7-plus", "point_rating_method": "sequential_elo", "public_id": "E-6c2a9942e92223c8", "rated_matches": 32, "raw_elo_rating": 1459.6484452884602, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "first_pass", "score": 26.781275124406115, "uncertainty": 43.288827977848925, "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": 39, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-9c877cdf80f00ddf", "rated_matches": 72, "raw_elo_rating": 1605.3208067268397, "reasoning": "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": 52.84580662581403, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 33 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 0, "generated_at": "2026-07-17T22:36:00Z", "losses": 13, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-34ecad20175c262b", "rated_matches": 58, "raw_elo_rating": 1792.5148238948805, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 80.99070339953418, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 45 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "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": 60, "raw_elo_rating": 1847.4300953133004, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 89.61913049897616, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 53 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 37, "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": 74, "raw_elo_rating": 1819.8426403190977, "reasoning": "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": 86.1290402353659, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 61 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 24, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 24, "generated_at": "2026-07-02T16:51:45Z", "losses": 5, "model": "x-ai/grok-build-0.1", "point_rating_method": "sequential_elo", "public_id": "E-3e2fe948d2bcebb0", "rated_matches": 32, "raw_elo_rating": 1460.0573151384351, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 26.844526314718102, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 17, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 17, "generated_at": "2026-07-03T19:35:00Z", "losses": 10, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-650d06103e7fa176", "rated_matches": 34, "raw_elo_rating": 1467.3593961658648, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 28.286432306166148, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 21, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 21, "generated_at": "2026-07-02T06:10:40Z", "losses": 10, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-b5eb7da0f5021b69", "rated_matches": 32, "raw_elo_rating": 1394.7580906041408, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 16.7428920697459, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 27, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 27, "generated_at": "2026-07-02T16:51:45Z", "losses": 3, "model": "xiaomi/mimo-v2.5-pro", "point_rating_method": "sequential_elo", "public_id": "E-bd1bb7ac29877b8f", "rated_matches": 32, "raw_elo_rating": 1453.3775637489682, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 25.811184711276827, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 32, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 32, "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": 46, "raw_elo_rating": 1455.3488403943122, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 27.861909258061228, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 43, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 43, "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": 48, "raw_elo_rating": 1455.156829952007, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 28.01832850418103, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 40, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 40, "generated_at": "2026-07-11T17:22:09Z", "losses": 5, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-da1e9a6be31e371f", "rated_matches": 46, "raw_elo_rating": 1451.1771451962684, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 27.216557963728263, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 1 } ] }, "full_freedom/baseline": { "GB2-01": [ { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 41, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 41, "generated_at": "2026-07-02T16:51:45Z", "losses": 10, "model": "claude-opus-4-5", "point_rating_method": "sequential_elo", "public_id": "E-2e3eca63f7980fac", "rated_matches": 62, "raw_elo_rating": 1440.0631482289907, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 40.23843353793476, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 16, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 16, "generated_at": "2026-07-02T16:51:45Z", "losses": 19, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-757a6149e87d8b53", "rated_matches": 58, "raw_elo_rating": 1573.4332627403917, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 57.22022924708464, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 36, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 36, "generated_at": "2026-07-25T15:48:00Z", "losses": 5, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-6c30dc38efb07e9e", "rated_matches": 52, "raw_elo_rating": 1538.1067446190257, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 52.29484651326144, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 12, "coverage_status": "rated", "distinct_rated_opponents": 26, "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": 52, "raw_elo_rating": 1790.6111623268318, "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": 84.85604721208772, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 31 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 12, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 12, "generated_at": "2026-07-02T16:51:45Z", "losses": 9, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-73ff84eba4ec19cb", "rated_matches": 44, "raw_elo_rating": 1562.340614191469, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 54.81582799890011, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 47, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 47, "generated_at": "2026-07-02T16:51:45Z", "losses": 11, "model": "cohere/north-mini-code", "point_rating_method": "sequential_elo", "public_id": "E-194759b182ce3244", "rated_matches": 72, "raw_elo_rating": 1467.9446557274146, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 44.295334926890746, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 18, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 18, "generated_at": "2026-07-11T17:22:09Z", "losses": 47, "model": "cohere/north-mini-code", "point_rating_method": "sequential_elo", "public_id": "E-c309b463b29efb71", "rated_matches": 68, "raw_elo_rating": 1209.147982936052, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 10.750205159497384, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 26, "coverage_status": "rated", "distinct_rated_opponents": 37, "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": 74, "raw_elo_rating": 1483.438796086254, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 46.374389594950806, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugin_count": 1, "attempted_matches": 84, "capped_draws": 28, "coverage_status": "rated", "distinct_rated_opponents": 42, "draws": 28, "generated_at": "2026-07-02T16:51:45Z", "losses": 30, "model": "deepseek/deepseek-v4-pro", "point_rating_method": "sequential_elo", "public_id": "E-e121525dd1846069", "rated_matches": 84, "raw_elo_rating": 1490.425377493292, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 47.636647445449704, "uncertainty": 10.482614454664043, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 23, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 23, "generated_at": "2026-07-02T16:51:45Z", "losses": 17, "model": "google/gemini-3.1-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-cc0af0bfa6a9a29f", "rated_matches": 46, "raw_elo_rating": 1337.399703918666, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 25.974404110127313, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-21c0edac8ac36f2e", "rated_matches": 0, "reasoning": "minimal", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "minimal", "repair_status": "first_pass", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-cf51875df5447bc2", "rated_matches": 0, "reasoning": "minimal", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "minimal", "repair_status": "first_pass", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-e0c4f14c94c0a42a", "rated_matches": 0, "reasoning": "minimal", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "minimal", "repair_status": "first_pass", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-e9733de94d982ade", "rated_matches": 0, "reasoning": "minimal", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "minimal", "repair_status": "first_pass", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 76, "capped_draws": 18, "coverage_status": "rated", "distinct_rated_opponents": 38, "draws": 18, "generated_at": "2026-07-02T16:51:45Z", "losses": 26, "model": "google/gemma-4-31b-it", "point_rating_method": "sequential_elo", "public_id": "E-caaa54d3c88e6570", "rated_matches": 76, "raw_elo_rating": 1467.5007886172232, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 44.39699646208931, "uncertainty": 13.230288229818967, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 23, "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": 46, "raw_elo_rating": 1573.0858652952545, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 56.36684029870736, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 2, "coverage_status": "rated", "distinct_rated_opponents": 33, "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": 66, "raw_elo_rating": 1840.8511544908365, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 92.11822076992448, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 58 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 21, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 21, "generated_at": "2026-07-01T00:15:48Z", "losses": 36, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-3834aa9e894c458b", "rated_matches": 66, "raw_elo_rating": 1298.181557125292, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 22.13935135696185, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 76, "capped_draws": 18, "coverage_status": "rated", "distinct_rated_opponents": 38, "draws": 18, "generated_at": "2026-07-02T06:10:40Z", "losses": 32, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-b6ed01547d27188c", "rated_matches": 76, "raw_elo_rating": 1491.1216061968814, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 47.44297161319194, "uncertainty": 13.230288229818967, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 78, "capped_draws": 31, "coverage_status": "rated", "distinct_rated_opponents": 39, "draws": 31, "generated_at": "2026-07-02T16:51:45Z", "losses": 27, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-ea1cb793f92b3cff", "rated_matches": 78, "raw_elo_rating": 1434.2195613946458, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 40.18016744239998, "uncertainty": 12.5043950463012, "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": 1401.7572655735244, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 35.760272791755234, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 20, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 20, "generated_at": "2026-07-09T17:30:50Z", "losses": 22, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-9eb27042bf28d67c", "rated_matches": 72, "raw_elo_rating": 1493.5688055188753, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 47.599645764976906, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 30 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 22, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 22, "generated_at": "2026-07-02T16:51:45Z", "losses": 26, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-a8887794a1195b75", "rated_matches": 64, "raw_elo_rating": 1528.155373010458, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 51.69894958662488, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 16 }, { "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": 38, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-f491ad1b583dbcac", "rated_matches": 62, "raw_elo_rating": 1217.7883112287816, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 11.575427783168683, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 86, "capped_draws": 62, "coverage_status": "rated", "distinct_rated_opponents": 43, "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": 86, "raw_elo_rating": 1491.1257108359016, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 47.79163908116498, "uncertainty": 9.855626741889738, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 20, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 20, "generated_at": "2026-07-10T05:30:29Z", "losses": 35, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-959ed218b1c5605b", "rated_matches": 67, "raw_elo_rating": 1353.552660186412, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 29.32612813598716, "uncertainty": 16.883906259083243, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 15, "coverage_status": "rated", "distinct_rated_opponents": 33, "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": 66, "raw_elo_rating": 1567.6962238815845, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 56.894074601780616, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 21, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 21, "generated_at": "2026-07-10T05:30:29Z", "losses": 24, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-40742129939a44b5", "rated_matches": 64, "raw_elo_rating": 1569.1781720591457, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 56.98896235225361, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 22, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 22, "generated_at": "2026-07-24T13:40:00Z", "losses": 20, "model": "inclusionai/ling-3.0-flash", "point_rating_method": "sequential_elo", "public_id": "E-3c618b88b6bdb039", "rated_matches": 62, "raw_elo_rating": 1413.3141988259033, "reasoning": "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": 36.78907642211369, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 13, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 13, "generated_at": "2026-07-24T13:40:00Z", "losses": 33, "model": "inclusionai/ling-3.0-flash", "point_rating_method": "sequential_elo", "public_id": "E-f9af396559c3a1cd", "rated_matches": 64, "raw_elo_rating": 1531.8401159225134, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 52.17410821779725, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 18, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 18, "generated_at": "2026-07-24T13:40:00Z", "losses": 25, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-9f5585b5fd96f2c3", "rated_matches": 64, "raw_elo_rating": 1499.0882262859534, "reasoning": "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": 47.95065398518296, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 23, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 23, "generated_at": "2026-07-24T13:40:00Z", "losses": 25, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-ed0f8e084958eebc", "rated_matches": 70, "raw_elo_rating": 1459.2708693088157, "reasoning": "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": 43.09238481644139, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 22 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 15, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 15, "generated_at": "2026-07-02T16:51:45Z", "losses": 23, "model": "minimax/minimax-m3", "point_rating_method": "sequential_elo", "public_id": "E-444510032bc433fc", "rated_matches": 70, "raw_elo_rating": 1497.8471484037084, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 48.06691150878728, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 6, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 6, "generated_at": "2026-07-02T16:51:45Z", "losses": 40, "model": "mistralai/mistral-medium-3-5", "point_rating_method": "sequential_elo", "public_id": "E-a0a38f5e77e983bc", "rated_matches": 67, "raw_elo_rating": 1404.142971092423, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 35.8499002021569, "uncertainty": 16.883906259083243, "unilateral_faults": 3, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 5, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 5, "generated_at": "2026-07-21T14:20:15Z", "losses": 16, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-2292c77f8fb54ff1", "rated_matches": 42, "raw_elo_rating": 1575.905025468466, "reasoning": "low", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "low", "repair_status": "first_pass", "score": 56.38821150296458, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 26, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 26, "generated_at": "2026-07-24T14:00:00Z", "losses": 5, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-fb8801908d28001f", "rated_matches": 42, "raw_elo_rating": 1579.431886642528, "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": 56.843010811301525, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 11, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 11, "generated_at": "2026-07-02T16:51:45Z", "losses": 17, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-0ce5e196701b51f3", "rated_matches": 44, "raw_elo_rating": 1552.6926849361364, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 53.57169863410424, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 10, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 10, "generated_at": "2026-07-21T14:20:15Z", "losses": 18, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-fbf1a1af436a64a7", "rated_matches": 46, "raw_elo_rating": 1468.7292262906526, "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": 42.909739239921585, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 11, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 11, "generated_at": "2026-07-21T14:20:15Z", "losses": 18, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-55f6c0e3dc8a8065", "rated_matches": 42, "raw_elo_rating": 1401.3232146087823, "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": 33.87536426896172, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 7, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 7, "generated_at": "2026-07-24T13:40:00Z", "losses": 31, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-8461eb1b16e40129", "rated_matches": 68, "raw_elo_rating": 1644.0015520281916, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 66.8258749095413, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 30 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 22, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 22, "generated_at": "2026-07-24T13:40:00Z", "losses": 24, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-c58ec61528547516", "rated_matches": 68, "raw_elo_rating": 1514.516696009371, "reasoning": "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": 50.12841502919046, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 22 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 21, "coverage_status": "rated", "distinct_rated_opponents": 35, "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": 70, "raw_elo_rating": 1586.388491274526, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 59.484582777796334, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 31 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 18, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 18, "generated_at": "2026-07-03T18:55:00Z", "losses": 36, "model": "qwen/qwen3.7-plus", "point_rating_method": "sequential_elo", "public_id": "E-5e09f0c994a59f3c", "rated_matches": 70, "raw_elo_rating": 1372.448577341908, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 31.896390308583022, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 14, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 14, "generated_at": "2026-07-21T14:20:15Z", "losses": 26, "model": "stepfun/step-3.7-flash", "point_rating_method": "sequential_elo", "public_id": "E-09ecaa63c419b917", "rated_matches": 58, "raw_elo_rating": 1474.9655056194315, "reasoning": "low", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "low", "repair_status": "repaired", "score": 44.52251713937394, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 76, "capped_draws": 15, "coverage_status": "rated", "distinct_rated_opponents": 38, "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": 76, "raw_elo_rating": 1686.569380601013, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 72.6465473220185, "uncertainty": 13.230288229818967, "unilateral_faults": 0, "wins": 46 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 33, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 33, "generated_at": "2026-07-24T13:40:00Z", "losses": 24, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-9e638fc0ac98df4f", "rated_matches": 64, "raw_elo_rating": 1361.1872095331362, "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": 30.167904978958862, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 26, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 26, "generated_at": "2026-07-24T13:40:00Z", "losses": 26, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-bc7c657b08ebac66", "rated_matches": 62, "raw_elo_rating": 1307.1395985619376, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 23.09754381568927, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 26, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 26, "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": 42, "raw_elo_rating": 1561.6048271216569, "reasoning": "low", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "low", "repair_status": "first_pass", "score": 54.54415810924417, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 13, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 13, "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": 42, "raw_elo_rating": 1647.4292378462578, "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": 65.61147284310373, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 22 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 3, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 3, "generated_at": "2026-07-02T06:10:40Z", "losses": 28, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-2cdd8ae895784956", "rated_matches": 66, "raw_elo_rating": 1603.4984396054735, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 61.51087751648144, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 35 }, { "admitted_plugin_count": 1, "attempted_matches": 80, "capped_draws": 24, "coverage_status": "rated", "distinct_rated_opponents": 40, "draws": 24, "generated_at": "2026-07-02T16:51:45Z", "losses": 29, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-912a4a40bbdcbd45", "rated_matches": 80, "raw_elo_rating": 1464.210701481668, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 44.11970871031872, "uncertainty": 11.805555555555554, "unilateral_faults": 0, "wins": 27 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 27, "coverage_status": "rated", "distinct_rated_opponents": 37, "draws": 27, "generated_at": "2026-07-01T00:15:48Z", "losses": 32, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-a168350bd057f924", "rated_matches": 74, "raw_elo_rating": 1407.0915273332496, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 36.5291806942871, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 80, "capped_draws": 26, "coverage_status": "rated", "distinct_rated_opponents": 40, "draws": 26, "generated_at": "2026-07-02T16:51:45Z", "losses": 30, "model": "xiaomi/mimo-v2.5-pro", "point_rating_method": "sequential_elo", "public_id": "E-9ce4191c7f1f3b3e", "rated_matches": 80, "raw_elo_rating": 1431.0064719759512, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 39.837923897204504, "uncertainty": 11.805555555555554, "unilateral_faults": 0, "wins": 24 }, { "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": 1525.552950569837, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 50.39247705958617, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 13, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 13, "generated_at": "2026-07-11T14:00:45Z", "losses": 23, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-5c3b7f5666a38043", "rated_matches": 48, "raw_elo_rating": 1450.5055406161034, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 40.71488884305701, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 8, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 8, "generated_at": "2026-07-02T06:10:40Z", "losses": 13, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-6a7eb114b16dc845", "rated_matches": 44, "raw_elo_rating": 1565.718530617541, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 55.25142043602127, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 1, "generated_at": "2026-07-02T16:51:45Z", "losses": 25, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-c8076ea61de8da45", "rated_matches": 44, "raw_elo_rating": 1373.8053371881217, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 30.503639526939683, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 18 } ], "GB2-02": [ { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 54, "generated_at": "2026-07-02T16:51:45Z", "losses": 5, "model": "claude-opus-4-5", "point_rating_method": "sequential_elo", "public_id": "E-16462f3d1f3a7b19", "rated_matches": 62, "raw_elo_rating": 1505.4621431048597, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 35.18281284883366, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 54, "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": 64, "raw_elo_rating": 1478.0802986534875, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 28.832423610551896, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 17, "generated_at": "2026-07-25T10:50:00Z", "losses": 11, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-51ddad48e10b006f", "rated_matches": 52, "raw_elo_rating": 1650.621303202366, "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": 68.75099079248285, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 33, "generated_at": "2026-07-25T10:50:00Z", "losses": 4, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-772d1a710082ddb3", "rated_matches": 52, "raw_elo_rating": 1584.041640885369, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 52.85628336403163, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 35, "generated_at": "2026-07-02T16:51:45Z", "losses": 3, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-e501d6808bd19ccc", "rated_matches": 38, "raw_elo_rating": 1479.0637410889549, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 25.620538806917818, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 67, "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": 70, "raw_elo_rating": 1498.6255036896976, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 34.248739162857234, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 52, "generated_at": "2026-07-02T06:10:40Z", "losses": 0, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-bc9a8c3886a48505", "rated_matches": 52, "raw_elo_rating": 1493.295680760276, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 31.192303158862845, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 51, "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": 54, "raw_elo_rating": 1493.1855742024472, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 31.406715690809293, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 34, "generated_at": "2026-07-02T16:51:45Z", "losses": 3, "model": "google/gemini-3.1-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-20b3484be872df52", "rated_matches": 38, "raw_elo_rating": 1492.955126495349, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 28.936859423853782, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-1010911d64a09b68", "rated_matches": 0, "reasoning": "minimal", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "minimal", "repair_status": "repaired", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-e65fdcb71f09a611", "rated_matches": 0, "reasoning": "minimal", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "minimal", "repair_status": "repaired", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-4492f6d65cd6280b", "rated_matches": 0, "reasoning": "minimal", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "minimal", "repair_status": "first_pass", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-9c8b43dc41bad760", "rated_matches": 0, "reasoning": "minimal", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "minimal", "repair_status": "repaired", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 31, "generated_at": "2026-07-02T16:51:45Z", "losses": 10, "model": "gpt-4.1", "point_rating_method": "sequential_elo", "public_id": "E-e4707b8e4c581ede", "rated_matches": 44, "raw_elo_rating": 1462.3741079493293, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 22.69204681390362, "uncertainty": 30.785599249992988, "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": "2026-07-02T16:51:45Z", "losses": 1, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-98ddce22d3eb5886", "rated_matches": 66, "raw_elo_rating": 1488.7746335763547, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 31.56362733585045, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 59, "generated_at": "2026-07-02T16:51:45Z", "losses": 1, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-322cbb8be1559087", "rated_matches": 60, "raw_elo_rating": 1485.6404248008662, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 30.2550926089942, "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": 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": 1501.07775493319, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 33.94047996889768, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 52, "generated_at": "2026-07-01T00:15:48Z", "losses": 2, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-dd45dfa7984ab9fa", "rated_matches": 56, "raw_elo_rating": 1509.288358746711, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 35.47888477141212, "uncertainty": 22.47661785325219, "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": "2026-07-09T17:30:50Z", "losses": 2, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-038a95fb13c8aa94", "rated_matches": 52, "raw_elo_rating": 1496.4171488213428, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 31.93749801043312, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 56, "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": 58, "raw_elo_rating": 1476.3347652037166, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 27.828028657999937, "uncertainty": 21.344455490411935, "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": 1501.0844310212506, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 34.672692270295386, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 2 }, { "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": 7, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-be95cc83ce87847c", "rated_matches": 56, "raw_elo_rating": 1441.841398262491, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 19.377125367304995, "uncertainty": 22.47661785325219, "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": "2026-07-02T16:51:45Z", "losses": 2, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-51e935956fa76015", "rated_matches": 70, "raw_elo_rating": 1501.6155054033272, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 34.962548767694756, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 62, "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": 62, "raw_elo_rating": 1488.2182531123694, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 31.0661415287832, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 46, "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": 58, "raw_elo_rating": 1500.5716831996058, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 33.61416074557098, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 63, "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": 68, "raw_elo_rating": 1476.5798481424442, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 28.82265996372679, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 60, "generated_at": "2026-07-24T13:40:00Z", "losses": 2, "model": "inclusionai/ling-3.0-flash", "point_rating_method": "sequential_elo", "public_id": "E-fc495094a55d2f94", "rated_matches": 62, "raw_elo_rating": 1472.6963835500655, "reasoning": "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": 27.360571887099717, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 63, "generated_at": "2026-07-24T13:40:00Z", "losses": 1, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-a0c74818516a7f27", "rated_matches": 64, "raw_elo_rating": 1480.4728086634052, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 29.40359272291873, "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": 59, "generated_at": "2026-07-02T16:51:45Z", "losses": 1, "model": "minimax/minimax-m3", "point_rating_method": "sequential_elo", "public_id": "E-1e46941293882535", "rated_matches": 60, "raw_elo_rating": 1474.9611713998297, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 27.705611244015376, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 35, "generated_at": "2026-07-24T14:00:00Z", "losses": 0, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-d3d3da42e99695b1", "rated_matches": 36, "raw_elo_rating": 1507.2663480895285, "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": 31.945574302047177, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 38, "generated_at": "2026-07-21T14:20:15Z", "losses": 1, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-fc3ad6db6543001f", "rated_matches": 42, "raw_elo_rating": 1524.5527886295524, "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": 37.20880876571812, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 47, "generated_at": "2026-07-11T17:22:09Z", "losses": 5, "model": "nex-agi/nex-n2-pro", "point_rating_method": "sequential_elo", "public_id": "E-811f47e902ce0d21", "rated_matches": 54, "raw_elo_rating": 1471.4715871938947, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 26.222888398882304, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 34, "generated_at": "2026-07-21T14:20:15Z", "losses": 1, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-e48b0ea99dfc517c", "rated_matches": 36, "raw_elo_rating": 1477.5847832126149, "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": 24.85962983613944, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 41, "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": 42, "raw_elo_rating": 1490.3396386261843, "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": 29.041029137757743, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 60, "generated_at": "2026-07-24T13:40:00Z", "losses": 2, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-d8c7a78cc7f666dc", "rated_matches": 64, "raw_elo_rating": 1477.5865175875335, "reasoning": "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": 28.71454218394329, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 50, "generated_at": "2026-07-02T16:51:45Z", "losses": 1, "model": "qwen/qwen3.7-max", "point_rating_method": "sequential_elo", "public_id": "E-5f64c2ae9860ba38", "rated_matches": 54, "raw_elo_rating": 1502.383120170803, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 33.60246582139271, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 58, "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": 58, "raw_elo_rating": 1495.3686744490708, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 32.37203516308192, "uncertainty": 21.344455490411935, "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": "2026-07-02T16:51:45Z", "losses": 6, "model": "tencent/hy3-preview", "point_rating_method": "sequential_elo", "public_id": "E-d910e47dd13c2c71", "rated_matches": 68, "raw_elo_rating": 1465.8989139702087, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 26.272777344588157, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 64, "generated_at": "2026-07-24T13:40:00Z", "losses": 1, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-66a4f0abd099d8f1", "rated_matches": 66, "raw_elo_rating": 1498.8766895584683, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 33.97531310705538, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 37, "generated_at": "2026-07-21T14:20:15Z", "losses": 2, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-1331dea6489316f2", "rated_matches": 40, "raw_elo_rating": 1479.3226256551393, "reasoning": "low", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "low", "repair_status": "repaired", "score": 26.059959111062756, "uncertainty": 34.33688094430304, "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": "2026-07-24T14:00:00Z", "losses": 1, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-1b0da3150a77b47b", "rated_matches": 40, "raw_elo_rating": 1496.3929521312668, "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": 30.135195235787354, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 57, "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": 60, "raw_elo_rating": 1468.175080615072, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 26.085553048269652, "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": 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": 1477.3293696473902, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 28.65315269754207, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 35, "generated_at": "2026-07-02T16:51:45Z", "losses": 3, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-4959351a96fd2b82", "rated_matches": 38, "raw_elo_rating": 1467.0041051022636, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 22.741515708401067, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 37, "generated_at": "2026-07-11T14:00:45Z", "losses": 1, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-925b589068dc7268", "rated_matches": 38, "raw_elo_rating": 1485.7980200777038, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 27.22822786004183, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 31, "generated_at": "2026-07-01T00:15:48Z", "losses": 4, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-b090ee9c8b9921ad", "rated_matches": 38, "raw_elo_rating": 1489.347643659299, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 28.07563720919052, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 3 } ], "GB2-03": [ { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 9, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 37, "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": 54, "raw_elo_rating": 1544.092140040724, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 54.1033903036507, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 4, "generated_at": "2026-07-25T15:48:00Z", "losses": 15, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-49aaba66f6b19080", "rated_matches": 42, "raw_elo_rating": 1584.5474115941763, "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": 59.72579535069838, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 8, "generated_at": "2026-07-25T15:48:00Z", "losses": 15, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-ecf847457e616425", "rated_matches": 40, "raw_elo_rating": 1469.8145918606804, "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": 40.15994036002895, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 4, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 13, "generated_at": "2026-07-02T16:51:45Z", "losses": 15, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-e7d1e6857fc48e7a", "rated_matches": 38, "raw_elo_rating": 1485.2660520172667, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 42.495274622791904, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 2, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 20, "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": 50, "raw_elo_rating": 1449.5908015255636, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 37.84215337762568, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 32, "generated_at": "2026-07-02T16:51:45Z", "losses": 21, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-ae9d59ec3a8a1d63", "rated_matches": 72, "raw_elo_rating": 1484.593650623879, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 45.2839963442032, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 15, "generated_at": "2026-07-02T16:51:45Z", "losses": 30, "model": "deepseek/deepseek-v4-pro", "point_rating_method": "sequential_elo", "public_id": "E-f82a334a0fd1fb8e", "rated_matches": 54, "raw_elo_rating": 1345.207385463267, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 20.61584059577335, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-28274045fbc35ae9", "rated_matches": 0, "reasoning": "minimal", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "minimal", "repair_status": "repaired", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-6743f1c221046d65", "rated_matches": 0, "reasoning": "minimal", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "minimal", "repair_status": "first_pass", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-80b8c1a18d6dd238", "rated_matches": 0, "reasoning": "minimal", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "minimal", "repair_status": "first_pass", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 30, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 15, "draws": 10, "generated_at": "2026-07-02T16:51:45Z", "losses": 10, "model": "gpt-4.1", "point_rating_method": "sequential_elo", "public_id": "E-c7da9914f86ee846", "rated_matches": 30, "raw_elo_rating": 1528.356600835827, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 48.43891826866166, "uncertainty": 46.05265101338746, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 2, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 29, "generated_at": "2026-07-02T16:51:45Z", "losses": 8, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-ebd456dc6b320c61", "rated_matches": 50, "raw_elo_rating": 1557.920108094656, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 56.08227965708637, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 55, "generated_at": "2026-07-02T16:51:45Z", "losses": 1, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-35117a2e624d7970", "rated_matches": 56, "raw_elo_rating": 1503.163188021814, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 47.37265857229025, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 21, "generated_at": "2026-07-01T00:15:48Z", "losses": 13, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-a51cd55f211305c2", "rated_matches": 48, "raw_elo_rating": 1519.4452930208924, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 49.41347491451111, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 20, "generated_at": "2026-07-02T06:10:40Z", "losses": 9, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-dfa5098ec9c3cf47", "rated_matches": 52, "raw_elo_rating": 1546.7025778967595, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 54.37316359475259, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 9, "generated_at": "2026-07-01T00:15:48Z", "losses": 25, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-0ecb5b73c09f13b2", "rated_matches": 50, "raw_elo_rating": 1415.921753576121, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 32.17307170658813, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 32, "generated_at": "2026-07-02T06:10:40Z", "losses": 20, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-e4eac938bdd5d40e", "rated_matches": 62, "raw_elo_rating": 1425.120377382622, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 34.66749845510415, "uncertainty": 19.244078834871203, "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": 1511.8331563488234, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 49.64522504637243, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 2, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 20, "generated_at": "2026-07-02T16:51:45Z", "losses": 9, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-446036823932df16", "rated_matches": 46, "raw_elo_rating": 1534.1619524841408, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 51.688836210667226, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 19, "generated_at": "2026-07-10T05:30:29Z", "losses": 13, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-d192bb239087b778", "rated_matches": 46, "raw_elo_rating": 1480.9188274128549, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 42.723936908981315, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 10, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 33, "generated_at": "2026-07-10T05:30:29Z", "losses": 18, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-527999604d620080", "rated_matches": 68, "raw_elo_rating": 1496.7556987902174, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 47.10653317662637, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 10, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 24, "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": 58, "raw_elo_rating": 1502.323955650604, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 47.38385520211626, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 18, "generated_at": "2026-07-24T13:40:00Z", "losses": 22, "model": "inclusionai/ling-3.0-flash", "point_rating_method": "sequential_elo", "public_id": "E-2524de3c7d4a81b7", "rated_matches": 50, "raw_elo_rating": 1391.1702280030038, "reasoning": "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": 28.00549262423692, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "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": 1384.97093175478, "reasoning": "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": 26.96167585855616, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 23, "generated_at": "2026-07-24T13:40:00Z", "losses": 18, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-198e8ddfe9f7ce20", "rated_matches": 48, "raw_elo_rating": 1420.98998690728, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 32.83589980329351, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 5, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 23, "generated_at": "2026-07-24T13:40:00Z", "losses": 14, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-84709c769628f9a2", "rated_matches": 52, "raw_elo_rating": 1450.342959592334, "reasoning": "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": 38.14845338678729, "uncertainty": 24.930281974344517, "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": 1532.5793891002238, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 53.01828026826074, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "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": 34, "raw_elo_rating": 1646.480963646981, "reasoning": "low", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "low", "repair_status": "first_pass", "score": 69.04049963440926, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 2, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "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": 34, "raw_elo_rating": 1595.879314119247, "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": 60.520363149032555, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 2, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 31, "generated_at": "2026-07-02T16:51:45Z", "losses": 13, "model": "nex-agi/nex-n2-pro", "point_rating_method": "sequential_elo", "public_id": "E-a05d4cef5f788f16", "rated_matches": 50, "raw_elo_rating": 1423.1096514863327, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 33.38334591324993, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 30, "capped_draws": 4, "coverage_status": "under_covered", "distinct_rated_opponents": 15, "draws": 18, "generated_at": "2026-07-02T16:51:45Z", "losses": 9, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-eb6e8a61f620acfd", "rated_matches": 30, "raw_elo_rating": 1419.179191434123, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 30.055991271142776, "uncertainty": 46.05265101338746, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 21, "generated_at": "2026-07-21T14:20:15Z", "losses": 9, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-08888c30d05ca8cb", "rated_matches": 34, "raw_elo_rating": 1451.000231276127, "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": 36.12610779925329, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 1, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 24, "generated_at": "2026-07-21T14:20:15Z", "losses": 8, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-c90a449ff5e7b79a", "rated_matches": 36, "raw_elo_rating": 1467.5326664526883, "reasoning": "low", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "low", "repair_status": "first_pass", "score": 39.2217430159087, "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": 15, "generated_at": "2026-07-24T13:40:00Z", "losses": 18, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-467272d131a1a99b", "rated_matches": 50, "raw_elo_rating": 1445.2282376124174, "reasoning": "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": 37.10759945867067, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 7, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 30, "generated_at": "2026-07-24T13:40:00Z", "losses": 13, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-91efdb0c216f8504", "rated_matches": 52, "raw_elo_rating": 1502.0964642833512, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 46.86253539161154, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 3, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 43, "generated_at": "2026-07-02T16:51:45Z", "losses": 7, "model": "qwen/qwen3.7-max", "point_rating_method": "sequential_elo", "public_id": "E-3325ebad2ef000c1", "rated_matches": 54, "raw_elo_rating": 1440.381307433771, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 36.64090722117748, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 6, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 21, "generated_at": "2026-07-21T14:20:15Z", "losses": 10, "model": "stepfun/step-3.7-flash", "point_rating_method": "sequential_elo", "public_id": "E-02b2a2f01700292d", "rated_matches": 40, "raw_elo_rating": 1526.648010167357, "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": 49.72936122718848, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 24, "generated_at": "2026-07-02T16:51:45Z", "losses": 20, "model": "tencent/hy3-preview", "point_rating_method": "sequential_elo", "public_id": "E-2346cd049910cc0a", "rated_matches": 70, "raw_elo_rating": 1437.0101184596929, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 37.16178607693494, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 4, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 25, "generated_at": "2026-07-24T13:40:00Z", "losses": 14, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-78048b7c08122f1c", "rated_matches": 48, "raw_elo_rating": 1437.6364882122498, "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": 35.638782010613795, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 8, "coverage_status": "rated", "distinct_rated_opponents": 25, "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": 50, "raw_elo_rating": 1608.1811038061967, "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": 64.54505799237667, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 8, "generated_at": "2026-07-24T14:00:00Z", "losses": 24, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-02f7e54245bd5c85", "rated_matches": 34, "raw_elo_rating": 1315.633820214499, "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": 13.333564304232562, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 29, "generated_at": "2026-07-21T14:20:15Z", "losses": 6, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-3c1904811d11cd84", "rated_matches": 44, "raw_elo_rating": 1517.811112552577, "reasoning": "low", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "low", "repair_status": "repaired", "score": 48.71979631230576, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 2, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 30, "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": 50, "raw_elo_rating": 1530.1875388618716, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 51.412762414887055, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 4, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 31, "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": 50, "raw_elo_rating": 1453.2674122393996, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 38.461208791388664, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugin_count": 1, "attempted_matches": 30, "capped_draws": 1, "coverage_status": "under_covered", "distinct_rated_opponents": 15, "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": 30, "raw_elo_rating": 1496.216497101582, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 43.02727511027319, "uncertainty": 46.05265101338746, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 4, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 16, "generated_at": "2026-07-11T14:00:45Z", "losses": 8, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-583be34ca1fb2631", "rated_matches": 32, "raw_elo_rating": 1501.165649912756, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 44.232887527949885, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 30, "capped_draws": 5, "coverage_status": "under_covered", "distinct_rated_opponents": 15, "draws": 9, "generated_at": "2026-07-02T06:10:40Z", "losses": 14, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-f1af7b938699d971", "rated_matches": 30, "raw_elo_rating": 1370.673621540632, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 21.88878566321076, "uncertainty": 46.05265101338746, "unilateral_faults": 0, "wins": 7 } ], "GB2-04": [ { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 34, "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": 54, "raw_elo_rating": 1531.367240999507, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 42.06024334765576, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 39, "generated_at": "2026-07-02T16:51:45Z", "losses": 8, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-688a139ef8557587", "rated_matches": 52, "raw_elo_rating": 1482.9701197438192, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 32.22275482443267, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 26, "generated_at": "2026-07-25T15:48:00Z", "losses": 14, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-72e9307528761b35", "rated_matches": 56, "raw_elo_rating": 1518.0882324573904, "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": 39.60625250250319, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 12, "generated_at": "2026-07-25T15:48:00Z", "losses": 17, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-9e7782014171d35f", "rated_matches": 52, "raw_elo_rating": 1604.4941766592642, "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": 56.42036349510957, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 23 }, { "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": 2, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-be938b7d5557f479", "rated_matches": 38, "raw_elo_rating": 1524.5933624248837, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 38.697311929291594, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 26, "generated_at": "2026-07-02T16:51:45Z", "losses": 21, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-81bc9a578754f220", "rated_matches": 48, "raw_elo_rating": 1344.1040186798332, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 4.134248861158849, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 65, "generated_at": "2026-07-01T00:15:48Z", "losses": 1, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-a43d18fadfcc5a89", "rated_matches": 70, "raw_elo_rating": 1515.3888515107851, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 40.16590248575036, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 58, "generated_at": "2026-07-02T06:10:40Z", "losses": 0, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-cb48b9466ec54175", "rated_matches": 58, "raw_elo_rating": 1508.100473988519, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 37.797858518143734, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-6a79049fd9ab6f5d", "rated_matches": 0, "reasoning": "minimal", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "minimal", "repair_status": "first_pass", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-b05b0185d0e8dc2a", "rated_matches": 0, "reasoning": "minimal", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "minimal", "repair_status": "repaired", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-0b528ba96380a3b5", "rated_matches": 0, "reasoning": "minimal", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "minimal", "repair_status": "first_pass", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-846809faa1345207", "rated_matches": 0, "reasoning": "minimal", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "minimal", "repair_status": "repaired", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 43, "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": 52, "raw_elo_rating": 1489.2296172501635, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 33.4691324962955, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 23, "generated_at": "2026-07-02T16:51:45Z", "losses": 9, "model": "gpt-4.1", "point_rating_method": "sequential_elo", "public_id": "E-ecb06954153be8d5", "rated_matches": 34, "raw_elo_rating": 1459.143974925331, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 24.956096391857447, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 49, "generated_at": "2026-07-02T16:51:45Z", "losses": 8, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-8d62bf1b340a70dc", "rated_matches": 68, "raw_elo_rating": 1495.1061108254105, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 35.99123440741221, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 42, "generated_at": "2026-07-02T16:51:45Z", "losses": 12, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-0880cdf1a43cb90c", "rated_matches": 70, "raw_elo_rating": 1490.652343272743, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 35.24042220294854, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 54, "generated_at": "2026-07-02T06:10:40Z", "losses": 4, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-c9bf6a0be0c43fd1", "rated_matches": 64, "raw_elo_rating": 1469.424915746871, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 30.587027141314085, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 43, "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": 56, "raw_elo_rating": 1473.3753217645994, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 30.703113955837612, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 43, "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": 62, "raw_elo_rating": 1472.5352153209826, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 31.05075873870246, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 49, "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": 64, "raw_elo_rating": 1498.8576559280334, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 36.44761102146728, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 48, "generated_at": "2026-07-02T16:51:45Z", "losses": 12, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-ba1aa87056709e9a", "rated_matches": 66, "raw_elo_rating": 1498.700299003465, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 36.564843479998515, "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": 50, "generated_at": "2026-07-10T05:30:29Z", "losses": 13, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-71a01107bf3f9fc1", "rated_matches": 70, "raw_elo_rating": 1494.4916414654292, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 36.004894996193826, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 49, "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": 56, "raw_elo_rating": 1480.4876650964738, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 32.11930845299747, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 76, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 38, "draws": 71, "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": 76, "raw_elo_rating": 1520.0291620852558, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 41.465613636603344, "uncertainty": 13.230288229818967, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 56, "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": 62, "raw_elo_rating": 1475.5058004589516, "reasoning": "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": 31.642255258124266, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 36, "generated_at": "2026-07-24T13:40:00Z", "losses": 13, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-9e1d4bf411e97fa6", "rated_matches": 64, "raw_elo_rating": 1565.1896956500836, "reasoning": "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": 49.655504012060575, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 19, "generated_at": "2026-07-24T14:00:00Z", "losses": 6, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-3c06949f23d4a77f", "rated_matches": 34, "raw_elo_rating": 1534.8297093158149, "reasoning": "low", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "low", "repair_status": "repaired", "score": 40.02647693394225, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 27, "generated_at": "2026-07-21T14:20:15Z", "losses": 7, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-818ed7ee27b56509", "rated_matches": 40, "raw_elo_rating": 1494.7605140992057, "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": 33.072015379639225, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 51, "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": 56, "raw_elo_rating": 1491.0471982021531, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 34.22189995892514, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 29, "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": 40, "raw_elo_rating": 1495.9339395098796, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 33.30566532198333, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 18, "generated_at": "2026-07-21T14:20:15Z", "losses": 9, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-a4643af0a1bcc24c", "rated_matches": 34, "raw_elo_rating": 1475.8102858634056, "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": 28.274656356852365, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 24, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 12, "draws": 11, "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": 24, "raw_elo_rating": 1401.6541457347726, "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": 11.042241208882738, "uncertainty": 56.25, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 40, "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": 46, "raw_elo_rating": 1507.7518112619032, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 36.47987858051721, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 28, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 14, "draws": 16, "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": 28, "raw_elo_rating": 1539.8999918600214, "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": 39.70878194898091, "uncertainty": 49.09766908852594, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 34, "generated_at": "2026-07-02T16:51:45Z", "losses": 6, "model": "tencent/hy3-preview", "point_rating_method": "sequential_elo", "public_id": "E-3fd10f7865cc280e", "rated_matches": 50, "raw_elo_rating": 1521.129620533277, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 39.60853817575416, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 30, "generated_at": "2026-07-24T13:40:00Z", "losses": 16, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-646ff33c7bab8b13", "rated_matches": 52, "raw_elo_rating": 1434.289539016747, "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": 22.529582359703383, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 52, "generated_at": "2026-07-24T13:40:00Z", "losses": 6, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-ddc16fa197bfc7c5", "rated_matches": 62, "raw_elo_rating": 1509.229278499366, "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": 38.35720162634748, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 28, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 14, "draws": 21, "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": 28, "raw_elo_rating": 1533.5405814547744, "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": 38.44250983571969, "uncertainty": 49.09766908852594, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 35, "generated_at": "2026-07-24T14:00:00Z", "losses": 4, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-617354569710a53d", "rated_matches": 44, "raw_elo_rating": 1529.50537203445, "reasoning": "low", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "low", "repair_status": "repaired", "score": 40.55603556868472, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 42, "generated_at": "2026-07-01T00:15:48Z", "losses": 5, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-7ad356726cce2b22", "rated_matches": 58, "raw_elo_rating": 1484.624320346856, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 33.123337330055804, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 48, "generated_at": "2026-07-02T06:10:40Z", "losses": 2, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-d58c55e107783a21", "rated_matches": 52, "raw_elo_rating": 1508.239089106963, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 37.254257620509655, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 27, "generated_at": "2026-07-02T16:51:45Z", "losses": 5, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-1d5f5ff0402ff944", "rated_matches": 38, "raw_elo_rating": 1541.791950099912, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 42.1218576925904, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 37, "generated_at": "2026-07-02T06:10:40Z", "losses": 1, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-3efc86009429a22c", "rated_matches": 40, "raw_elo_rating": 1499.4200524361283, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 33.99981262509591, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 30, "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": 40, "raw_elo_rating": 1486.846732114631, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 31.49624014279844, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 18, "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": 40, "raw_elo_rating": 1505.5790197351166, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 35.22617293842966, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 11 } ], "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": 24, "model": "claude-opus-4-5", "point_rating_method": "sequential_elo", "public_id": "E-934b5bc34a7e20b9", "rated_matches": 66, "raw_elo_rating": 1537.0274446215944, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 50.38845226238323, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 42 }, { "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": 36, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-233f9cae6335e53d", "rated_matches": 66, "raw_elo_rating": 1402.501367016649, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 34.69618438144857, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 30 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 0, "generated_at": "2026-07-25T10:50:00Z", "losses": 15, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-09963ffe0b0fa5fd", "rated_matches": 60, "raw_elo_rating": 1828.041975577455, "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": 84.06109558414614, "uncertainty": 20.268439966447993, "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": 14, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-b53cb955b1d8baab", "rated_matches": 58, "raw_elo_rating": 1819.349185874928, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 82.94668203406992, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 44 }, { "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": 27, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-e619c51e7d5d70d2", "rated_matches": 48, "raw_elo_rating": 1433.5767315502376, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 37.35580390238191, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 41, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-0dca18c79b6ac9d7", "rated_matches": 66, "raw_elo_rating": 1462.271811781849, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 41.66831831500828, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 41, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-b8554f0ccf0845da", "rated_matches": 64, "raw_elo_rating": 1397.1418637639106, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 33.98397291984452, "uncertainty": 18.26736729460423, "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": 47, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-efa8d9109b008ee9", "rated_matches": 84, "raw_elo_rating": 1438.4527555048498, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 39.529291228691534, "uncertainty": 10.482614454664043, "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": 48, "model": "deepseek/deepseek-v4-pro", "point_rating_method": "sequential_elo", "public_id": "E-da5f3b1a4e370e1a", "rated_matches": 86, "raw_elo_rating": 1403.244405392198, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 35.48079904046824, "uncertainty": 9.855626741889738, "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": 32, "model": "google/gemini-3.1-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-d979b43c3aeea657", "rated_matches": 48, "raw_elo_rating": 1296.6134001853593, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 21.379233976999053, "uncertainty": 27.67857142857143, "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": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 40, "model": "google/gemma-4-31b-it", "point_rating_method": "sequential_elo", "public_id": "E-e8e17fbbdd12faa4", "rated_matches": 64, "raw_elo_rating": 1296.022394286137, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 22.18853644184757, "uncertainty": 18.26736729460423, "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": "2026-07-02T16:51:45Z", "losses": 29, "model": "gpt-4.1", "point_rating_method": "sequential_elo", "public_id": "E-1b9f1f7b70f02927", "rated_matches": 48, "raw_elo_rating": 1339.63995352344, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 26.39821775319491, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 19 }, { "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": 25, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-6d3546010ef68f50", "rated_matches": 84, "raw_elo_rating": 1752.4021108928348, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 76.1510189524612, "uncertainty": 10.482614454664043, "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": "2026-07-02T16:51:45Z", "losses": 41, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-427bdffeacc6c394", "rated_matches": 62, "raw_elo_rating": 1311.6911384019315, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 23.925126691680777, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 0, "generated_at": "2026-07-01T00:15:48Z", "losses": 28, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-8ed627956c0a0292", "rated_matches": 64, "raw_elo_rating": 1409.3463288872344, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 35.407605716313434, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 36 }, { "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": 46, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-cdd304da89074d54", "rated_matches": 76, "raw_elo_rating": 1367.284453130071, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 30.971204407632033, "uncertainty": 13.230288229818967, "unilateral_faults": 0, "wins": 30 }, { "admitted_plugin_count": 1, "attempted_matches": 76, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 38, "draws": 0, "generated_at": "2026-07-09T17:30:50Z", "losses": 53, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-3311575b341ee4a8", "rated_matches": 76, "raw_elo_rating": 1333.8464687908915, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 27.07071301599414, "uncertainty": 13.230288229818967, "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": "2026-07-01T00:15:48Z", "losses": 48, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-49b3c6006a3b9fcc", "rated_matches": 72, "raw_elo_rating": 1385.3452388274272, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 32.934230725765595, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 45, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-6c37eeef15b82287", "rated_matches": 62, "raw_elo_rating": 1268.0317786889311, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 18.83232698827737, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 25, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-6f42dbbf02274b56", "rated_matches": 64, "raw_elo_rating": 1589.5434120737496, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 56.42732881438667, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 39 }, { "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": 57, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-59156a669808a24f", "rated_matches": 62, "raw_elo_rating": 1106.586721726533, "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": 19.244078834871203, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 25, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-471e9297eea18ffd", "rated_matches": 68, "raw_elo_rating": 1600.385772117564, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 57.86232872007845, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 43 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 26, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-1f00b423eab1c19d", "rated_matches": 64, "raw_elo_rating": 1584.708544050022, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 55.863348614056285, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 38 }, { "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": 58, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-067ab716d64e3e9a", "rated_matches": 74, "raw_elo_rating": 1251.2405254174005, "reasoning": "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": 17.364420640765804, "uncertainty": 13.985026918962571, "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": 43, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-8cc657b7db4428cb", "rated_matches": 70, "raw_elo_rating": 1352.959444081681, "reasoning": "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": 29.080093373194575, "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": 41, "model": "minimax/minimax-m3", "point_rating_method": "sequential_elo", "public_id": "E-33797d7b77c7800c", "rated_matches": 76, "raw_elo_rating": 1461.8308552065046, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 41.99990230008747, "uncertainty": 13.230288229818967, "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": 51, "model": "mistralai/mistral-medium-3-5", "point_rating_method": "sequential_elo", "public_id": "E-4a7d37b86196302f", "rated_matches": 92, "raw_elo_rating": 1425.928615167466, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 38.2909369413615, "uncertainty": 8.09758473652126, "unilateral_faults": 0, "wins": 41 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 0, "generated_at": "2026-07-24T14:00:00Z", "losses": 11, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-4419230379dcd41e", "rated_matches": 42, "raw_elo_rating": 1666.7344489808431, "reasoning": "low", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "low", "repair_status": "first_pass", "score": 64.10344331483314, "uncertainty": 32.49928516630233, "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": "2026-07-21T14:20:15Z", "losses": 14, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-91be72471ad409b6", "rated_matches": 42, "raw_elo_rating": 1641.280898786558, "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": 61.13432435083197, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 86, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 43, "draws": 0, "generated_at": "2026-07-11T17:22:09Z", "losses": 46, "model": "nex-agi/nex-n2-pro", "point_rating_method": "sequential_elo", "public_id": "E-962a9da8812a74d4", "rated_matches": 86, "raw_elo_rating": 1467.516113452013, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 42.97799867637564, "uncertainty": 9.855626741889738, "unilateral_faults": 0, "wins": 40 }, { "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": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-4477e0de2e04aad4", "rated_matches": 50, "raw_elo_rating": 1540.701516438078, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 49.983757275316115, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 33 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 0, "generated_at": "2026-07-21T14:20:15Z", "losses": 12, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-b556333d605791f4", "rated_matches": 42, "raw_elo_rating": 1632.2043690442968, "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": 60.075560587845395, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 30 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 0, "generated_at": "2026-07-21T14:20:15Z", "losses": 22, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-172336d3fd38632a", "rated_matches": 42, "raw_elo_rating": 1403.3905933062547, "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": 33.3847722466155, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 20, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-1ca53619662c7f6f", "rated_matches": 70, "raw_elo_rating": 1710.148150878068, "reasoning": "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": 70.74562745316447, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 50 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 36, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-21623e96b2b104e9", "rated_matches": 66, "raw_elo_rating": 1395.5116389588086, "reasoning": "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": 33.88084294690067, "uncertainty": 17.33472217815261, "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": 36, "model": "qwen/qwen3.7-max", "point_rating_method": "sequential_elo", "public_id": "E-c577c41440c17864", "rated_matches": 68, "raw_elo_rating": 1535.2272824362703, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 50.261687320285, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 38, "model": "qwen/qwen3.7-plus", "point_rating_method": "sequential_elo", "public_id": "E-94daaf1196d89c6c", "rated_matches": 72, "raw_elo_rating": 1414.093697253425, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 36.28769585919104, "uncertainty": 14.770573598065289, "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": "2026-07-21T14:20:15Z", "losses": 24, "model": "stepfun/step-3.7-flash", "point_rating_method": "sequential_elo", "public_id": "E-386b7a319dfe25ad", "rated_matches": 42, "raw_elo_rating": 1409.8102664408416, "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": 34.13361761793311, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 90, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 45, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 58, "model": "tencent/hy3-preview", "point_rating_method": "sequential_elo", "public_id": "E-1bb81f8a4ae78954", "rated_matches": 90, "raw_elo_rating": 1354.5945266252224, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 29.9170413033881, "uncertainty": 8.664241836095918, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 40, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-0f05573125dedc2b", "rated_matches": 72, "raw_elo_rating": 1436.418304167105, "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": 38.89182821971972, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 47, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-f7a1d86c7e241f8d", "rated_matches": 72, "raw_elo_rating": 1465.2847904158946, "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": 42.25906112401628, "uncertainty": 14.770573598065289, "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": "2026-07-24T14:00:00Z", "losses": 18, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-f1d32edccc2b8ba2", "rated_matches": 42, "raw_elo_rating": 1585.4726493848916, "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": 54.62437464317196, "uncertainty": 32.49928516630233, "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": "2026-07-21T14:20:15Z", "losses": 3, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-fcfafa8fb4ccd299", "rated_matches": 42, "raw_elo_rating": 1828.4405960558256, "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": 82.96622607838233, "uncertainty": 32.49928516630233, "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": 28, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-09d406abc15f7c9a", "rated_matches": 68, "raw_elo_rating": 1600.1680494446266, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 57.836931692466315, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 40 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 0, "generated_at": "2026-07-01T00:15:48Z", "losses": 42, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-9490f08c56c27d13", "rated_matches": 68, "raw_elo_rating": 1324.696058522038, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 25.70353159478331, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 26 }, { "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": 33, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-be8fc9653466bbe1", "rated_matches": 68, "raw_elo_rating": 1428.7666841039816, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 37.843216065211045, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 35 }, { "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": 48, "model": "xiaomi/mimo-v2.5-pro", "point_rating_method": "sequential_elo", "public_id": "E-af55f57b03605914", "rated_matches": 82, "raw_elo_rating": 1349.7941697138317, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 29.12678637185235, "uncertainty": 11.132129994845172, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 0, "generated_at": "2026-07-11T14:00:45Z", "losses": 24, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-38e323f4ce233fa1", "rated_matches": 48, "raw_elo_rating": 1444.1826238143783, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 38.592965540395134, "uncertainty": 27.67857142857143, "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": "2026-07-01T00:15:48Z", "losses": 28, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-6370c4b68d38a97e", "rated_matches": 48, "raw_elo_rating": 1369.1095988048637, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 29.8358082660935, "uncertainty": 27.67857142857143, "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": "2026-07-02T06:10:40Z", "losses": 28, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-a6655b3c71893984", "rated_matches": 48, "raw_elo_rating": 1423.806776959368, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 36.21615315693525, "uncertainty": 27.67857142857143, "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": "2026-07-02T16:51:45Z", "losses": 22, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-d8655d29a4806df8", "rated_matches": 48, "raw_elo_rating": 1582.8898901773864, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 54.77296290263492, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 26 } ], "GB2-06": [ { "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": 35, "model": "claude-opus-4-5", "point_rating_method": "sequential_elo", "public_id": "E-40a259ca8a40b5b4", "rated_matches": 64, "raw_elo_rating": 1471.0980280128524, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 49.2174811242672, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 27 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 3, "generated_at": "2026-07-02T16:51:45Z", "losses": 31, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-db414178442322d3", "rated_matches": 68, "raw_elo_rating": 1511.7733406383302, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 54.83012501610077, "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": 13, "generated_at": "2026-07-25T10:50:00Z", "losses": 7, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-ca8985adf5006428", "rated_matches": 56, "raw_elo_rating": 1774.1459218022244, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 89.13691320039523, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 36 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 2, "generated_at": "2026-07-02T16:51:45Z", "losses": 22, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-500304c7462c6005", "rated_matches": 44, "raw_elo_rating": 1514.184208348665, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 53.62283719668116, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 0, "generated_at": "2026-07-01T00:15:48Z", "losses": 33, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-8daa317358045ed1", "rated_matches": 54, "raw_elo_rating": 1357.6100610068163, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 33.52439839431363, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 46, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-db0efb02339d9e80", "rated_matches": 60, "raw_elo_rating": 1201.9135524183437, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 13.147076218822994, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 6, "generated_at": "2026-07-02T16:51:45Z", "losses": 12, "model": "deepseek/deepseek-v4-pro", "point_rating_method": "sequential_elo", "public_id": "E-945bebaa34963e03", "rated_matches": 60, "raw_elo_rating": 1674.832336171311, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 76.1429991599217, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 42 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 1, "generated_at": "2026-07-02T16:51:45Z", "losses": 19, "model": "google/gemini-3.1-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-dc1c0f46738d1091", "rated_matches": 42, "raw_elo_rating": 1423.8254161871469, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 41.40382647576317, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 22 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "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": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 34, "model": "google/gemma-4-31b-it", "point_rating_method": "sequential_elo", "public_id": "E-da266f7bbd330107", "rated_matches": 58, "raw_elo_rating": 1390.6201022386813, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 38.16937604000977, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 8, "generated_at": "2026-07-02T16:51:45Z", "losses": 16, "model": "gpt-4.1", "point_rating_method": "sequential_elo", "public_id": "E-4dcd6d3653c67437", "rated_matches": 44, "raw_elo_rating": 1506.0471700351973, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 52.53892965023924, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 6, "generated_at": "2026-07-02T16:51:45Z", "losses": 15, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-00a57c19a4229948", "rated_matches": 58, "raw_elo_rating": 1638.165952256158, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 71.14412736694287, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 37 }, { "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": 1424.1759694354694, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 43.72752008171095, "uncertainty": 11.132129994845172, "unilateral_faults": 0, "wins": 35 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 37, "draws": 4, "generated_at": "2026-07-02T16:51:45Z", "losses": 36, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-144154b792c9e9a6", "rated_matches": 74, "raw_elo_rating": 1430.085237613073, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 44.210653995549066, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 1, "generated_at": "2026-07-02T06:10:40Z", "losses": 27, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-e726e4bfd20b0da9", "rated_matches": 58, "raw_elo_rating": 1362.71123706275, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 34.451729838595895, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 30 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 2, "generated_at": "2026-07-02T06:10:40Z", "losses": 21, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-3d7e23d6ea4c2792", "rated_matches": 62, "raw_elo_rating": 1615.1312453994922, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 68.29957872227698, "uncertainty": 19.244078834871203, "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": "2026-07-09T17:30:50Z", "losses": 38, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-a1fb59d78d39d217", "rated_matches": 66, "raw_elo_rating": 1396.2987934543962, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 39.3531139122755, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 28 }, { "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": 18, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-d5866895bf388f66", "rated_matches": 60, "raw_elo_rating": 1646.446024495557, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 72.36175391371486, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 42 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 46, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-ae522f9c5c491f57", "rated_matches": 56, "raw_elo_rating": 1174.1929957595082, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 9.219198794244829, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugin_count": 1, "attempted_matches": 84, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 42, "draws": 1, "generated_at": "2026-07-10T05:30:29Z", "losses": 49, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-992b9a5ebbb74c80", "rated_matches": 84, "raw_elo_rating": 1406.6038581939165, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 41.45601398414009, "uncertainty": 10.482614454664043, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 1, "generated_at": "2026-07-10T05:30:29Z", "losses": 42, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-22ffdca36d9bac9c", "rated_matches": 72, "raw_elo_rating": 1356.4473281980904, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 34.31788335875319, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 3, "generated_at": "2026-07-24T13:40:00Z", "losses": 36, "model": "inclusionai/ling-3.0-flash", "point_rating_method": "sequential_elo", "public_id": "E-6807fffacebac165", "rated_matches": 66, "raw_elo_rating": 1384.4414912461937, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 37.77364250648877, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 27 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 59, "model": "inclusionai/ling-3.0-flash", "point_rating_method": "sequential_elo", "public_id": "E-9bde0475193e2c4a", "rated_matches": 62, "raw_elo_rating": 1102.3972113195412, "reasoning": "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": 19.244078834871203, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 2, "generated_at": "2026-07-24T13:40:00Z", "losses": 40, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-3e8b2d11481a50d7", "rated_matches": 66, "raw_elo_rating": 1456.7679027076622, "reasoning": "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": 47.40800087744506, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 11, "generated_at": "2026-07-24T13:40:00Z", "losses": 28, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-e3023ff7ecf82fc4", "rated_matches": 68, "raw_elo_rating": 1533.2515897825635, "reasoning": "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": 57.69117045240684, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 5, "generated_at": "2026-07-02T16:51:45Z", "losses": 34, "model": "mistralai/mistral-medium-3-5", "point_rating_method": "sequential_elo", "public_id": "E-cf0bc4a1e7a8d72a", "rated_matches": 64, "raw_elo_rating": 1330.3542233252822, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 30.469471573505537, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 0, "generated_at": "2026-07-21T14:20:15Z", "losses": 5, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-2f8c760ee4329d00", "rated_matches": 36, "raw_elo_rating": 1759.3228885332007, "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": 85.46023220629932, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 31 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 25, "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": 50, "raw_elo_rating": 1504.3686423432716, "reasoning": "low", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "low", "repair_status": "first_pass", "score": 52.7971838064758, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 2, "generated_at": "2026-07-11T17:22:09Z", "losses": 43, "model": "nex-agi/nex-n2-pro", "point_rating_method": "sequential_elo", "public_id": "E-973417dedd770061", "rated_matches": 66, "raw_elo_rating": 1329.3201234614855, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 30.43111022257915, "uncertainty": 17.33472217815261, "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": "2026-07-02T16:51:45Z", "losses": 26, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-6e76a1c11ba24bc6", "rated_matches": 44, "raw_elo_rating": 1368.7430753287372, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 34.249112314196054, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 1, "generated_at": "2026-07-21T14:20:15Z", "losses": 4, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-e4a4a86669325de4", "rated_matches": 36, "raw_elo_rating": 1768.0118763760397, "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": 86.61766309589059, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 31 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "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": 58, "raw_elo_rating": 1478.406710872713, "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": 49.8631353550523, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 2, "generated_at": "2026-07-24T13:40:00Z", "losses": 33, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-a29031412bc33c39", "rated_matches": 64, "raw_elo_rating": 1345.579754559503, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 32.49761345604342, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 29 }, { "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": 36, "model": "qwen/qwen3.7-max", "point_rating_method": "sequential_elo", "public_id": "E-0c7e9f6c7d4cb892", "rated_matches": 56, "raw_elo_rating": 1341.8150715027673, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 31.547572564793132, "uncertainty": 22.47661785325219, "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": 47, "model": "qwen/qwen3.7-plus", "point_rating_method": "sequential_elo", "public_id": "E-2fb82a23fdec2792", "rated_matches": 64, "raw_elo_rating": 1346.5858526769046, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 32.63163240739917, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-21T14:20:15Z", "losses": 25, "model": "stepfun/step-3.7-flash", "point_rating_method": "sequential_elo", "public_id": "E-8a88dceef8a0239c", "rated_matches": 38, "raw_elo_rating": 1359.2957907129323, "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": 32.401527305050784, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 39, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-02be9616e86c7055", "rated_matches": 66, "raw_elo_rating": 1421.3056015259317, "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": 42.684186833033415, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 27 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "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": 38, "raw_elo_rating": 1570.6476467281004, "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": 60.55499824424813, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "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": 38, "raw_elo_rating": 1571.930757481107, "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": 60.725917118478186, "uncertainty": 36.31407690254356, "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": "2026-07-02T16:51:45Z", "losses": 32, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-d572bc902e0e416b", "rated_matches": 54, "raw_elo_rating": 1371.8471393219586, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 35.420871783105014, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 22 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 45, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-d79ad8bc05d1b933", "rated_matches": 68, "raw_elo_rating": 1398.996868656436, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 39.807549930033865, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 0, "generated_at": "2026-07-01T00:15:48Z", "losses": 22, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-ff7683792b6b3363", "rated_matches": 60, "raw_elo_rating": 1605.0497655291583, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 66.84749728131351, "uncertainty": 20.268439966447993, "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": "2026-07-02T16:51:45Z", "losses": 38, "model": "xiaomi/mimo-v2.5-pro", "point_rating_method": "sequential_elo", "public_id": "E-6b662c734cdcff91", "rated_matches": 72, "raw_elo_rating": 1453.7533405191086, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 47.279690469131054, "uncertainty": 14.770573598065289, "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": "2026-07-01T00:15:48Z", "losses": 35, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-18454080fac44f8c", "rated_matches": 42, "raw_elo_rating": 1190.1011190442018, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 10.270197789171506, "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": 4, "generated_at": "2026-07-11T14:00:45Z", "losses": 19, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-657c61c9039ce566", "rated_matches": 42, "raw_elo_rating": 1469.4176086881623, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 47.47700932275704, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 6, "generated_at": "2026-07-02T06:10:40Z", "losses": 19, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-6954e92d5890c32a", "rated_matches": 42, "raw_elo_rating": 1504.6005016612066, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 52.16360433804945, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 3, "generated_at": "2026-07-02T16:51:45Z", "losses": 18, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-ec1479c855f477b4", "rated_matches": 42, "raw_elo_rating": 1591.4136790455657, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 63.72769614547851, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 21 } ], "GB2-07": [ { "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": 33, "model": "claude-opus-4-5", "point_rating_method": "sequential_elo", "public_id": "E-ca22621c58b6f244", "rated_matches": 64, "raw_elo_rating": 1489.8456094590335, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 46.82415975623741, "uncertainty": 18.26736729460423, "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": 25, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-76804598cce96e62", "rated_matches": 66, "raw_elo_rating": 1614.8782657464328, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 62.93013963759991, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 41 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 0, "generated_at": "2026-07-25T10:50:00Z", "losses": 19, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-914b104a64ab3110", "rated_matches": 54, "raw_elo_rating": 1742.0788730945349, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 78.56920080122724, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 35 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 20, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-cd6f193a087d8c8d", "rated_matches": 44, "raw_elo_rating": 1564.596224581565, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 55.113612498782416, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 41, "model": "cohere/north-mini-code", "point_rating_method": "sequential_elo", "public_id": "E-3b908f26a42804a4", "rated_matches": 70, "raw_elo_rating": 1445.8745630141473, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 41.46802802496643, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 0, "generated_at": "2026-07-11T17:22:09Z", "losses": 56, "model": "cohere/north-mini-code", "point_rating_method": "sequential_elo", "public_id": "E-c7f5dc6d5d3c2a8d", "rated_matches": 70, "raw_elo_rating": 1212.5244825073055, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 11.5875352293604, "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": 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": 1389.6179735971475, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 34.1769003514353, "uncertainty": 16.4429265428846, "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": "2026-07-02T16:51:45Z", "losses": 40, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-c394c0713cfcfaa4", "rated_matches": 72, "raw_elo_rating": 1434.5302003634831, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 40.09922979490467, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugin_count": 1, "attempted_matches": 76, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 38, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 41, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-c8fd55a5d257c569", "rated_matches": 76, "raw_elo_rating": 1408.808537777866, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 36.96335616112706, "uncertainty": 13.230288229818967, "unilateral_faults": 0, "wins": 35 }, { "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": 31, "model": "deepseek/deepseek-v4-pro", "point_rating_method": "sequential_elo", "public_id": "E-f76d96b0f3163d4b", "rated_matches": 66, "raw_elo_rating": 1443.3127110418286, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 40.96115933902756, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 35 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 40, "model": "google/gemini-3.1-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-3d6a15fe821fe6ad", "rated_matches": 44, "raw_elo_rating": 1134.1894705301404, "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": 30.785599249992988, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "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": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 37, "model": "google/gemma-4-31b-it", "point_rating_method": "sequential_elo", "public_id": "E-3f820f7e8ff15839", "rated_matches": 60, "raw_elo_rating": 1350.8159516092887, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 28.816413152201964, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 23 }, { "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": 20, "model": "gpt-4.1", "point_rating_method": "sequential_elo", "public_id": "E-fcfa606d3cbb0ba0", "rated_matches": 46, "raw_elo_rating": 1507.3262272831655, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 47.944407671620375, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 76, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 38, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 43, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-c8176c382cf75e88", "rated_matches": 76, "raw_elo_rating": 1369.3333503741408, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 31.908555878820593, "uncertainty": 13.230288229818967, "unilateral_faults": 0, "wins": 33 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "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-022243613d51f0fb", "rated_matches": 66, "raw_elo_rating": 1362.071311220552, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 30.55819287425519, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 48, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-6a87ebc54bdde781", "rated_matches": 64, "raw_elo_rating": 1250.3650623117942, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 16.15866031360461, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 16 }, { "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": 46, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-c2ab31787514c10c", "rated_matches": 62, "raw_elo_rating": 1263.5146220810454, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 17.742407906208506, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 16 }, { "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": 47, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-4e14ae758717169e", "rated_matches": 80, "raw_elo_rating": 1450.3222942234418, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 42.42514502852104, "uncertainty": 11.805555555555554, "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": 37, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-ce2925d9379d2a5d", "rated_matches": 66, "raw_elo_rating": 1332.8504775262977, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 26.816463243023417, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 29 }, { "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": 28, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-4edfe4117ad3e936", "rated_matches": 62, "raw_elo_rating": 1459.9750388104458, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 42.899176885906776, "uncertainty": 19.244078834871203, "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": "2026-07-10T05:30:29Z", "losses": 49, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-ea529147555b5f2e", "rated_matches": 64, "raw_elo_rating": 1231.8599986467784, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 13.7890857228278, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 31, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-bef852aad169a609", "rated_matches": 64, "raw_elo_rating": 1592.027897449992, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 59.90860829604776, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 33 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 36, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-8ebe8776c7d44d46", "rated_matches": 64, "raw_elo_rating": 1494.7496459810498, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 47.45212194783904, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 34, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-c1f595f47c71e648", "rated_matches": 68, "raw_elo_rating": 1353.2540341715787, "reasoning": "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": 29.520495572548967, "uncertainty": 16.4429265428846, "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": "2026-07-24T13:40:00Z", "losses": 37, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-e2db910734ca5315", "rated_matches": 66, "raw_elo_rating": 1492.4680851538344, "reasoning": "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": 47.25550815103084, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 31, "model": "minimax/minimax-m3", "point_rating_method": "sequential_elo", "public_id": "E-24e15c4d7490cdf3", "rated_matches": 62, "raw_elo_rating": 1436.3423615846004, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 39.873011049349245, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 31 }, { "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": 29, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-4d8815930b656774", "rated_matches": 50, "raw_elo_rating": 1429.3321694188307, "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": 38.256233977072846, "uncertainty": 26.26400420140049, "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": "2026-07-21T14:20:15Z", "losses": 15, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-c00660d2a8eb25c9", "rated_matches": 40, "raw_elo_rating": 1577.9650499245272, "reasoning": "low", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "low", "repair_status": "first_pass", "score": 56.46169796332241, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 0, "generated_at": "2026-07-11T17:22:09Z", "losses": 22, "model": "nex-agi/nex-n2-pro", "point_rating_method": "sequential_elo", "public_id": "E-1006c453b0c3a745", "rated_matches": 68, "raw_elo_rating": 1667.1651313142668, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 69.71683172233598, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 46 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 0, "generated_at": "2026-07-03T18:15:00Z", "losses": 34, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-0e1c7f89e1c19b69", "rated_matches": 44, "raw_elo_rating": 1299.8016849909914, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 21.20665469801167, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 0, "generated_at": "2026-07-21T14:20:15Z", "losses": 22, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-3fae70801895971d", "rated_matches": 46, "raw_elo_rating": 1400.5331075430531, "reasoning": "low", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "low", "repair_status": "first_pass", "score": 34.26954183020419, "uncertainty": 29.182495748947275, "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": "2026-07-21T14:20:15Z", "losses": 24, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-759d747bb732d949", "rated_matches": 40, "raw_elo_rating": 1389.7423245669345, "reasoning": "low", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "low", "repair_status": "first_pass", "score": 32.35976589284266, "uncertainty": 34.33688094430304, "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": "2026-07-24T13:40:00Z", "losses": 39, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-069a963abdd14cdf", "rated_matches": 66, "raw_elo_rating": 1495.9916626938689, "reasoning": "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": 47.706702481330936, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 27 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 28, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-d8e68d23876f6d21", "rated_matches": 68, "raw_elo_rating": 1585.1752235655044, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 59.21801876937681, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 40 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 22, "model": "qwen/qwen3.7-max", "point_rating_method": "sequential_elo", "public_id": "E-3142a09c7f192060", "rated_matches": 68, "raw_elo_rating": 1755.2492100095503, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 80.99600365638999, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 46 }, { "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": 39, "model": "qwen/qwen3.7-plus", "point_rating_method": "sequential_elo", "public_id": "E-737a66790985a5e6", "rated_matches": 64, "raw_elo_rating": 1257.5505253206957, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 17.078759313374523, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 0, "generated_at": "2026-07-21T14:20:15Z", "losses": 27, "model": "stepfun/step-3.7-flash", "point_rating_method": "sequential_elo", "public_id": "E-1140a7c92290e8f4", "rated_matches": 50, "raw_elo_rating": 1408.2743046740543, "reasoning": "low", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "low", "repair_status": "repaired", "score": 35.55977304408127, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 44, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-062d41f517db2ccb", "rated_matches": 68, "raw_elo_rating": 1354.4160981986215, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 29.66929794584434, "uncertainty": 16.4429265428846, "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": "2026-07-21T14:20:15Z", "losses": 7, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-7e2507a947914c49", "rated_matches": 40, "raw_elo_rating": 1695.4365075568585, "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": 71.5039256576441, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 33 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 0, "generated_at": "2026-07-24T14:00:00Z", "losses": 5, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-ca54791ad3682b4f", "rated_matches": 42, "raw_elo_rating": 1756.547345722592, "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": 79.51741581546919, "uncertainty": 32.49928516630233, "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": "2026-07-02T16:51:45Z", "losses": 35, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-0984b025e9005f5b", "rated_matches": 60, "raw_elo_rating": 1326.9005822633198, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 25.754048571506956, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugin_count": 1, "attempted_matches": 76, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 38, "draws": 0, "generated_at": "2026-07-01T00:15:48Z", "losses": 44, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-47d67dcf0077af42", "rated_matches": 76, "raw_elo_rating": 1451.7215822177934, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 42.458374257712485, "uncertainty": 13.230288229818967, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 22, "model": "xiaomi/mimo-v2.5-pro", "point_rating_method": "sequential_elo", "public_id": "E-83580d03385c6759", "rated_matches": 60, "raw_elo_rating": 1653.249574240341, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 67.54305795364324, "uncertainty": 20.268439966447993, "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": "2026-07-11T14:00:45Z", "losses": 21, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-62e8714f035ebc68", "rated_matches": 48, "raw_elo_rating": 1533.9355228025909, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 51.5057917564914, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 27 }, { "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": 24, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-e31f275ab7ef3741", "rated_matches": 46, "raw_elo_rating": 1537.094717810298, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 51.75626479547493, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 22 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 0, "generated_at": "2026-07-01T00:15:48Z", "losses": 18, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-f7579fbfcb1dcbb9", "rated_matches": 46, "raw_elo_rating": 1592.179295886225, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 58.80984855585626, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 28 } ], "GB2-08": [ { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 6, "coverage_status": "rated", "distinct_rated_opponents": 37, "draws": 6, "generated_at": "2026-07-02T16:51:45Z", "losses": 19, "model": "claude-opus-4-5", "point_rating_method": "sequential_elo", "public_id": "E-01b57d5e6655f927", "rated_matches": 74, "raw_elo_rating": 1645.4486548697253, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 59.15070675443215, "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": "2026-07-02T16:51:45Z", "losses": 21, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-c9d7578e8375d994", "rated_matches": 74, "raw_elo_rating": 1657.365116897373, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 60.99415499988833, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 53 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 0, "generated_at": "2026-07-25T10:50:00Z", "losses": 25, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-5a7942274854aaa6", "rated_matches": 58, "raw_elo_rating": 1571.8431949043122, "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": 46.853328871691126, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 33 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 44, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 44, "generated_at": "2026-07-02T16:51:45Z", "losses": 2, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-cf0ed4bbe4aaadd7", "rated_matches": 46, "raw_elo_rating": 1444.104133950512, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 26.12237999875593, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 51, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 51, "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": 64, "raw_elo_rating": 1449.4863124214994, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 28.305825631962907, "uncertainty": 18.26736729460423, "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": 1425.4281094231785, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 24.915538389642823, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 58, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 58, "generated_at": "2026-07-02T06:10:40Z", "losses": 8, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-95b070e1c29e44f0", "rated_matches": 66, "raw_elo_rating": 1415.6944083866397, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 23.19372107781717, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 58, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 58, "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": 72, "raw_elo_rating": 1444.3940064125673, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 27.95081455535383, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 59, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 59, "generated_at": "2026-07-02T16:51:45Z", "losses": 8, "model": "deepseek/deepseek-v4-pro", "point_rating_method": "sequential_elo", "public_id": "E-c296a7abab6975d7", "rated_matches": 70, "raw_elo_rating": 1445.9523521591466, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 28.090589774286613, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-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": 56, "capped_draws": 45, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 45, "generated_at": "2026-07-02T16:51:45Z", "losses": 10, "model": "google/gemma-4-31b-it", "point_rating_method": "sequential_elo", "public_id": "E-8546650b7690a81a", "rated_matches": 56, "raw_elo_rating": 1436.727549023724, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 25.811146558890066, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 29, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 29, "generated_at": "2026-07-02T16:51:45Z", "losses": 14, "model": "gpt-4.1", "point_rating_method": "sequential_elo", "public_id": "E-eabc996d553eebe0", "rated_matches": 50, "raw_elo_rating": 1417.0774072462827, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 22.30259680139711, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 51, "coverage_status": "rated", "distinct_rated_opponents": 37, "draws": 51, "generated_at": "2026-07-02T16:51:45Z", "losses": 13, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-95f891d54f35bb4a", "rated_matches": 74, "raw_elo_rating": 1450.5903871925957, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 29.006597636421393, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 34, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 34, "generated_at": "2026-07-02T06:10:40Z", "losses": 25, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-00b5df785d927901", "rated_matches": 70, "raw_elo_rating": 1436.789657201984, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 26.67314272471412, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 80, "capped_draws": 57, "coverage_status": "rated", "distinct_rated_opponents": 40, "draws": 57, "generated_at": "2026-07-01T00:15:48Z", "losses": 20, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-7ff0b78720f446ad", "rated_matches": 80, "raw_elo_rating": 1420.764326523804, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 24.662304425908992, "uncertainty": 11.805555555555554, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 57, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 57, "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": 64, "raw_elo_rating": 1432.9306505001732, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 25.744704231128832, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 65, "coverage_status": "rated", "distinct_rated_opponents": 37, "draws": 65, "generated_at": "2026-07-09T17:30:50Z", "losses": 9, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-024aff0a983df40d", "rated_matches": 74, "raw_elo_rating": 1410.5597559530413, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 22.813954488493017, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 76, "capped_draws": 60, "coverage_status": "rated", "distinct_rated_opponents": 38, "draws": 60, "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": 76, "raw_elo_rating": 1417.5690820683249, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 23.99168553536854, "uncertainty": 13.230288229818967, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 56, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 56, "generated_at": "2026-07-01T00:15:48Z", "losses": 11, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-c320ceaf4558afab", "rated_matches": 72, "raw_elo_rating": 1461.1213257667816, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 30.538490951516476, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 3, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 3, "generated_at": "2026-07-02T16:51:45Z", "losses": 23, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-fd5a36e5fd795426", "rated_matches": 70, "raw_elo_rating": 1604.1522009988105, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 52.563728957568706, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 44 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 46, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 46, "generated_at": "2026-07-02T16:51:45Z", "losses": 10, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-c42fbee03a029c83", "rated_matches": 60, "raw_elo_rating": 1442.9671606777888, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 27.049679476012503, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 53, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 53, "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": 62, "raw_elo_rating": 1439.1437448693234, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 26.58497915083693, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 5, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 5, "generated_at": "2026-07-10T05:30:29Z", "losses": 25, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-994624d0bc2e266d", "rated_matches": 64, "raw_elo_rating": 1508.549910317883, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 37.44282331296946, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 55, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 55, "generated_at": "2026-07-10T05:30:29Z", "losses": 9, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-44cace55a6126cdf", "rated_matches": 68, "raw_elo_rating": 1443.099914328351, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 27.543654388822937, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 56, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 56, "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": 68, "raw_elo_rating": 1417.7904354977372, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 23.628338396923972, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 57, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 57, "generated_at": "2026-07-24T13:40:00Z", "losses": 11, "model": "inclusionai/ling-3.0-flash", "point_rating_method": "sequential_elo", "public_id": "E-28bcc8394e411616", "rated_matches": 72, "raw_elo_rating": 1424.1762047851312, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 24.823168879094652, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 57, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 57, "generated_at": "2026-07-24T13:40:00Z", "losses": 7, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-87d69837bf65e78b", "rated_matches": 68, "raw_elo_rating": 1421.2556708046552, "reasoning": "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": 24.164402031567377, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 58, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 58, "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": 72, "raw_elo_rating": 1431.4718888272553, "reasoning": "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": 25.951793794413707, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 7, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 7, "generated_at": "2026-07-02T16:51:45Z", "losses": 33, "model": "minimax/minimax-m3", "point_rating_method": "sequential_elo", "public_id": "E-e67e41d4491d7ad3", "rated_matches": 70, "raw_elo_rating": 1513.6287669745502, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 38.55996968426065, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 30 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 53, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 53, "generated_at": "2026-07-02T16:51:45Z", "losses": 5, "model": "mistralai/mistral-medium-3-5", "point_rating_method": "sequential_elo", "public_id": "E-ba85be2fa53925f5", "rated_matches": 58, "raw_elo_rating": 1437.5092940470956, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 26.072194902063597, "uncertainty": 21.344455490411935, "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": "2026-07-24T14:00:00Z", "losses": 1, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-3e1be56b9d966ded", "rated_matches": 40, "raw_elo_rating": 1808.9160748580327, "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": 81.92002001715609, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 39 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 14, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 14, "generated_at": "2026-07-21T14:20:15Z", "losses": 15, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-b88e77144afeb8fd", "rated_matches": 40, "raw_elo_rating": 1498.091938504907, "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": 33.836267685615866, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 50, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 50, "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": 58, "raw_elo_rating": 1441.5298755363042, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 26.69416926616589, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 40, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 40, "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": 46, "raw_elo_rating": 1452.3787650864267, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 27.40244569391851, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 19, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 19, "generated_at": "2026-07-21T14:20:15Z", "losses": 13, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-cbb72b5e25b55cee", "rated_matches": 40, "raw_elo_rating": 1494.8376381329836, "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": 33.33283518216888, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 33, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 33, "generated_at": "2026-07-21T14:20:15Z", "losses": 5, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-f6e9da46c61ad315", "rated_matches": 40, "raw_elo_rating": 1434.1465689714887, "reasoning": "low", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "low", "repair_status": "first_pass", "score": 23.944071579260378, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 62, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 62, "generated_at": "2026-07-24T13:40:00Z", "losses": 9, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-4030acdbccf3ca03", "rated_matches": 72, "raw_elo_rating": 1417.7751810997115, "reasoning": "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": 23.8329457864827, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 57, "coverage_status": "rated", "distinct_rated_opponents": 37, "draws": 57, "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": 74, "raw_elo_rating": 1413.9267753590686, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 23.33482435759152, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 76, "capped_draws": 49, "coverage_status": "rated", "distinct_rated_opponents": 38, "draws": 49, "generated_at": "2026-07-02T16:51:45Z", "losses": 22, "model": "qwen/qwen3.7-max", "point_rating_method": "sequential_elo", "public_id": "E-a667eb7d15f7f43e", "rated_matches": 76, "raw_elo_rating": 1456.1357275132184, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 29.95785357363107, "uncertainty": 13.230288229818967, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 32, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 32, "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": 40, "raw_elo_rating": 1405.907367827263, "reasoning": "low", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "low", "repair_status": "first_pass", "score": 19.57553453515884, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 80, "capped_draws": 65, "coverage_status": "rated", "distinct_rated_opponents": 40, "draws": 65, "generated_at": "2026-07-02T16:51:45Z", "losses": 14, "model": "tencent/hy3-preview", "point_rating_method": "sequential_elo", "public_id": "E-56487337fad4192f", "rated_matches": 80, "raw_elo_rating": 1448.1797497732612, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 28.903404995054014, "uncertainty": 11.805555555555554, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 1, "generated_at": "2026-07-24T13:40:00Z", "losses": 38, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-68669040dc891a7d", "rated_matches": 68, "raw_elo_rating": 1639.5524233506335, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 57.934388839397826, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 20, "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": 40, "raw_elo_rating": 1712.6788343858598, "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": 67.03234851831978, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 0, "generated_at": "2026-07-24T14:00:00Z", "losses": 7, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-b914d026c7631fcb", "rated_matches": 40, "raw_elo_rating": 1748.8021724726273, "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": 72.62054273750772, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 33 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 47, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 47, "generated_at": "2026-07-02T16:51:45Z", "losses": 17, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-cabbf604f15eb575", "rated_matches": 66, "raw_elo_rating": 1369.1623511787177, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 15.9953228436439, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 56, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 56, "generated_at": "2026-07-01T00:15:48Z", "losses": 6, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-d51fce0298267f96", "rated_matches": 62, "raw_elo_rating": 1440.781930662483, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 26.83840258466534, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 39, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 39, "generated_at": "2026-07-11T14:00:45Z", "losses": 5, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-6a361d88d8c1fb48", "rated_matches": 46, "raw_elo_rating": 1466.4937248820224, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 29.58599629891401, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 2 }, { "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": 17, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-97efd9455394f6d7", "rated_matches": 48, "raw_elo_rating": 1608.38355668495, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 51.72213756239715, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 31 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 3, "coverage_status": "rated", "distinct_rated_opponents": 23, "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": 46, "raw_elo_rating": 1540.7683006503114, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 41.076095966448115, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 26 } ] }, "full_freedom/intensive": { "GB2-01": [ { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "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": 58, "raw_elo_rating": 1614.289805193975, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 62.48880272697796, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 6, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 6, "generated_at": "2026-07-03T17:20:00Z", "losses": 19, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-3308d2952452916e", "rated_matches": 58, "raw_elo_rating": 1593.5380641852346, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 59.81280359013286, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 33 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 0, "generated_at": "2026-07-25T15:48:00Z", "losses": 9, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-700f3dddd611df07", "rated_matches": 40, "raw_elo_rating": 1807.1973005834263, "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": 86.02447212008084, "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": 1471.125886827351, "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": 42.68705706893992, "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": 1580.6415648788145, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 59.06172320072071, "uncertainty": 12.5043950463012, "unilateral_faults": 0, "wins": 44 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 18, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 18, "generated_at": "2026-07-02T16:51:45Z", "losses": 28, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-b9882650a0cde9ac", "rated_matches": 62, "raw_elo_rating": 1396.162780126903, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 34.57734962700469, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 12, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 12, "generated_at": "2026-07-02T06:10:40Z", "losses": 25, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-cb8739e00cafec5b", "rated_matches": 60, "raw_elo_rating": 1501.6717916093205, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 48.07737701917374, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 12, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 12, "generated_at": "2026-07-02T16:51:45Z", "losses": 22, "model": "deepseek/deepseek-v4-pro", "point_rating_method": "sequential_elo", "public_id": "E-e192048d4eaa3c43", "rated_matches": 62, "raw_elo_rating": 1482.114031725191, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 45.66102087130642, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-3ade0bdbb45d890e", "rated_matches": 0, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-401e0639de33ca9e", "rated_matches": 0, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-e9260a0da3a64563", "rated_matches": 0, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 7, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 7, "generated_at": "2026-07-02T16:51:45Z", "losses": 17, "model": "gpt-5", "point_rating_method": "sequential_elo", "public_id": "E-3e63b136f656e976", "rated_matches": 38, "raw_elo_rating": 1501.5044492434015, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 46.400491379313614, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 2, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-5d8a6b14c27539ab", "rated_matches": 60, "raw_elo_rating": 1904.3194643073384, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 100.0, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 58 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 6, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 6, "generated_at": "2026-07-02T06:10:40Z", "losses": 19, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-ca99b677101014a8", "rated_matches": 60, "raw_elo_rating": 1533.3730974136329, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 52.16535532101704, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 35 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 31, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 31, "generated_at": "2026-07-09T17:30:50Z", "losses": 18, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-db1fc33e2a2467d5", "rated_matches": 58, "raw_elo_rating": 1422.4893012366283, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 37.75555346272907, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 7, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 7, "generated_at": "2026-07-02T06:10:40Z", "losses": 46, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-fbb3f2dccb7c7fba", "rated_matches": 60, "raw_elo_rating": 1247.6398373848845, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 15.319195912858827, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 19, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 19, "generated_at": "2026-07-02T16:51:45Z", "losses": 12, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-8c61292c31db2722", "rated_matches": 60, "raw_elo_rating": 1726.2827891456054, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 77.04163766987543, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 18, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-38187ed58fb76057", "rated_matches": 54, "raw_elo_rating": 1644.604801686931, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 66.15810496914253, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 36 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 16, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-9e683b3cd6c7f7c3", "rated_matches": 58, "raw_elo_rating": 1716.2957199694602, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 75.64277085800467, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 42 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 12, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 12, "generated_at": "2026-07-10T05:30:29Z", "losses": 23, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-36d36f4895d90b11", "rated_matches": 54, "raw_elo_rating": 1474.4008078994289, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 44.20979035442635, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 4, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 4, "generated_at": "2026-07-02T16:51:45Z", "losses": 24, "model": "mistralai/mistral-medium-3-5", "point_rating_method": "sequential_elo", "public_id": "E-99c7b0d758665b66", "rated_matches": 32, "raw_elo_rating": 1298.752594032639, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 19.535500553304832, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 1, "generated_at": "2026-07-17T22:36:00Z", "losses": 22, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-c89e5a24623ed70c", "rated_matches": 46, "raw_elo_rating": 1534.6956612737772, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "score": 51.41630854421455, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 16, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 16, "generated_at": "2026-07-17T22:36:00Z", "losses": 13, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-d2f6679f6ac952b3", "rated_matches": 42, "raw_elo_rating": 1489.127041295967, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "score": 45.19793061785928, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 5, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 5, "generated_at": "2026-07-24T14:00:00Z", "losses": 16, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-dbb89dcf5242a5a0", "rated_matches": 40, "raw_elo_rating": 1522.5986867020624, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "score": 49.3246287299255, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 7, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 7, "generated_at": "2026-07-11T17:22:09Z", "losses": 20, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-ce064a9927030b28", "rated_matches": 32, "raw_elo_rating": 1351.6159358621478, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 26.352386762848873, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 1, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 1, "generated_at": "2026-07-02T16:51:45Z", "losses": 28, "model": "stepfun/step-3.7-flash", "point_rating_method": "sequential_elo", "public_id": "E-4b0ce2bc67b08d8a", "rated_matches": 32, "raw_elo_rating": 1255.3105806304277, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 13.933522853305266, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 4, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 4, "generated_at": "2026-07-02T16:51:45Z", "losses": 19, "model": "tencent/hy3-preview", "point_rating_method": "sequential_elo", "public_id": "E-29e8870e43d717e5", "rated_matches": 38, "raw_elo_rating": 1536.8211359232482, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 50.9546838700397, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 5, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 5, "generated_at": "2026-07-17T22:36:00Z", "losses": 8, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-098480b7039ef18d", "rated_matches": 32, "raw_elo_rating": 1626.391326237206, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 61.78549606968857, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 8, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 8, "generated_at": "2026-07-24T14:00:00Z", "losses": 6, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-1c8e452ede41ea2e", "rated_matches": 32, "raw_elo_rating": 1671.8010064527873, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 67.64121029675636, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 3, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 3, "generated_at": "2026-07-17T22:36:00Z", "losses": 14, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-f9b8636a677996e4", "rated_matches": 34, "raw_elo_rating": 1582.217568421379, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 56.3494779833692, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 33, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 33, "generated_at": "2026-07-02T06:10:40Z", "losses": 11, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-8478c64d84536b61", "rated_matches": 44, "raw_elo_rating": 1306.1499854705874, "reasoning": "highest", "reasoning_bracket": "highest", "reasoning_setting": "highest", "repair_status": "repaired", "score": 21.77927935287923, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 34, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 34, "generated_at": "2026-07-11T14:00:45Z", "losses": 11, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-5ab5088af70c19d6", "rated_matches": 58, "raw_elo_rating": 1468.7686993741677, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 43.72342041989681, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 34, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 34, "generated_at": "2026-07-03T18:27:00Z", "losses": 17, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-88bed07a2e526eed", "rated_matches": 62, "raw_elo_rating": 1527.6648692331044, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 51.53493775386614, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 11 } ], "GB2-02": [ { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "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": 60, "raw_elo_rating": 1665.515391796302, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 73.19703425601392, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 30 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 20, "generated_at": "2026-07-03T17:20:00Z", "losses": 3, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-a81bd03e764818f6", "rated_matches": 58, "raw_elo_rating": 1737.1613209336665, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 90.09571894996164, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 35 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 12, "generated_at": "2026-07-25T15:48:01Z", "losses": 7, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-6b45cf5aebf0c66e", "rated_matches": 40, "raw_elo_rating": 1655.6035207934715, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 68.14388017555835, "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": 1742.7134166182843, "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": 88.93981485101536, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 39, "generated_at": "2026-07-03T16:50:00Z", "losses": 10, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-e35d82f3fd09a1f4", "rated_matches": 56, "raw_elo_rating": 1527.1746719119114, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 39.748923171140326, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 52, "generated_at": "2026-07-02T16:51:45Z", "losses": 2, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-12dcb25370550495", "rated_matches": 58, "raw_elo_rating": 1476.913822136368, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 27.966268177526015, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 52, "generated_at": "2026-07-02T06:10:40Z", "losses": 6, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-f2e6dd87c5656ee3", "rated_matches": 60, "raw_elo_rating": 1490.5117813480674, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 31.418042140470977, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-939a2dc80becc700", "rated_matches": 0, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-a3da6c33bd873fb7", "rated_matches": 0, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 25, "generated_at": "2026-07-02T16:51:45Z", "losses": 9, "model": "gpt-5", "point_rating_method": "sequential_elo", "public_id": "E-5bccb9b671ce5eae", "rated_matches": 38, "raw_elo_rating": 1485.9869743562572, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 27.27333732546178, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 37, "generated_at": "2026-07-02T16:51:45Z", "losses": 7, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-4aa582caf9d9f6da", "rated_matches": 64, "raw_elo_rating": 1597.2143177522778, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 57.273546807227696, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 49, "generated_at": "2026-07-02T16:51:45Z", "losses": 5, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-59f362f57892ab54", "rated_matches": 56, "raw_elo_rating": 1486.3448735458198, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 30.001536704958095, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 56, "generated_at": "2026-07-02T06:10:40Z", "losses": 3, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-7ef67fa468b6c12c", "rated_matches": 60, "raw_elo_rating": 1475.6820234756003, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 27.877701826106545, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 58, "generated_at": "2026-07-09T17:30:50Z", "losses": 4, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-1ce420518fc32de1", "rated_matches": 62, "raw_elo_rating": 1469.783695669112, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 26.665219581500377, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 37, "draws": 58, "generated_at": "2026-07-02T16:51:45Z", "losses": 10, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-b084ba147f956b49", "rated_matches": 74, "raw_elo_rating": 1493.389893096581, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 33.30518228882905, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 64, "generated_at": "2026-07-10T05:30:29Z", "losses": 6, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-a30e455ba172d80e", "rated_matches": 70, "raw_elo_rating": 1473.0639451591423, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 28.146372762679754, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 11, "generated_at": "2026-07-10T05:30:29Z", "losses": 4, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-33dc9365cfacf9c0", "rated_matches": 58, "raw_elo_rating": 1778.6483184624055, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 100.0, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 43 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 37, "generated_at": "2026-07-10T05:30:29Z", "losses": 10, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-1b12482867c807c9", "rated_matches": 60, "raw_elo_rating": 1549.3008269640052, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 45.45287871885732, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 28, "generated_at": "2026-07-24T14:00:00Z", "losses": 8, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-1beeecccf3f2c84f", "rated_matches": 40, "raw_elo_rating": 1493.0353624600734, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "score": 29.333630559260232, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 22, "generated_at": "2026-07-18T00:14:00Z", "losses": 6, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-97d6a124a1509fc1", "rated_matches": 32, "raw_elo_rating": 1497.4607645377262, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "score": 28.680422200738533, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 30, "generated_at": "2026-07-17T22:36:00Z", "losses": 3, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-b0de9fa15f139d69", "rated_matches": 34, "raw_elo_rating": 1466.8816147147952, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "score": 21.862129220339213, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 33, "generated_at": "2026-07-02T16:51:45Z", "losses": 6, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-2404d10bab26a254", "rated_matches": 40, "raw_elo_rating": 1470.471675440953, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 23.94695253784734, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 29, "generated_at": "2026-07-11T17:22:09Z", "losses": 4, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-abd2cae3e3ff9bdb", "rated_matches": 34, "raw_elo_rating": 1473.203828704759, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 23.37144510109701, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 28, "generated_at": "2026-07-02T16:51:45Z", "losses": 4, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-e5b4a3586049e1c9", "rated_matches": 32, "raw_elo_rating": 1451.3652894673198, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 17.675949295316034, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 27, "generated_at": "2026-07-02T16:51:45Z", "losses": 5, "model": "tencent/hy3-preview", "point_rating_method": "sequential_elo", "public_id": "E-fbf6af15f65f01d7", "rated_matches": 32, "raw_elo_rating": 1440.1817737672786, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 15.006084296192038, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-9468e854340a4e9b", "rated_matches": 0, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 16, "generated_at": "2026-07-24T14:00:00Z", "losses": 7, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-0576181f89efa7a7", "rated_matches": 32, "raw_elo_rating": 1529.5895530689522, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 36.350597686204246, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 23, "generated_at": "2026-07-17T22:36:00Z", "losses": 6, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-8728b59f87c3369e", "rated_matches": 34, "raw_elo_rating": 1498.4661201948384, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 29.402366830547656, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 33, "generated_at": "2026-07-02T06:10:40Z", "losses": 3, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-9077f1e8e006290b", "rated_matches": 38, "raw_elo_rating": 1483.4827683360977, "reasoning": "highest", "reasoning_bracket": "highest", "reasoning_setting": "highest", "repair_status": "repaired", "score": 26.675502781911693, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 55, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 45, "generated_at": "2026-07-11T14:00:45Z", "losses": 7, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-4442c0e8a06187bf", "rated_matches": 55, "raw_elo_rating": 1479.8621657148212, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 28.34147388545191, "uncertainty": 23.065310478106092, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 56, "generated_at": "2026-07-02T16:51:45Z", "losses": 4, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-98394109d97d67ee", "rated_matches": 60, "raw_elo_rating": 1469.9243196020857, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 26.50315267184008, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 45, "generated_at": "2026-07-02T06:10:40Z", "losses": 8, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-dd5764d86cd88052", "rated_matches": 60, "raw_elo_rating": 1498.5754889140435, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 33.34310856600406, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 7 } ], "GB2-03": [ { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 20, "generated_at": "2026-07-03T17:50:00Z", "losses": 4, "model": "claude-fable-5", "point_rating_method": "sequential_elo", "public_id": "E-04fa5b762ca703f0", "rated_matches": 42, "raw_elo_rating": 1640.207188118948, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 69.09760234044293, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 1, "generated_at": "2026-07-25T15:48:00Z", "losses": 2, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-38759212c025e8eb", "rated_matches": 40, "raw_elo_rating": 1825.2086317117496, "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": 1813.538468676055, "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": 98.03501698464945, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 36 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 1, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 18, "generated_at": "2026-07-19T15:25:00Z", "losses": 7, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-1c251b669239429c", "rated_matches": 38, "raw_elo_rating": 1574.8313346483474, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 57.57597731707655, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 3, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 10, "generated_at": "2026-07-03T16:50:00Z", "losses": 25, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-2e43b0d163a7f12d", "rated_matches": 38, "raw_elo_rating": 1321.3059497167385, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 14.888221042628048, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 2, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 18, "generated_at": "2026-07-19T15:25:00Z", "losses": 12, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-d49e8df479ed0377", "rated_matches": 48, "raw_elo_rating": 1537.466076513104, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 52.44775415955655, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 18, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 9, "draws": 13, "generated_at": "2026-07-02T16:51:45Z", "losses": 1, "model": "google/gemini-3.5-flash", "point_rating_method": "sequential_elo", "public_id": "E-46c3bb79de67d970", "rated_matches": 18, "raw_elo_rating": 1530.8652651817986, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 45.50655322042652, "uncertainty": 70.95786693528086, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-dc837629b72c2e03", "rated_matches": 0, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-e9957a543416b0ad", "rated_matches": 0, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-ed24a723621c4481", "rated_matches": 0, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 22, "capped_draws": 1, "coverage_status": "under_covered", "distinct_rated_opponents": 11, "draws": 7, "generated_at": "2026-07-02T16:51:45Z", "losses": 9, "model": "gpt-5", "point_rating_method": "sequential_elo", "public_id": "E-cc568b7069d5a0fd", "rated_matches": 21, "raw_elo_rating": 1451.1281633788087, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 33.172778902818145, "uncertainty": 62.850358177805205, "unilateral_faults": 1, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 7, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 14, "generated_at": "2026-07-02T16:51:45Z", "losses": 18, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-4b75acaf58f14113", "rated_matches": 44, "raw_elo_rating": 1459.0530820785134, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 38.82631568621353, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 3, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 13, "generated_at": "2026-07-02T06:10:40Z", "losses": 23, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-6c4158c55a35d268", "rated_matches": 48, "raw_elo_rating": 1424.3051991222185, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 33.39410414668713, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 2, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 20, "generated_at": "2026-07-02T16:51:45Z", "losses": 10, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-e53a932f820d9724", "rated_matches": 39, "raw_elo_rating": 1524.6990353724188, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 49.27053092873559, "uncertainty": 35.30694150420948, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 2, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 17, "generated_at": "2026-07-10T10:07:13Z", "losses": 20, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-3bca3b4e02f2acf9", "rated_matches": 46, "raw_elo_rating": 1409.099303746516, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 30.63120574976151, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 4, "generated_at": "2026-07-10T05:30:29Z", "losses": 14, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-2ac4e83a1b9ba989", "rated_matches": 46, "raw_elo_rating": 1590.350902249458, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 61.14974362057465, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 11, "generated_at": "2026-07-10T05:30:29Z", "losses": 13, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-39e763b7d49209b4", "rated_matches": 42, "raw_elo_rating": 1548.6158310169712, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 53.67575600395128, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 18, "capped_draws": 2, "coverage_status": "under_covered", "distinct_rated_opponents": 9, "draws": 9, "generated_at": "2026-07-24T14:00:00Z", "losses": 5, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-c0c60ca46f3ce498", "rated_matches": 18, "raw_elo_rating": 1496.1041348226042, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 39.65359036624168, "uncertainty": 70.95786693528086, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 16, "generated_at": "2026-07-19T14:50:00Z", "losses": 14, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-714519b339aeb2e2", "rated_matches": 50, "raw_elo_rating": 1550.6088266920624, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 54.85123055069407, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 7, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 22, "generated_at": "2026-07-11T15:43:48Z", "losses": 17, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-bd2653f21938737f", "rated_matches": 46, "raw_elo_rating": 1432.536774486679, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 34.577528674842526, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 7 } ], "GB2-04": [ { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 9, "generated_at": "2026-07-03T17:50:00Z", "losses": 1, "model": "claude-fable-5", "point_rating_method": "sequential_elo", "public_id": "E-0ca15b39b465b370", "rated_matches": 56, "raw_elo_rating": 1821.3947826255776, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 100.0, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 46 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 30, "generated_at": "2026-07-03T17:20:00Z", "losses": 10, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-6344242dae68be1b", "rated_matches": 66, "raw_elo_rating": 1578.4078028250656, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 52.43603009561291, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 10, "generated_at": "2026-07-25T15:48:00Z", "losses": 8, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-4c98514bdb0eaf10", "rated_matches": 40, "raw_elo_rating": 1641.3226623696942, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 62.25515491431247, "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": 1752.5900684317492, "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": 84.41048134127871, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 27 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 43, "generated_at": "2026-07-03T16:50:00Z", "losses": 8, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-8e980ad934b3251e", "rated_matches": 62, "raw_elo_rating": 1533.9773873174586, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 43.2849917916824, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 22, "generated_at": "2026-07-02T16:51:45Z", "losses": 19, "model": "deepseek/deepseek-v4-pro", "point_rating_method": "sequential_elo", "public_id": "E-38bc194a470fbf62", "rated_matches": 48, "raw_elo_rating": 1440.214332474687, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 23.27152769675579, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 18, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 9, "draws": 14, "generated_at": "2026-07-02T16:51:45Z", "losses": 4, "model": "google/gemini-3.1-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-2be6f5c895691cb3", "rated_matches": 18, "raw_elo_rating": 1449.9540436634004, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 18.316733886011004, "uncertainty": 70.95786693528086, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 7, "generated_at": "2026-07-02T16:51:45Z", "losses": 16, "model": "google/gemini-3.5-flash", "point_rating_method": "sequential_elo", "public_id": "E-8e95359e4cbd1851", "rated_matches": 32, "raw_elo_rating": 1479.6173364839724, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 28.630744502168437, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-6c734fef813f984b", "rated_matches": 0, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-d7f1cd65263dbed7", "rated_matches": 0, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-ccfb6c993d1622b0", "rated_matches": 0, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 28, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 14, "draws": 21, "generated_at": "2026-07-02T16:51:45Z", "losses": 5, "model": "gpt-5", "point_rating_method": "sequential_elo", "public_id": "E-7e3da77777a95e31", "rated_matches": 28, "raw_elo_rating": 1469.0066409376975, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 25.5926504889775, "uncertainty": 49.09766908852594, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 27, "generated_at": "2026-07-02T16:51:45Z", "losses": 13, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-9279285adff8ed29", "rated_matches": 68, "raw_elo_rating": 1617.2220685254226, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 60.3067010884318, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 36, "generated_at": "2026-07-02T06:10:40Z", "losses": 12, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-040a4b654fceeb0c", "rated_matches": 56, "raw_elo_rating": 1477.4284617057842, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 31.510166457816872, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 15, "generated_at": "2026-07-09T17:30:50Z", "losses": 21, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-3403c285ceec6345", "rated_matches": 66, "raw_elo_rating": 1534.1070795948144, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 43.614965429384334, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 30 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 26, "generated_at": "2026-07-02T06:10:40Z", "losses": 22, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-bbf36865f2b7fe63", "rated_matches": 56, "raw_elo_rating": 1378.718853491191, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 11.855321711525466, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 42, "generated_at": "2026-07-02T16:51:45Z", "losses": 13, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-64bf5daf186f8119", "rated_matches": 66, "raw_elo_rating": 1470.3598482849127, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 30.921753926830576, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 33, "generated_at": "2026-07-10T05:30:29Z", "losses": 15, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-e348813cda8b38b7", "rated_matches": 60, "raw_elo_rating": 1514.736546987583, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 39.29062220793382, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 26, "generated_at": "2026-07-10T05:30:29Z", "losses": 2, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-270a233119b6cc62", "rated_matches": 54, "raw_elo_rating": 1653.789369331552, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 66.43667406598968, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 27, "generated_at": "2026-07-10T05:30:29Z", "losses": 12, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-b85c80e7475ef9ec", "rated_matches": 58, "raw_elo_rating": 1561.4093381266223, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 48.412604814752626, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 30, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 15, "draws": 15, "generated_at": "2026-07-17T22:36:00Z", "losses": 7, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-2a7239d6b25916b0", "rated_matches": 30, "raw_elo_rating": 1533.6610234761592, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "score": 38.95154594834624, "uncertainty": 46.05265101338746, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 11, "generated_at": "2026-07-24T14:00:00Z", "losses": 7, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-601725df2c678708", "rated_matches": 32, "raw_elo_rating": 1573.6723557360497, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "score": 47.35877751178312, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 8, "generated_at": "2026-07-17T22:36:00Z", "losses": 10, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-6f3da6d3b01bcfad", "rated_matches": 32, "raw_elo_rating": 1540.1574056912934, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "score": 40.68535278926445, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 26, "generated_at": "2026-07-11T17:22:09Z", "losses": 5, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-958dea26b779a042", "rated_matches": 32, "raw_elo_rating": 1453.633991580523, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 23.45699678597452, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 21, "generated_at": "2026-07-02T16:51:45Z", "losses": 9, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-3a27113d21c73b01", "rated_matches": 34, "raw_elo_rating": 1458.6554530564592, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 24.858822968717504, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 18, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 9, "draws": 11, "generated_at": "2026-07-02T16:51:45Z", "losses": 6, "model": "tencent/hy3-preview", "point_rating_method": "sequential_elo", "public_id": "E-51c104b34ef2a244", "rated_matches": 18, "raw_elo_rating": 1437.5787582504663, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 15.852593688498793, "uncertainty": 70.95786693528086, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 14, "generated_at": "2026-07-24T14:00:00Z", "losses": 12, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-07caaa12175b0b3c", "rated_matches": 34, "raw_elo_rating": 1490.7798276084395, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 31.25535929189119, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 24, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 12, "draws": 15, "generated_at": "2026-07-17T22:36:00Z", "losses": 9, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-70da8ff73f18e636", "rated_matches": 24, "raw_elo_rating": 1401.1566928359573, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 10.943189458281616, "uncertainty": 56.25, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 20, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 10, "draws": 11, "generated_at": "2026-07-17T22:36:00Z", "losses": 6, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-dac812d348a29158", "rated_matches": 20, "raw_elo_rating": 1465.438200124379, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 22.291782005613324, "uncertainty": 65.3589451179962, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 30, "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": 40, "raw_elo_rating": 1495.9190911735002, "reasoning": "highest", "reasoning_bracket": "highest", "reasoning_setting": "highest", "repair_status": "repaired", "score": 33.302708753199845, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 80, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 40, "draws": 57, "generated_at": "2026-07-11T15:43:48Z", "losses": 12, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-6d59400949b2dde9", "rated_matches": 80, "raw_elo_rating": 1514.4116043081467, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 40.57400938510051, "uncertainty": 11.805555555555554, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 25, "generated_at": "2026-07-02T06:10:40Z", "losses": 16, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-f9359f32abb5e3c8", "rated_matches": 50, "raw_elo_rating": 1438.546321559748, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 23.164729418732747, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 9 } ], "GB2-05": [ { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 8, "model": "claude-fable-5", "point_rating_method": "sequential_elo", "public_id": "E-5aa4402ccce7b855", "rated_matches": 64, "raw_elo_rating": 1897.678809124274, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 92.3708669015868, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 56 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 35, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-6774d700e60de31a", "rated_matches": 64, "raw_elo_rating": 1539.0151173817317, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 50.53327801033048, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 0, "generated_at": "2026-07-25T10:50:00Z", "losses": 0, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-3f3686d02d1503fa", "rated_matches": 40, "raw_elo_rating": 1975.937162276245, "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": 1742.2952393168755, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 72.74601543009426, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 76, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 38, "draws": 0, "generated_at": "2026-07-03T16:50:00Z", "losses": 38, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-c902807aab849f31", "rated_matches": 76, "raw_elo_rating": 1550.6378956784858, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 52.35911215449047, "uncertainty": 13.230288229818967, "unilateral_faults": 0, "wins": 38 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 57, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-b306c8f5ffbbec38", "rated_matches": 70, "raw_elo_rating": 1282.17152675321, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 20.822787568784545, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 13 }, { "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": 29, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-b3d889b0631db85f", "rated_matches": 72, "raw_elo_rating": 1561.569551356425, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 53.49053600554524, "uncertainty": 14.770573598065289, "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": 23, "model": "deepseek/deepseek-v4-pro", "point_rating_method": "sequential_elo", "public_id": "E-0ca4798825ceaccb", "rated_matches": 72, "raw_elo_rating": 1760.1833865422625, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 76.6585459712308, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 49 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 34, "model": "google/gemini-3.1-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-a72dd193e1dc4331", "rated_matches": 38, "raw_elo_rating": 1231.4676614197515, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 12.974224804876902, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 18, "model": "google/gemini-3.5-flash", "point_rating_method": "sequential_elo", "public_id": "E-b50da126631c1ea1", "rated_matches": 38, "raw_elo_rating": 1496.535066946335, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 43.89394541282078, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-27023858537764ac", "rated_matches": 0, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-2aebd7296279d5e5", "rated_matches": 0, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-68cd3c6f37a30f06", "rated_matches": 0, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 14, "model": "gpt-5", "point_rating_method": "sequential_elo", "public_id": "E-c5ad048b6fb4e93d", "rated_matches": 38, "raw_elo_rating": 1613.0836013006249, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 57.48915947673398, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 4, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-f6403f7a30e19e82", "rated_matches": 64, "raw_elo_rating": 1933.7094741760584, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 96.57379066170128, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 60 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 34, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-481582e8f8e3217e", "rated_matches": 64, "raw_elo_rating": 1550.7619638532972, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 51.903530268255835, "uncertainty": 18.26736729460423, "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": "2026-07-02T06:10:40Z", "losses": 43, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-95d1a872f51b78e7", "rated_matches": 82, "raw_elo_rating": 1447.8287691287428, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 40.56237732200695, "uncertainty": 11.132129994845172, "unilateral_faults": 0, "wins": 39 }, { "admitted_plugin_count": 1, "attempted_matches": 69, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 35, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-54b9ca4996a5589d", "rated_matches": 69, "raw_elo_rating": 1570.947088336314, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 54.46861652336368, "uncertainty": 16.01143046671968, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 0, "generated_at": "2026-07-09T17:30:50Z", "losses": 27, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-b05a7e0987de9967", "rated_matches": 68, "raw_elo_rating": 1662.473619841533, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 65.10478427948581, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 41 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 15, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-762e9d80a60b41ed", "rated_matches": 68, "raw_elo_rating": 1822.9563803754577, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 83.82486081338791, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 53 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 31, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-25a83ddaeb1268a4", "rated_matches": 66, "raw_elo_rating": 1576.596774461676, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 55.00415603353663, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 35 }, { "admitted_plugin_count": 1, "attempted_matches": 76, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 38, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 21, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-af9c2c2998294ad0", "rated_matches": 76, "raw_elo_rating": 1723.892992498132, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 72.56906281561947, "uncertainty": 13.230288229818967, "unilateral_faults": 0, "wins": 55 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 25, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-012ecb9ce0709c05", "rated_matches": 68, "raw_elo_rating": 1618.9193174279271, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 60.024239354593, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 43 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 34, "model": "mistralai/mistral-medium-3-5", "point_rating_method": "sequential_elo", "public_id": "E-1954b83d439b455c", "rated_matches": 38, "raw_elo_rating": 1194.7598086768326, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 8.692308102693845, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 0, "generated_at": "2026-07-18T00:14:00Z", "losses": 27, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-288f9a63e6b6cae3", "rated_matches": 52, "raw_elo_rating": 1497.0639330934057, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "score": 45.01795913236869, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugin_count": 1, "attempted_matches": 45, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 0, "generated_at": "2026-07-17T22:08:39Z", "losses": 20, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-95ac38f534c0080f", "rated_matches": 45, "raw_elo_rating": 1510.4006181260008, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "score": 46.10327191283094, "uncertainty": 29.97097807744857, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 30, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-48ed5c5e00ef38fb", "rated_matches": 38, "raw_elo_rating": 1303.4501134184768, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 21.370871310899688, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-11T17:22:09Z", "losses": 25, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-da3b98638ff53ea9", "rated_matches": 38, "raw_elo_rating": 1360.358923076814, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 28.009199743891315, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 0, "generated_at": "2026-07-03T16:00:00Z", "losses": 25, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-4fc62dc65156d576", "rated_matches": 46, "raw_elo_rating": 1464.7366162584292, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 40.85021390602501, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 22, "model": "stepfun/step-3.7-flash", "point_rating_method": "sequential_elo", "public_id": "E-358338a9fbdbcb6a", "rated_matches": 38, "raw_elo_rating": 1467.120892265347, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 40.4628254633776, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 0, "generated_at": "2026-07-03T19:10:00Z", "losses": 20, "model": "tencent/hy3-preview", "point_rating_method": "sequential_elo", "public_id": "E-92dc0ac61d798488", "rated_matches": 46, "raw_elo_rating": 1503.968198223127, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 45.426519887314186, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-e9202aa1565d1c4e", "rated_matches": 0, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-18T00:06:00Z", "losses": 20, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-87d1c39ddc685d7b", "rated_matches": 38, "raw_elo_rating": 1526.5340720250022, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 47.39328496272123, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 0, "generated_at": "2026-07-18T00:06:00Z", "losses": 23, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-bd7fcc801178eba2", "rated_matches": 48, "raw_elo_rating": 1509.86634976789, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 46.25487497409825, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 0, "generated_at": "2026-07-11T14:00:45Z", "losses": 40, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-235e4beedf22bc99", "rated_matches": 72, "raw_elo_rating": 1565.520646932364, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 53.95142545764748, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 39, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-503ecd021099d8f9", "rated_matches": 66, "raw_elo_rating": 1422.304523945283, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 37.006193332463226, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 27 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 31, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-51c8f79c1671819e", "rated_matches": 72, "raw_elo_rating": 1571.046296112905, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 54.59598425770226, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 41 } ], "GB2-06": [ { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 9, "generated_at": "2026-07-02T16:51:45Z", "losses": 11, "model": "claude-fable-5", "point_rating_method": "sequential_elo", "public_id": "E-499fbc92ee0778fb", "rated_matches": 58, "raw_elo_rating": 1705.5493909205152, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 80.12004893199418, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 38 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 3, "generated_at": "2026-07-03T17:20:00Z", "losses": 16, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-e804041031295d93", "rated_matches": 56, "raw_elo_rating": 1703.484096247477, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 79.72428872775545, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 37 }, { "admitted_plugin_count": 1, "attempted_matches": 84, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 42, "draws": 10, "generated_at": "2026-07-03T16:50:00Z", "losses": 33, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-51f3682dc3b76107", "rated_matches": 84, "raw_elo_rating": 1514.0458901456975, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 55.76800622889098, "uncertainty": 10.482614454664043, "unilateral_faults": 0, "wins": 41 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 46, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-5f5fd61f4544b8d7", "rated_matches": 68, "raw_elo_rating": 1323.215703235196, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 29.712995386485055, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 22 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 43, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-f527097ad30176f4", "rated_matches": 60, "raw_elo_rating": 1339.904328244146, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 31.52836404063522, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 2, "generated_at": "2026-07-02T16:51:45Z", "losses": 34, "model": "deepseek/deepseek-v4-pro", "point_rating_method": "sequential_elo", "public_id": "E-c9778645f1bbd12c", "rated_matches": 62, "raw_elo_rating": 1418.4552403692137, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 42.10102860564115, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 35, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 30, "model": "google/gemini-3.1-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-6238c7d8dc9e77d9", "rated_matches": 35, "raw_elo_rating": 1274.142055028033, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 20.710094817582146, "uncertainty": 39.583333333333336, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 6, "generated_at": "2026-07-02T16:51:45Z", "losses": 11, "model": "google/gemini-3.5-flash", "point_rating_method": "sequential_elo", "public_id": "E-5dcb27eaa0273049", "rated_matches": 36, "raw_elo_rating": 1612.9721687195993, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 65.96534432177022, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-48cc2611d5aa8816", "rated_matches": 0, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-9c3a169358692b43", "rated_matches": 0, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-280a7de63c992141", "rated_matches": 0, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-905531e52a8460f5", "rated_matches": 0, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 3, "generated_at": "2026-07-02T16:51:45Z", "losses": 15, "model": "gpt-5", "point_rating_method": "sequential_elo", "public_id": "E-1b082700b3692175", "rated_matches": 42, "raw_elo_rating": 1579.3828175389745, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 62.12510548843214, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 8, "generated_at": "2026-07-02T16:51:45Z", "losses": 9, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-6e5bbab022d4d9fa", "rated_matches": 54, "raw_elo_rating": 1779.224826819665, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 89.6862854041758, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 37 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 8, "generated_at": "2026-07-02T06:10:40Z", "losses": 16, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-0b7e07d12feb8fb5", "rated_matches": 58, "raw_elo_rating": 1635.094107106265, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 70.73493719095964, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 39, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-eca073d7ce610515", "rated_matches": 62, "raw_elo_rating": 1447.969206663917, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 46.032484936541564, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 5, "generated_at": "2026-07-02T06:10:40Z", "losses": 19, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-f9bb09fb2842dd1f", "rated_matches": 56, "raw_elo_rating": 1693.7457177478934, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 78.42707203303546, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 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": 66, "raw_elo_rating": 1718.0303169897015, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 82.20988966457762, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 38 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 13, "generated_at": "2026-07-10T05:30:29Z", "losses": 15, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-9eafeacabdedfdba", "rated_matches": 56, "raw_elo_rating": 1679.089981134785, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 76.4748305783871, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 6, "generated_at": "2026-07-10T05:30:29Z", "losses": 21, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-eb315c759774ef38", "rated_matches": 56, "raw_elo_rating": 1676.3558507059174, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 76.11062624621614, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugin_count": 1, "attempted_matches": 78, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 39, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 29, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-e6571a10c1120fab", "rated_matches": 78, "raw_elo_rating": 1635.2207187307338, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 71.69384651100232, "uncertainty": 12.5043950463012, "unilateral_faults": 0, "wins": 49 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 27, "model": "mistralai/mistral-medium-3-5", "point_rating_method": "sequential_elo", "public_id": "E-6c35f5ff426e7ada", "rated_matches": 34, "raw_elo_rating": 1302.1263042354692, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 24.311812653475105, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 3, "generated_at": "2026-07-17T22:36:00Z", "losses": 8, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-026a38fa3b1622ee", "rated_matches": 36, "raw_elo_rating": 1662.31724131217, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "score": 72.53843572214959, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 3, "generated_at": "2026-07-17T22:36:00Z", "losses": 13, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-3f2124a8621f4c67", "rated_matches": 36, "raw_elo_rating": 1565.9239776958489, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "score": 59.69821280136425, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 35, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 2, "generated_at": "2026-07-11T17:22:09Z", "losses": 19, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-ba2fb1c121873708", "rated_matches": 35, "raw_elo_rating": 1441.077477665935, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 42.947001834010294, "uncertainty": 39.583333333333336, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 4, "generated_at": "2026-07-03T16:00:00Z", "losses": 15, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-4162fe183e6383e1", "rated_matches": 36, "raw_elo_rating": 1473.8682311793768, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 47.435775966404, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 2, "generated_at": "2026-07-02T16:51:45Z", "losses": 24, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-a97b527d9b41a80c", "rated_matches": 54, "raw_elo_rating": 1547.9448102788183, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 58.87825112775808, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 24, "model": "stepfun/step-3.7-flash", "point_rating_method": "sequential_elo", "public_id": "E-2d684425ca56be18", "rated_matches": 36, "raw_elo_rating": 1377.7162538693242, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 34.627693984144734, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 29, "model": "tencent/hy3-preview", "point_rating_method": "sequential_elo", "public_id": "E-3627e3dbf7a48738", "rated_matches": 34, "raw_elo_rating": 1263.5377986641415, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 19.171567421318443, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-56e54327930d2f64", "rated_matches": 0, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 4, "generated_at": "2026-07-24T14:00:00Z", "losses": 21, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-5a1e23bce371a184", "rated_matches": 44, "raw_elo_rating": 1507.7875135985614, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 52.77075497157389, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 2, "generated_at": "2026-07-17T22:36:00Z", "losses": 23, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-5bedcf6c046c3b54", "rated_matches": 52, "raw_elo_rating": 1562.2705478444366, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 60.65223070845501, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 27 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 0, "generated_at": "2026-07-17T22:36:00Z", "losses": 21, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-cc9d4b5c56aea8b6", "rated_matches": 42, "raw_elo_rating": 1486.110635704911, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 49.700631390071806, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 6, "generated_at": "2026-07-02T06:10:40Z", "losses": 19, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-51421c7ae2af8f7b", "rated_matches": 42, "raw_elo_rating": 1501.76159895558, "reasoning": "highest", "reasoning_bracket": "highest", "reasoning_setting": "highest", "repair_status": "repaired", "score": 51.785443642756896, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 6, "generated_at": "2026-07-11T14:00:45Z", "losses": 17, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-f94d63d03c820dac", "rated_matches": 54, "raw_elo_rating": 1625.082997776762, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 69.153570024744, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 31 } ], "GB2-07": [ { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 25, "model": "claude-fable-5", "point_rating_method": "sequential_elo", "public_id": "E-babd82321b910e7b", "rated_matches": 62, "raw_elo_rating": 1604.40868111242, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 61.39391405879897, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 37 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 0, "generated_at": "2026-07-03T17:20:00Z", "losses": 20, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-5e09cecd1172d99b", "rated_matches": 54, "raw_elo_rating": 1619.730475331812, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 62.90248060999168, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 0, "generated_at": "2026-07-25T10:50:00Z", "losses": 1, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-1e882072d8d97548", "rated_matches": 40, "raw_elo_rating": 1910.1513048995253, "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": 98.99816924724276, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 39 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 0, "generated_at": "2026-07-03T16:50:00Z", "losses": 39, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-2146a36b46e938d6", "rated_matches": 66, "raw_elo_rating": 1413.3656681646023, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 37.12643857527608, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 27 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 37, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-20285efe5ad468c1", "rated_matches": 64, "raw_elo_rating": 1414.8050025004843, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 37.21520521577782, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 27 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 25, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-ecf2a6ea6f9fe06c", "rated_matches": 60, "raw_elo_rating": 1615.0471532159254, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 62.651235487949734, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 35 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 36, "model": "deepseek/deepseek-v4-pro", "point_rating_method": "sequential_elo", "public_id": "E-f398fd6ac8c8bada", "rated_matches": 70, "raw_elo_rating": 1591.641725509094, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 60.13352254421294, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 26, "model": "google/gemini-3.1-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-0d43f308cfa4da52", "rated_matches": 38, "raw_elo_rating": 1405.0073937310488, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 34.1119149241441, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 20, "model": "google/gemini-3.5-flash", "point_rating_method": "sequential_elo", "public_id": "E-f7f306cca2bb9532", "rated_matches": 38, "raw_elo_rating": 1599.944227917813, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 59.07358906140703, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-3e0523b11110a55d", "rated_matches": 0, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-82a1dfc4206e9ddd", "rated_matches": 0, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 21, "model": "gpt-5", "point_rating_method": "sequential_elo", "public_id": "E-15dad0db253c0497", "rated_matches": 46, "raw_elo_rating": 1534.7451158394265, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 51.45539811220371, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 6, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-80aa3ec3ac4ad97f", "rated_matches": 64, "raw_elo_rating": 1841.7924577346591, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 91.89097628140996, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 58 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 21, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-1b33882368041bb3", "rated_matches": 62, "raw_elo_rating": 1625.5679651607013, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 64.1033617401179, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 41 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 29, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-e453890c6dd35fa3", "rated_matches": 64, "raw_elo_rating": 1655.8031190639394, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 68.0750295196216, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 35 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 0, "generated_at": "2026-07-09T17:30:50Z", "losses": 32, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-b9e3f57bc887c6ae", "rated_matches": 66, "raw_elo_rating": 1614.0817686577604, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 62.82814813424107, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 39, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-e0e874b71d913c12", "rated_matches": 62, "raw_elo_rating": 1373.8370593378063, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 31.869203082298856, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 8, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-6201278165db862a", "rated_matches": 66, "raw_elo_rating": 1810.87837198572, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 88.02796582947613, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 58 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 21, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-73a7b73c1df452ad", "rated_matches": 54, "raw_elo_rating": 1627.6157786139568, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 63.912194201697034, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 33 }, { "admitted_plugin_count": 1, "attempted_matches": 78, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 39, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 28, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-1b522c9c14f3860c", "rated_matches": 78, "raw_elo_rating": 1544.1316071761985, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 54.36584442360475, "uncertainty": 12.5043950463012, "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": "2026-07-10T05:30:29Z", "losses": 26, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-65bf9818e3e1b632", "rated_matches": 68, "raw_elo_rating": 1685.24753254842, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 72.0322843616957, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 42 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 38, "model": "mistralai/mistral-medium-3-5", "point_rating_method": "sequential_elo", "public_id": "E-d0d0df9d83b6e37e", "rated_matches": 38, "raw_elo_rating": 1159.6470831593338, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 2.6935113973845364, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 0, "generated_at": "2026-07-24T14:00:00Z", "losses": 22, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-1d1372c78963efdf", "rated_matches": 46, "raw_elo_rating": 1557.566963460809, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "score": 54.377737165834944, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 0, "generated_at": "2026-07-17T22:36:00Z", "losses": 26, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-49105fbc7f72e6fe", "rated_matches": 52, "raw_elo_rating": 1541.026511259736, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "score": 52.69532819673755, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 0, "generated_at": "2026-07-17T22:36:00Z", "losses": 15, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-77d9c422124dcbfe", "rated_matches": 42, "raw_elo_rating": 1514.0936270512832, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "score": 48.47120156822998, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 27 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-03T16:00:00Z", "losses": 27, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-312d25e3a9eeeee3", "rated_matches": 38, "raw_elo_rating": 1346.6875431579392, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 26.64405431271601, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 27, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-29bc7f4fdf0f7b14", "rated_matches": 38, "raw_elo_rating": 1341.462164017372, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 25.974944178170976, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 30, "model": "stepfun/step-3.7-flash", "point_rating_method": "sequential_elo", "public_id": "E-6a5e44fe2dde4257", "rated_matches": 38, "raw_elo_rating": 1290.2573125898307, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 19.41815966428748, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 27, "model": "tencent/hy3-preview", "point_rating_method": "sequential_elo", "public_id": "E-dfed1e345a939bcd", "rated_matches": 38, "raw_elo_rating": 1342.1997504917822, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 26.06939217359004, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-38e756fc6f3a2db6", "rated_matches": 0, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-17T22:36:00Z", "losses": 17, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-0929811cef80813b", "rated_matches": 38, "raw_elo_rating": 1479.0889751496873, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 43.59806618262557, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 0, "generated_at": "2026-07-24T14:00:00Z", "losses": 25, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-436a3933a93e10cd", "rated_matches": 42, "raw_elo_rating": 1539.6947107510462, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 51.74942198019185, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-17T22:36:00Z", "losses": 13, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-8e7f3829f3e45642", "rated_matches": 38, "raw_elo_rating": 1679.6525385132904, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 69.28024335235449, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugin_count": 1, "attempted_matches": 76, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 38, "draws": 0, "generated_at": "2026-07-11T14:00:45Z", "losses": 28, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-c81741d135c9dc9c", "rated_matches": 76, "raw_elo_rating": 1580.50015200578, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 58.94847838975526, "uncertainty": 13.230288229818967, "unilateral_faults": 0, "wins": 48 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 27, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-cb438d112c0ea172", "rated_matches": 60, "raw_elo_rating": 1543.579363142568, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 53.49978037909996, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 33 }, { "admitted_plugin_count": 1, "attempted_matches": 78, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 39, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 37, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-d96269dd04d644e0", "rated_matches": 78, "raw_elo_rating": 1584.3015958519711, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 59.509614053419874, "uncertainty": 12.5043950463012, "unilateral_faults": 0, "wins": 41 } ], "GB2-08": [ { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 1, "generated_at": "2026-07-02T16:51:45Z", "losses": 4, "model": "claude-fable-5", "point_rating_method": "sequential_elo", "public_id": "E-12891afa894223fd", "rated_matches": 66, "raw_elo_rating": 1912.1873848057296, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 100.0, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 61 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 0, "generated_at": "2026-07-03T17:20:00Z", "losses": 20, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-22dc6fe5ae5fb8b1", "rated_matches": 66, "raw_elo_rating": 1686.1260261745642, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 65.02884715553996, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 46 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 0, "generated_at": "2026-07-25T15:48:01Z", "losses": 10, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-a40851c4f03704e5", "rated_matches": 40, "raw_elo_rating": 1796.884681881971, "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": 80.0587922281817, "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": 1582.4905656280778, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 46.89253394385154, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugin_count": 1, "attempted_matches": 80, "capped_draws": 42, "coverage_status": "rated", "distinct_rated_opponents": 40, "draws": 42, "generated_at": "2026-07-03T16:50:00Z", "losses": 28, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-b5805acb90227d50", "rated_matches": 80, "raw_elo_rating": 1464.6642579295235, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 31.45351907819096, "uncertainty": 11.805555555555554, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 48, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 48, "generated_at": "2026-07-02T16:51:45Z", "losses": 14, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-a7310645c3b96434", "rated_matches": 66, "raw_elo_rating": 1432.1969593602666, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 25.746626341753977, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 54, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 54, "generated_at": "2026-07-02T16:51:45Z", "losses": 10, "model": "deepseek/deepseek-v4-pro", "point_rating_method": "sequential_elo", "public_id": "E-3a5b5c4507a989d3", "rated_matches": 70, "raw_elo_rating": 1440.883097011328, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 27.30638809711645, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 29, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 29, "generated_at": "2026-07-02T16:51:45Z", "losses": 6, "model": "google/gemini-3.1-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-b335c9f92035f80b", "rated_matches": 38, "raw_elo_rating": 1424.855704467417, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 22.26210300852069, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 25, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 25, "generated_at": "2026-07-02T16:51:45Z", "losses": 13, "model": "google/gemini-3.5-flash", "point_rating_method": "sequential_elo", "public_id": "E-fa332e578ae97122", "rated_matches": 38, "raw_elo_rating": 1374.5261450195408, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 14.4762402378837, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-0d09401e4a31ea61", "rated_matches": 0, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-96566b3cf3a15c23", "rated_matches": 0, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-37e04d4125f1d7fa", "rated_matches": 0, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-ee7ca879a02fdaf7", "rated_matches": 0, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 27, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 27, "generated_at": "2026-07-02T16:51:45Z", "losses": 10, "model": "gpt-5", "point_rating_method": "sequential_elo", "public_id": "E-ebca8ea756b4a4ad", "rated_matches": 42, "raw_elo_rating": 1424.0251709745728, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 22.605732802891488, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 15, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 15, "generated_at": "2026-07-02T16:51:45Z", "losses": 28, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-ddc1f3e68bf1e74a", "rated_matches": 68, "raw_elo_rating": 1526.706490224709, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 40.47739221194158, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 4, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 4, "generated_at": "2026-07-02T16:51:45Z", "losses": 30, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-1e5d07fc67fd8710", "rated_matches": 64, "raw_elo_rating": 1539.8645730727508, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 42.287126930820214, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 30 }, { "admitted_plugin_count": 1, "attempted_matches": 80, "capped_draws": 48, "coverage_status": "rated", "distinct_rated_opponents": 40, "draws": 48, "generated_at": "2026-07-02T06:10:40Z", "losses": 20, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-b63acb1096519102", "rated_matches": 80, "raw_elo_rating": 1435.7608686525116, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 26.98223371456328, "uncertainty": 11.805555555555554, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 15, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-98e55f26cfe52488", "rated_matches": 70, "raw_elo_rating": 1750.5108418795649, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 75.20506152028769, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 55 }, { "admitted_plugin_count": 1, "attempted_matches": 76, "capped_draws": 58, "coverage_status": "rated", "distinct_rated_opponents": 38, "draws": 58, "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": 76, "raw_elo_rating": 1434.2406436791346, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 26.57073634165292, "uncertainty": 13.230288229818967, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 49, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 49, "generated_at": "2026-07-09T17:30:50Z", "losses": 14, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-bb4437fab8180bfc", "rated_matches": 70, "raw_elo_rating": 1428.0616564555903, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 25.32294183245682, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 9, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 9, "generated_at": "2026-07-02T16:51:45Z", "losses": 16, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-3e859a6b27767128", "rated_matches": 68, "raw_elo_rating": 1690.1796710479507, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 65.76630327200057, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 43 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 5, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 5, "generated_at": "2026-07-10T05:30:29Z", "losses": 29, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-0fb7de4e8156a229", "rated_matches": 66, "raw_elo_rating": 1548.27072293001, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 43.70296063793118, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 12, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 12, "generated_at": "2026-07-10T05:30:29Z", "losses": 32, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-3ae62f195160add3", "rated_matches": 64, "raw_elo_rating": 1369.9378527645924, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 15.99986870925893, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 10, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 10, "generated_at": "2026-07-10T05:30:29Z", "losses": 31, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-b061663dc342c859", "rated_matches": 68, "raw_elo_rating": 1548.5237946011143, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 43.85247714738262, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 27 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 25, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 25, "generated_at": "2026-07-18T00:14:00Z", "losses": 11, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-134262cb96978830", "rated_matches": 38, "raw_elo_rating": 1388.9362846288373, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "score": 16.705454455820554, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 33, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 33, "generated_at": "2026-07-17T22:36:00Z", "losses": 14, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-b06cbc77b01de3b3", "rated_matches": 50, "raw_elo_rating": 1428.8251492988911, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "score": 24.11994446924585, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 28, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 28, "generated_at": "2026-07-11T17:22:09Z", "losses": 10, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-2e3c01d0103fc439", "rated_matches": 42, "raw_elo_rating": 1438.964107250163, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 24.91675060350417, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 28, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 28, "generated_at": "2026-07-02T16:51:45Z", "losses": 8, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-8c24e8bcbe9b1228", "rated_matches": 42, "raw_elo_rating": 1429.4122086278544, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 23.439094675493273, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 1, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 1, "generated_at": "2026-07-03T16:00:00Z", "losses": 15, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-1b6fc7dfefb8cea4", "rated_matches": 38, "raw_elo_rating": 1613.100257778122, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 51.3830862930041, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 22 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 32, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 32, "generated_at": "2026-07-02T16:51:45Z", "losses": 7, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-24a75273941e6ea3", "rated_matches": 44, "raw_elo_rating": 1440.0315846686565, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 25.29396931156561, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 28, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 28, "generated_at": "2026-07-02T16:51:45Z", "losses": 13, "model": "stepfun/step-3.7-flash", "point_rating_method": "sequential_elo", "public_id": "E-8b265019ada47f24", "rated_matches": 44, "raw_elo_rating": 1425.956256611796, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 23.116549641999313, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 9, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 9, "generated_at": "2026-07-02T16:51:45Z", "losses": 22, "model": "tencent/hy3-preview", "point_rating_method": "sequential_elo", "public_id": "E-81a5e5ef15f371dc", "rated_matches": 46, "raw_elo_rating": 1431.7219769582784, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 24.206889853330413, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-d21921560d198b28", "rated_matches": 0, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-17T22:36:00Z", "losses": 13, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-1c7222840add0cf9", "rated_matches": 38, "raw_elo_rating": 1634.515679078594, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 54.69600087540841, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-17T22:36:00Z", "losses": 10, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-60939cc4ea338b18", "rated_matches": 38, "raw_elo_rating": 1671.2557038089158, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 60.37959504706703, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-24T14:00:00Z", "losses": 4, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-707dd709e358a173", "rated_matches": 38, "raw_elo_rating": 1783.1611323348034, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 77.69109785674755, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 39, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 39, "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": 46, "raw_elo_rating": 1439.4563174105635, "reasoning": "highest", "reasoning_bracket": "highest", "reasoning_setting": "highest", "repair_status": "repaired", "score": 25.403373868757644, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 0, "generated_at": "2026-07-11T14:00:45Z", "losses": 23, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-907d60010bf80864", "rated_matches": 64, "raw_elo_rating": 1695.4682380124432, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 66.3586426587361, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 41 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 58, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 58, "generated_at": "2026-07-02T06:10:40Z", "losses": 14, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-9e8f3e43bfd2810e", "rated_matches": 72, "raw_elo_rating": 1400.4491945908924, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 21.152657009799032, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 30, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 30, "generated_at": "2026-07-02T16:51:45Z", "losses": 30, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-bc28f817090c9f60", "rated_matches": 62, "raw_elo_rating": 1307.1251840172183, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 6.162022756076456, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 2 } ] }, "full_freedom/mixed": { "GB2-01": [ { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 20, "model": "claude-fable-5", "point_rating_method": "sequential_elo", "public_id": "E-2dbc6efbd7db03b5", "rated_matches": 56, "raw_elo_rating": 1665.451007353691, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 68.96939634840618, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 36 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 0, "generated_at": "2026-07-03T17:50:00Z", "losses": 24, "model": "claude-fable-5", "point_rating_method": "sequential_elo", "public_id": "E-8000131e469a8bb6", "rated_matches": 58, "raw_elo_rating": 1614.289805193975, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 62.48880272697796, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 41, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 41, "generated_at": "2026-07-02T16:51:45Z", "losses": 10, "model": "claude-opus-4-5", "point_rating_method": "sequential_elo", "public_id": "E-2e3eca63f7980fac", "rated_matches": 62, "raw_elo_rating": 1440.0631482289907, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 40.23843353793476, "uncertainty": 19.244078834871203, "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": 34, "capped_draws": 5, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 5, "losses": 14, "model": "claude-opus-4-5", "point_rating_method": "sequential_elo", "public_id": "E-5b675f86b98132f4", "rated_matches": 34, "raw_elo_rating": 1520.743874815622, "reasoning": "legacy_shared_thinking_budget", "reasoning_bracket": "intensive", "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "legacy_shared_thinking_budget", "repair_status": "first_pass", "score": 48.42226113161696, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 0, "model": "claude-opus-4-5", "point_rating_method": "sequential_elo", "public_id": "E-7631f602d0516364", "rated_matches": 0, "reasoning": "legacy_shared_thinking_budget", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "budget", "reasoning_setting": "legacy_shared_thinking_budget", "repair_status": "first_pass", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 6, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 6, "losses": 12, "model": "claude-opus-4-5", "point_rating_method": "sequential_elo", "public_id": "E-829b603611fbdcef", "rated_matches": 32, "raw_elo_rating": 1537.5958304960288, "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": 50.33505102707553, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 9, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 9, "generated_at": "2026-07-02T16:51:45Z", "losses": 23, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-13ec9509bc80f2bf", "rated_matches": 52, "raw_elo_rating": 1484.8070614799876, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 45.42169278538346, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 6, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 6, "generated_at": "2026-07-03T17:20:00Z", "losses": 19, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-3308d2952452916e", "rated_matches": 58, "raw_elo_rating": 1593.5380641852346, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 59.81280359013286, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 33 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 16, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 16, "generated_at": "2026-07-02T16:51:45Z", "losses": 19, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-757a6149e87d8b53", "rated_matches": 58, "raw_elo_rating": 1573.4332627403917, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 57.22022924708464, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 5, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 5, "generated_at": "2026-07-25T15:48:00Z", "losses": 16, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-0437af9582860271", "rated_matches": 50, "raw_elo_rating": 1555.183876640609, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 54.35940383926061, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 36, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 36, "generated_at": "2026-07-25T15:48:00Z", "losses": 5, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-6c30dc38efb07e9e", "rated_matches": 52, "raw_elo_rating": 1538.1067446190257, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 52.29484651326144, "uncertainty": 24.930281974344517, "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": 1807.1973005834263, "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": 86.02447212008084, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 31 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 12, "coverage_status": "rated", "distinct_rated_opponents": 26, "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": 52, "raw_elo_rating": 1790.6111623268318, "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": 84.85604721208772, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 31 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 2, "coverage_status": "rated", "distinct_rated_opponents": 25, "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": 50, "raw_elo_rating": 1689.9192786895337, "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": 71.73393735110122, "uncertainty": 26.26400420140049, "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": "2026-07-25T15:48:00Z", "losses": 21, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-bf06fe9df8858291", "rated_matches": 40, "raw_elo_rating": 1471.125886827351, "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": 42.68705706893992, "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": 1580.6415648788145, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 59.06172320072071, "uncertainty": 12.5043950463012, "unilateral_faults": 0, "wins": 44 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 12, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 12, "generated_at": "2026-07-02T16:51:45Z", "losses": 9, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-73ff84eba4ec19cb", "rated_matches": 44, "raw_elo_rating": 1562.340614191469, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 54.81582799890011, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 8, "coverage_status": "rated", "distinct_rated_opponents": 31, "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": 62, "raw_elo_rating": 1452.0417343596705, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 41.78310808513646, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 47, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 47, "generated_at": "2026-07-02T16:51:45Z", "losses": 11, "model": "cohere/north-mini-code", "point_rating_method": "sequential_elo", "public_id": "E-194759b182ce3244", "rated_matches": 72, "raw_elo_rating": 1467.9446557274146, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 44.295334926890746, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 18, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 18, "generated_at": "2026-07-11T17:22:09Z", "losses": 47, "model": "cohere/north-mini-code", "point_rating_method": "sequential_elo", "public_id": "E-c309b463b29efb71", "rated_matches": 68, "raw_elo_rating": 1209.147982936052, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 10.750205159497384, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 18, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 18, "generated_at": "2026-07-02T16:51:45Z", "losses": 28, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-b9882650a0cde9ac", "rated_matches": 62, "raw_elo_rating": 1396.162780126903, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 34.57734962700469, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 26, "coverage_status": "rated", "distinct_rated_opponents": 37, "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": 74, "raw_elo_rating": 1483.438796086254, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 46.374389594950806, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 12, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 12, "generated_at": "2026-07-02T06:10:40Z", "losses": 25, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-cb8739e00cafec5b", "rated_matches": 60, "raw_elo_rating": 1501.6717916093205, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 48.07737701917374, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 24, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 24, "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": 46, "raw_elo_rating": 1358.062733964776, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 28.638963702727548, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 6, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 6, "generated_at": "2026-07-01T00:15:48Z", "losses": 20, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-fd9da5310ad15cac", "rated_matches": 44, "raw_elo_rating": 1603.8559723664998, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 60.16935773866531, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 84, "capped_draws": 28, "coverage_status": "rated", "distinct_rated_opponents": 42, "draws": 28, "generated_at": "2026-07-02T16:51:45Z", "losses": 30, "model": "deepseek/deepseek-v4-pro", "point_rating_method": "sequential_elo", "public_id": "E-e121525dd1846069", "rated_matches": 84, "raw_elo_rating": 1490.425377493292, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 47.636647445449704, "uncertainty": 10.482614454664043, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 12, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 12, "generated_at": "2026-07-02T16:51:45Z", "losses": 22, "model": "deepseek/deepseek-v4-pro", "point_rating_method": "sequential_elo", "public_id": "E-e192048d4eaa3c43", "rated_matches": 62, "raw_elo_rating": 1482.114031725191, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 45.66102087130642, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 29, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 29, "generated_at": "2026-07-02T16:51:45Z", "losses": 16, "model": "google/gemini-3.1-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-7669b8a03ef19548", "rated_matches": 58, "raw_elo_rating": 1455.3793905117934, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 41.996828952531544, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 23, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 23, "generated_at": "2026-07-02T16:51:45Z", "losses": 17, "model": "google/gemini-3.1-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-cc0af0bfa6a9a29f", "rated_matches": 46, "raw_elo_rating": 1337.399703918666, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 25.974404110127313, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 9, "model": "google/gemini-3.5-flash", "point_rating_method": "sequential_elo", "public_id": "E-22f31826bcf76511", "rated_matches": 56, "raw_elo_rating": 1823.1594383472432, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 89.30637072728769, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 47 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-21T14:20:15Z", "losses": 0, "model": "google/gemini-3.5-flash", "point_rating_method": "sequential_elo", "public_id": "E-b33eea8b864e22bf", "rated_matches": 0, "reasoning": "low", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "low", "repair_status": "first_pass", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-21c0edac8ac36f2e", "rated_matches": 0, "reasoning": "minimal", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "minimal", "repair_status": "first_pass", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-3ade0bdbb45d890e", "rated_matches": 0, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-401e0639de33ca9e", "rated_matches": 0, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 20, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 20, "generated_at": "2026-07-24T13:40:00Z", "losses": 23, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-77d8df8cd762fd09", "rated_matches": 68, "raw_elo_rating": 1487.8622040397863, "reasoning": "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": 46.69123848223904, "uncertainty": 16.4429265428846, "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-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": 62, "capped_draws": 11, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 11, "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": 62, "raw_elo_rating": 1516.2643236863769, "reasoning": "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": 50.06480327070365, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 33, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 33, "generated_at": "2026-07-24T13:40:00Z", "losses": 18, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-4b36631072d1c39e", "rated_matches": 62, "raw_elo_rating": 1326.375382396334, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 25.57805573590371, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 2, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 2, "generated_at": "2026-07-24T13:40:00Z", "losses": 8, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-7484f4e7d8863a3b", "rated_matches": 62, "raw_elo_rating": 1844.595746189268, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 92.40412327507312, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 52 }, { "admitted_plugin_count": 1, "attempted_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": 76, "capped_draws": 18, "coverage_status": "rated", "distinct_rated_opponents": 38, "draws": 18, "generated_at": "2026-07-02T16:51:45Z", "losses": 26, "model": "google/gemma-4-31b-it", "point_rating_method": "sequential_elo", "public_id": "E-caaa54d3c88e6570", "rated_matches": 76, "raw_elo_rating": 1467.5007886172232, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 44.39699646208931, "uncertainty": 13.230288229818967, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 23, "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": 46, "raw_elo_rating": 1573.0858652952545, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 56.36684029870736, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 7, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 7, "generated_at": "2026-07-02T16:51:45Z", "losses": 17, "model": "gpt-5", "point_rating_method": "sequential_elo", "public_id": "E-3e63b136f656e976", "rated_matches": 38, "raw_elo_rating": 1501.5044492434015, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 46.400491379313614, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-21T14:20:15Z", "losses": 0, "model": "gpt-5", "point_rating_method": "sequential_elo", "public_id": "E-4370194a9beec334", "rated_matches": 0, "reasoning": "low", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "low", "repair_status": "first_pass", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 17, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 17, "generated_at": "2026-07-02T16:51:45Z", "losses": 25, "model": "gpt-5", "point_rating_method": "sequential_elo", "public_id": "E-adee794ecd761044", "rated_matches": 56, "raw_elo_rating": 1358.9198897376532, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 29.44129093251917, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 26, "coverage_status": "rated", "distinct_rated_opponents": 31, "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": 62, "raw_elo_rating": 1645.4310233167598, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 66.72123593215844, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 2, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-5d8a6b14c27539ab", "rated_matches": 60, "raw_elo_rating": 1904.3194643073384, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 100.0, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 58 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 2, "coverage_status": "rated", "distinct_rated_opponents": 33, "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": 66, "raw_elo_rating": 1840.8511544908365, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 92.11822076992448, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 58 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 21, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 21, "generated_at": "2026-07-01T00:15:48Z", "losses": 36, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-3834aa9e894c458b", "rated_matches": 66, "raw_elo_rating": 1298.181557125292, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 22.13935135696185, "uncertainty": 17.33472217815261, "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": 1588.6473905325695, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 59.29314091807598, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 31 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 16, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 16, "generated_at": "2026-07-01T00:15:48Z", "losses": 34, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-aa899d4eca8a2891", "rated_matches": 58, "raw_elo_rating": 1312.380356821258, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 23.556675397975365, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 76, "capped_draws": 18, "coverage_status": "rated", "distinct_rated_opponents": 38, "draws": 18, "generated_at": "2026-07-02T06:10:40Z", "losses": 32, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-b6ed01547d27188c", "rated_matches": 76, "raw_elo_rating": 1491.1216061968814, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 47.44297161319194, "uncertainty": 13.230288229818967, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 76, "capped_draws": 11, "coverage_status": "rated", "distinct_rated_opponents": 38, "draws": 11, "generated_at": "2026-07-02T06:10:40Z", "losses": 30, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-c675a6c67536654d", "rated_matches": 76, "raw_elo_rating": 1503.5911773559517, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 49.05096014988609, "uncertainty": 13.230288229818967, "unilateral_faults": 0, "wins": 35 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 6, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 6, "generated_at": "2026-07-02T06:10:40Z", "losses": 19, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-ca99b677101014a8", "rated_matches": 60, "raw_elo_rating": 1533.3730974136329, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 52.16535532101704, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 35 }, { "admitted_plugin_count": 1, "attempted_matches": 78, "capped_draws": 31, "coverage_status": "rated", "distinct_rated_opponents": 39, "draws": 31, "generated_at": "2026-07-02T16:51:45Z", "losses": 27, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-ea1cb793f92b3cff", "rated_matches": 78, "raw_elo_rating": 1434.2195613946458, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 40.18016744239998, "uncertainty": 12.5043950463012, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 17, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 17, "generated_at": "2026-07-02T06:10:40Z", "losses": 21, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-22c14c8deb751cb3", "rated_matches": 54, "raw_elo_rating": 1396.077491107873, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 34.109764142612626, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 18, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 18, "generated_at": "2026-07-02T06:10:40Z", "losses": 35, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-5c28f8f5135ce060", "rated_matches": 72, "raw_elo_rating": 1401.7572655735244, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 35.760272791755234, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 15, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 15, "generated_at": "2026-07-02T16:51:45Z", "losses": 26, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-9257cc1e94bf4b17", "rated_matches": 62, "raw_elo_rating": 1423.032941291813, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 38.04233736243864, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 10, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 10, "generated_at": "2026-07-01T00:15:48Z", "losses": 45, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-98c36ba5e36ecf75", "rated_matches": 56, "raw_elo_rating": 1130.609635080802, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 0.0, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 20, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 20, "generated_at": "2026-07-09T17:30:50Z", "losses": 22, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-9eb27042bf28d67c", "rated_matches": 72, "raw_elo_rating": 1493.5688055188753, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 47.599645764976906, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 30 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 22, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 22, "generated_at": "2026-07-02T16:51:45Z", "losses": 26, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-a8887794a1195b75", "rated_matches": 64, "raw_elo_rating": 1528.155373010458, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 51.69894958662488, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 9, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 9, "generated_at": "2026-07-09T17:30:50Z", "losses": 46, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-c48c1aed1cdecc72", "rated_matches": 56, "raw_elo_rating": 1163.6421749792917, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 4.259644924198314, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 31, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 31, "generated_at": "2026-07-09T17:30:50Z", "losses": 18, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-db1fc33e2a2467d5", "rated_matches": 58, "raw_elo_rating": 1422.4893012366283, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 37.75555346272907, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 9 }, { "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": 38, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-f491ad1b583dbcac", "rated_matches": 62, "raw_elo_rating": 1217.7883112287816, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 11.575427783168683, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 7, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 7, "generated_at": "2026-07-02T06:10:40Z", "losses": 46, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-fbb3f2dccb7c7fba", "rated_matches": 60, "raw_elo_rating": 1247.6398373848845, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 15.319195912858827, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 86, "capped_draws": 62, "coverage_status": "rated", "distinct_rated_opponents": 43, "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": 86, "raw_elo_rating": 1491.1257108359016, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 47.79163908116498, "uncertainty": 9.855626741889738, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 19, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 19, "generated_at": "2026-07-02T16:51:45Z", "losses": 12, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-8c61292c31db2722", "rated_matches": 60, "raw_elo_rating": 1726.2827891456054, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 77.04163766987543, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 38, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 38, "generated_at": "2026-07-02T16:51:45Z", "losses": 3, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-e4496be687faac9d", "rated_matches": 56, "raw_elo_rating": 1579.6537688986575, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 57.905585560065134, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 18, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-38187ed58fb76057", "rated_matches": 54, "raw_elo_rating": 1644.604801686931, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 66.15810496914253, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 36 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 8, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 8, "generated_at": "2026-07-10T05:30:29Z", "losses": 23, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-4f775a5b7b265dae", "rated_matches": 62, "raw_elo_rating": 1633.9498843243437, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 65.24070868286577, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 31 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 20, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 20, "generated_at": "2026-07-10T05:30:29Z", "losses": 35, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-959ed218b1c5605b", "rated_matches": 67, "raw_elo_rating": 1353.552660186412, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 29.32612813598716, "uncertainty": 16.883906259083243, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 15, "coverage_status": "rated", "distinct_rated_opponents": 33, "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": 66, "raw_elo_rating": 1567.6962238815845, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 56.894074601780616, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 16, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-9e683b3cd6c7f7c3", "rated_matches": 58, "raw_elo_rating": 1716.2957199694602, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 75.64277085800467, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 42 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 25, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-bc834303cebba06a", "rated_matches": 54, "raw_elo_rating": 1590.5607673020877, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 59.188964919420734, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 12, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 12, "generated_at": "2026-07-10T05:30:29Z", "losses": 23, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-36d36f4895d90b11", "rated_matches": 54, "raw_elo_rating": 1474.4008078994289, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 44.20979035442635, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 21, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 21, "generated_at": "2026-07-10T05:30:29Z", "losses": 24, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-40742129939a44b5", "rated_matches": 64, "raw_elo_rating": 1569.1781720591457, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 56.98896235225361, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 20, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 20, "generated_at": "2026-07-10T05:30:29Z", "losses": 18, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-46de264ad4571b48", "rated_matches": 56, "raw_elo_rating": 1501.322471283357, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 47.80453019713377, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 22, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 22, "generated_at": "2026-07-24T13:40:00Z", "losses": 20, "model": "inclusionai/ling-3.0-flash", "point_rating_method": "sequential_elo", "public_id": "E-3c618b88b6bdb039", "rated_matches": 62, "raw_elo_rating": 1413.3141988259033, "reasoning": "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": 36.78907642211369, "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": 64, "capped_draws": 13, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 13, "generated_at": "2026-07-24T13:40:00Z", "losses": 33, "model": "inclusionai/ling-3.0-flash", "point_rating_method": "sequential_elo", "public_id": "E-f9af396559c3a1cd", "rated_matches": 64, "raw_elo_rating": 1531.8401159225134, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 52.17410821779725, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-5e8d45873865cc93", "rated_matches": 0, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 18, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 18, "generated_at": "2026-07-24T13:40:00Z", "losses": 25, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-9f5585b5fd96f2c3", "rated_matches": 64, "raw_elo_rating": 1499.0882262859534, "reasoning": "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": 47.95065398518296, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 23, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 23, "generated_at": "2026-07-24T13:40:00Z", "losses": 25, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-ed0f8e084958eebc", "rated_matches": 70, "raw_elo_rating": 1459.2708693088157, "reasoning": "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": 43.09238481644139, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 22 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 15, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 15, "generated_at": "2026-07-02T16:51:45Z", "losses": 23, "model": "minimax/minimax-m3", "point_rating_method": "sequential_elo", "public_id": "E-444510032bc433fc", "rated_matches": 70, "raw_elo_rating": 1497.8471484037084, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 48.06691150878728, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 1, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 1, "generated_at": "2026-07-02T16:51:45Z", "losses": 17, "model": "minimax/minimax-m3", "point_rating_method": "sequential_elo", "public_id": "E-e0a841a9daa66219", "rated_matches": 34, "raw_elo_rating": 1461.0913426668806, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 40.72988850257243, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 4, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 4, "generated_at": "2026-07-02T16:51:45Z", "losses": 24, "model": "mistralai/mistral-medium-3-5", "point_rating_method": "sequential_elo", "public_id": "E-99c7b0d758665b66", "rated_matches": 32, "raw_elo_rating": 1298.752594032639, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 19.535500553304832, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 6, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 6, "generated_at": "2026-07-02T16:51:45Z", "losses": 40, "model": "mistralai/mistral-medium-3-5", "point_rating_method": "sequential_elo", "public_id": "E-a0a38f5e77e983bc", "rated_matches": 67, "raw_elo_rating": 1404.142971092423, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 35.8499002021569, "uncertainty": 16.883906259083243, "unilateral_faults": 3, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 30, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 15, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 14, "model": "moonshotai/kimi-k2.7-code", "point_rating_method": "sequential_elo", "public_id": "E-4935e918b1e70ea1", "rated_matches": 30, "raw_elo_rating": 1510.753247793639, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 46.5884970123769, "uncertainty": 46.05265101338746, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 5, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 5, "generated_at": "2026-07-21T14:20:15Z", "losses": 16, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-2292c77f8fb54ff1", "rated_matches": 42, "raw_elo_rating": 1575.905025468466, "reasoning": "low", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "low", "repair_status": "first_pass", "score": 56.38821150296458, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 30, "capped_draws": 19, "coverage_status": "under_covered", "distinct_rated_opponents": 15, "draws": 19, "generated_at": "2026-07-24T14:00:00Z", "losses": 6, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-6cc4477cf8936e55", "rated_matches": 30, "raw_elo_rating": 1505.7500994571997, "reasoning": "high", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 45.94332605423027, "uncertainty": 46.05265101338746, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 1, "generated_at": "2026-07-17T22:36:00Z", "losses": 22, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-c89e5a24623ed70c", "rated_matches": 46, "raw_elo_rating": 1534.6956612737772, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "score": 51.41630854421455, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 16, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 16, "generated_at": "2026-07-17T22:36:00Z", "losses": 13, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-d2f6679f6ac952b3", "rated_matches": 42, "raw_elo_rating": 1489.127041295967, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "score": 45.19793061785928, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 5, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 5, "generated_at": "2026-07-24T14:00:00Z", "losses": 16, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-dbb89dcf5242a5a0", "rated_matches": 40, "raw_elo_rating": 1522.5986867020624, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "score": 49.3246287299255, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 30, "capped_draws": 11, "coverage_status": "under_covered", "distinct_rated_opponents": 15, "draws": 11, "generated_at": "2026-07-21T14:43:57Z", "losses": 6, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-ee608da1db5fc482", "rated_matches": 30, "raw_elo_rating": 1590.3751112138789, "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": 56.85597469999918, "uncertainty": 46.05265101338746, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 26, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 26, "generated_at": "2026-07-24T14:00:00Z", "losses": 5, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-fb8801908d28001f", "rated_matches": 42, "raw_elo_rating": 1579.431886642528, "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": 56.843010811301525, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 11, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 11, "generated_at": "2026-07-02T16:51:45Z", "losses": 17, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-0ce5e196701b51f3", "rated_matches": 44, "raw_elo_rating": 1552.6926849361364, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 53.57169863410424, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 16 }, { "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": 26, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-b851008baae8f441", "rated_matches": 66, "raw_elo_rating": 1514.38343795476, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 50.01923123018594, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 7, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 7, "generated_at": "2026-07-11T17:22:09Z", "losses": 20, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-ce064a9927030b28", "rated_matches": 32, "raw_elo_rating": 1351.6159358621478, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 26.352386762848873, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 7, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 7, "generated_at": "2026-07-02T16:51:45Z", "losses": 21, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-428923c2eb87dc7a", "rated_matches": 54, "raw_elo_rating": 1522.6714120111717, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 50.4344292839315, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 10, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 10, "generated_at": "2026-07-21T14:20:15Z", "losses": 18, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-fbf1a1af436a64a7", "rated_matches": 46, "raw_elo_rating": 1468.7292262906526, "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": 42.909739239921585, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 11, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 11, "generated_at": "2026-07-21T14:20:15Z", "losses": 18, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-55f6c0e3dc8a8065", "rated_matches": 42, "raw_elo_rating": 1401.3232146087823, "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": 33.87536426896172, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 18, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 18, "generated_at": "2026-07-02T16:51:45Z", "losses": 22, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-a3e0c8f8ea39b5ec", "rated_matches": 56, "raw_elo_rating": 1405.3393264056997, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 35.427216277491794, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 7, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 7, "generated_at": "2026-07-24T13:40:00Z", "losses": 31, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-8461eb1b16e40129", "rated_matches": 68, "raw_elo_rating": 1644.0015520281916, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 66.8258749095413, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 30 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 22, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 22, "generated_at": "2026-07-24T13:40:00Z", "losses": 24, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-c58ec61528547516", "rated_matches": 68, "raw_elo_rating": 1514.516696009371, "reasoning": "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": 50.12841502919046, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 22 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-ffd72d2c5c11728a", "rated_matches": 0, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "first_pass", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 30, "capped_draws": 7, "coverage_status": "under_covered", "distinct_rated_opponents": 15, "draws": 7, "generated_at": "2026-07-02T16:51:45Z", "losses": 14, "model": "qwen/qwen3.7-max", "point_rating_method": "sequential_elo", "public_id": "E-24581eb49b81bf8f", "rated_matches": 30, "raw_elo_rating": 1453.9243685520637, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 39.26024288014395, "uncertainty": 46.05265101338746, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 21, "coverage_status": "rated", "distinct_rated_opponents": 35, "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": 70, "raw_elo_rating": 1586.388491274526, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 59.484582777796334, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 31 }, { "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": 1494.5247005260037, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 45.70440415487458, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 18, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 18, "generated_at": "2026-07-03T18:55:00Z", "losses": 36, "model": "qwen/qwen3.7-plus", "point_rating_method": "sequential_elo", "public_id": "E-5e09f0c994a59f3c", "rated_matches": 70, "raw_elo_rating": 1372.448577341908, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 31.896390308583022, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 14, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 14, "generated_at": "2026-07-21T14:20:15Z", "losses": 26, "model": "stepfun/step-3.7-flash", "point_rating_method": "sequential_elo", "public_id": "E-09ecaa63c419b917", "rated_matches": 58, "raw_elo_rating": 1474.9655056194315, "reasoning": "low", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "low", "repair_status": "repaired", "score": 44.52251713937394, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 1, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 1, "generated_at": "2026-07-02T16:51:45Z", "losses": 28, "model": "stepfun/step-3.7-flash", "point_rating_method": "sequential_elo", "public_id": "E-4b0ce2bc67b08d8a", "rated_matches": 32, "raw_elo_rating": 1255.3105806304277, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 13.933522853305266, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 4, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 4, "generated_at": "2026-07-02T16:51:45Z", "losses": 19, "model": "tencent/hy3-preview", "point_rating_method": "sequential_elo", "public_id": "E-29e8870e43d717e5", "rated_matches": 38, "raw_elo_rating": 1536.8211359232482, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 50.9546838700397, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 76, "capped_draws": 15, "coverage_status": "rated", "distinct_rated_opponents": 38, "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": 76, "raw_elo_rating": 1686.569380601013, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 72.6465473220185, "uncertainty": 13.230288229818967, "unilateral_faults": 0, "wins": 46 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 13, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 13, "generated_at": "2026-07-24T13:40:00Z", "losses": 22, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-7382cf954e1b755d", "rated_matches": 62, "raw_elo_rating": 1458.1721573044606, "reasoning": "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": 42.57364447925613, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 27 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 33, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 33, "generated_at": "2026-07-24T13:40:00Z", "losses": 24, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-9e638fc0ac98df4f", "rated_matches": 64, "raw_elo_rating": 1361.1872095331362, "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": 30.167904978958862, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 26, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 26, "generated_at": "2026-07-24T13:40:00Z", "losses": 26, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-bc7c657b08ebac66", "rated_matches": 62, "raw_elo_rating": 1307.1395985619376, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 23.09754381568927, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 22, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 22, "generated_at": "2026-07-24T13:40:00Z", "losses": 27, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-c9890f6abafaf54f", "rated_matches": 62, "raw_elo_rating": 1301.5360292948533, "reasoning": "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": 22.3749467807873, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 5, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 5, "generated_at": "2026-07-17T22:36:00Z", "losses": 8, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-098480b7039ef18d", "rated_matches": 32, "raw_elo_rating": 1626.391326237206, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 61.78549606968857, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 8, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 8, "generated_at": "2026-07-24T14:00:00Z", "losses": 6, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-1c8e452ede41ea2e", "rated_matches": 32, "raw_elo_rating": 1671.8010064527873, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 67.64121029675636, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 26, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 26, "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": 42, "raw_elo_rating": 1561.6048271216569, "reasoning": "low", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "low", "repair_status": "first_pass", "score": 54.54415810924417, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugin_count": 1, "attempted_matches": 76, "capped_draws": 7, "coverage_status": "rated", "distinct_rated_opponents": 38, "draws": 7, "generated_at": "2026-07-17T22:36:00Z", "losses": 37, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-abb31ae26e404d88", "rated_matches": 76, "raw_elo_rating": 1466.268081692571, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 44.23803521324939, "uncertainty": 13.230288229818967, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 6, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 6, "generated_at": "2026-07-24T14:00:00Z", "losses": 10, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-d709aeb6802f9289", "rated_matches": 72, "raw_elo_rating": 1812.526480046139, "reasoning": "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": 88.73019290150756, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 56 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 13, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 13, "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": 42, "raw_elo_rating": 1647.4292378462578, "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": 65.61147284310373, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 22 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 3, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 3, "generated_at": "2026-07-17T22:36:00Z", "losses": 14, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-f9b8636a677996e4", "rated_matches": 34, "raw_elo_rating": 1582.217568421379, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 56.3494779833692, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 12, "coverage_status": "rated", "distinct_rated_opponents": 31, "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": 62, "raw_elo_rating": 1625.8640214601994, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 64.19801245627039, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 30 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 5, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 5, "generated_at": "2026-07-02T16:51:45Z", "losses": 16, "model": "x-ai/grok-build-0.1", "point_rating_method": "sequential_elo", "public_id": "E-f1ded648f3ab17dc", "rated_matches": 40, "raw_elo_rating": 1516.557076145994, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 48.545544959248915, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 3, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 3, "generated_at": "2026-07-02T16:51:45Z", "losses": 16, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-1208f50b0908ecb4", "rated_matches": 38, "raw_elo_rating": 1508.73482689852, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 47.33287022675642, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 4, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 4, "generated_at": "2026-07-02T06:10:40Z", "losses": 18, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-2a71bee21bd7c0b9", "rated_matches": 36, "raw_elo_rating": 1488.9872818158133, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 44.56607045433817, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 3, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 3, "generated_at": "2026-07-02T06:10:40Z", "losses": 28, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-2cdd8ae895784956", "rated_matches": 66, "raw_elo_rating": 1603.4984396054735, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 61.51087751648144, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 35 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 33, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 33, "generated_at": "2026-07-02T06:10:40Z", "losses": 11, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-8478c64d84536b61", "rated_matches": 44, "raw_elo_rating": 1306.1499854705874, "reasoning": "highest", "reasoning_bracket": "highest", "reasoning_setting": "highest", "repair_status": "repaired", "score": 21.77927935287923, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 80, "capped_draws": 24, "coverage_status": "rated", "distinct_rated_opponents": 40, "draws": 24, "generated_at": "2026-07-02T16:51:45Z", "losses": 29, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-912a4a40bbdcbd45", "rated_matches": 80, "raw_elo_rating": 1464.210701481668, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 44.11970871031872, "uncertainty": 11.805555555555554, "unilateral_faults": 0, "wins": 27 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 27, "coverage_status": "rated", "distinct_rated_opponents": 37, "draws": 27, "generated_at": "2026-07-01T00:15:48Z", "losses": 32, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-a168350bd057f924", "rated_matches": 74, "raw_elo_rating": 1407.0915273332496, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 36.5291806942871, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 80, "capped_draws": 26, "coverage_status": "rated", "distinct_rated_opponents": 40, "draws": 26, "generated_at": "2026-07-02T16:51:45Z", "losses": 30, "model": "xiaomi/mimo-v2.5-pro", "point_rating_method": "sequential_elo", "public_id": "E-9ce4191c7f1f3b3e", "rated_matches": 80, "raw_elo_rating": 1431.0064719759512, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 39.837923897204504, "uncertainty": 11.805555555555554, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 34, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 34, "generated_at": "2026-07-11T14:00:45Z", "losses": 11, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-5ab5088af70c19d6", "rated_matches": 58, "raw_elo_rating": 1468.7686993741677, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 43.72342041989681, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 13 }, { "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": 1525.552950569837, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 50.39247705958617, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 13, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 13, "generated_at": "2026-07-11T14:00:45Z", "losses": 23, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-5c3b7f5666a38043", "rated_matches": 48, "raw_elo_rating": 1450.5055406161034, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 40.71488884305701, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 8, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 8, "generated_at": "2026-07-02T06:10:40Z", "losses": 13, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-6a7eb114b16dc845", "rated_matches": 44, "raw_elo_rating": 1565.718530617541, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 55.25142043602127, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 34, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 34, "generated_at": "2026-07-03T18:27:00Z", "losses": 17, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-88bed07a2e526eed", "rated_matches": 62, "raw_elo_rating": 1527.6648692331044, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 51.53493775386614, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 34, "coverage_status": "rated", "distinct_rated_opponents": 23, "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": 46, "raw_elo_rating": 1468.3050824237796, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 42.85504461833912, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 1, "generated_at": "2026-07-02T16:51:45Z", "losses": 25, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-c8076ea61de8da45", "rated_matches": 44, "raw_elo_rating": 1373.8053371881217, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 30.503639526939683, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 3, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 3, "generated_at": "2026-07-11T17:22:09Z", "losses": 18, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-f889d782e3cce209", "rated_matches": 46, "raw_elo_rating": 1449.2185211300243, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 40.39377539153461, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 25 } ], "GB2-02": [ { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 30, "generated_at": "2026-07-02T16:51:45Z", "losses": 9, "model": "claude-fable-5", "point_rating_method": "sequential_elo", "public_id": "E-cd3608270e8c00fd", "rated_matches": 60, "raw_elo_rating": 1624.69812777023, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 63.452640140055266, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "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": 60, "raw_elo_rating": 1665.515391796302, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 73.19703425601392, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 30 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 31, "losses": 4, "model": "claude-opus-4-5", "point_rating_method": "sequential_elo", "public_id": "E-03472a04778e9928", "rated_matches": 36, "raw_elo_rating": 1481.959800682918, "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": 25.904087261497683, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 0, "model": "claude-opus-4-5", "point_rating_method": "sequential_elo", "public_id": "E-0454dbb9530f84f7", "rated_matches": 0, "reasoning": "legacy_shared_thinking_budget", "reasoning_bracket": "highest", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "budget", "reasoning_setting": "legacy_shared_thinking_budget", "repair_status": "first_pass", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 54, "generated_at": "2026-07-02T16:51:45Z", "losses": 5, "model": "claude-opus-4-5", "point_rating_method": "sequential_elo", "public_id": "E-16462f3d1f3a7b19", "rated_matches": 62, "raw_elo_rating": 1505.4621431048597, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 35.18281284883366, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 0, "model": "claude-opus-4-5", "point_rating_method": "sequential_elo", "public_id": "E-3cbd11fb314c75e1", "rated_matches": 0, "reasoning": "legacy_shared_thinking_budget", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "budget", "reasoning_setting": "legacy_shared_thinking_budget", "repair_status": "first_pass", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 31, "losses": 3, "model": "claude-opus-4-5", "point_rating_method": "sequential_elo", "public_id": "E-63fde27ceab11930", "rated_matches": 34, "raw_elo_rating": 1461.147572391836, "reasoning": "legacy_shared_thinking_budget", "reasoning_bracket": "intensive", "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "legacy_shared_thinking_budget", "repair_status": "first_pass", "score": 20.493228839441244, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 20, "generated_at": "2026-07-03T17:20:00Z", "losses": 3, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-a81bd03e764818f6", "rated_matches": 58, "raw_elo_rating": 1737.1613209336665, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 90.09571894996164, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 35 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 54, "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": 64, "raw_elo_rating": 1478.0802986534875, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 28.832423610551896, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 41, "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": 46, "raw_elo_rating": 1476.4547971192335, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 26.35973023478462, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 22, "generated_at": "2026-07-25T10:50:00Z", "losses": 10, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-50b401cafe71e710", "rated_matches": 52, "raw_elo_rating": 1643.4265617903695, "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": 67.0333745447079, "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": 17, "generated_at": "2026-07-25T10:50:00Z", "losses": 11, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-51ddad48e10b006f", "rated_matches": 52, "raw_elo_rating": 1650.621303202366, "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": 68.75099079248285, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 24 }, { "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": 1655.6035207934715, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 68.14388017555835, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 33, "generated_at": "2026-07-25T10:50:00Z", "losses": 4, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-772d1a710082ddb3", "rated_matches": 52, "raw_elo_rating": 1584.041640885369, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 52.85628336403163, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 25, "generated_at": "2026-07-25T10:50:00Z", "losses": 7, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-8a5bf2e23121edf6", "rated_matches": 50, "raw_elo_rating": 1624.2203382943308, "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": 62.19350916040092, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 18 }, { "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": 1742.7134166182843, "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": 88.93981485101536, "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": 52, "generated_at": "2026-07-02T16:51:45Z", "losses": 3, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-a1a16bb5799cfdbe", "rated_matches": 56, "raw_elo_rating": 1489.0475371244402, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 30.6467494525862, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 39, "generated_at": "2026-07-03T16:50:00Z", "losses": 10, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-e35d82f3fd09a1f4", "rated_matches": 56, "raw_elo_rating": 1527.1746719119114, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 39.748923171140326, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 35, "generated_at": "2026-07-02T16:51:45Z", "losses": 3, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-e501d6808bd19ccc", "rated_matches": 38, "raw_elo_rating": 1479.0637410889549, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 25.620538806917818, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 32, "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": 38, "raw_elo_rating": 1450.9053103013168, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 18.89821545113325, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 52, "generated_at": "2026-07-02T16:51:45Z", "losses": 2, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-12dcb25370550495", "rated_matches": 58, "raw_elo_rating": 1476.913822136368, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 27.966268177526015, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 38, "generated_at": "2026-07-01T00:15:48Z", "losses": 0, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-1e168b9e73c26073", "rated_matches": 38, "raw_elo_rating": 1493.436723483075, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 29.05183211899724, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 67, "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": 70, "raw_elo_rating": 1498.6255036896976, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 34.248739162857234, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 52, "generated_at": "2026-07-02T06:10:40Z", "losses": 0, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-bc9a8c3886a48505", "rated_matches": 52, "raw_elo_rating": 1493.295680760276, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 31.192303158862845, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 52, "generated_at": "2026-07-02T06:10:40Z", "losses": 6, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-f2e6dd87c5656ee3", "rated_matches": 60, "raw_elo_rating": 1490.5117813480674, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 31.418042140470977, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 51, "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": 54, "raw_elo_rating": 1493.1855742024472, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 31.406715690809293, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 34, "generated_at": "2026-07-02T16:51:45Z", "losses": 3, "model": "google/gemini-3.1-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-20b3484be872df52", "rated_matches": 38, "raw_elo_rating": 1492.955126495349, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 28.936859423853782, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-21T14:20:15Z", "losses": 0, "model": "google/gemini-3.5-flash", "point_rating_method": "sequential_elo", "public_id": "E-cbf88e49a4581eb0", "rated_matches": 0, "reasoning": "low", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "low", "repair_status": "repaired", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 47, "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": 56, "raw_elo_rating": 1497.501056091277, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 32.664876400707286, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-1010911d64a09b68", "rated_matches": 0, "reasoning": "minimal", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "minimal", "repair_status": "repaired", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 57, "generated_at": "2026-07-24T13:40:00Z", "losses": 3, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-60dfb882a81b3944", "rated_matches": 64, "raw_elo_rating": 1490.4414707801473, "reasoning": "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": 31.783433086846944, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-939a2dc80becc700", "rated_matches": 0, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-a3da6c33bd873fb7", "rated_matches": 0, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-e65fdcb71f09a611", "rated_matches": 0, "reasoning": "minimal", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "minimal", "repair_status": "repaired", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 63, "generated_at": "2026-07-24T13:40:00Z", "losses": 1, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-f2b9f6de4830b5f8", "rated_matches": 64, "raw_elo_rating": 1482.1184189823184, "reasoning": "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": 29.79645284942148, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-4492f6d65cd6280b", "rated_matches": 0, "reasoning": "minimal", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "minimal", "repair_status": "first_pass", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 62, "generated_at": "2026-07-24T13:40:00Z", "losses": 4, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-62275b0c39dda32a", "rated_matches": 66, "raw_elo_rating": 1470.8519879795908, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 27.284915215803313, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-9c8b43dc41bad760", "rated_matches": 0, "reasoning": "minimal", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "minimal", "repair_status": "repaired", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 61, "generated_at": "2026-07-24T13:40:00Z", "losses": 1, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-e49b9c0097a352eb", "rated_matches": 62, "raw_elo_rating": 1481.8613724353104, "reasoning": "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": 29.548549594502184, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 31, "generated_at": "2026-07-02T16:51:45Z", "losses": 10, "model": "gpt-4.1", "point_rating_method": "sequential_elo", "public_id": "E-e4707b8e4c581ede", "rated_matches": 44, "raw_elo_rating": 1462.3741079493293, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 22.69204681390362, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-21T14:20:15Z", "losses": 0, "model": "gpt-5", "point_rating_method": "sequential_elo", "public_id": "E-4f8f0a47f75ab6b7", "rated_matches": 0, "reasoning": "low", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "low", "repair_status": "first_pass", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 25, "generated_at": "2026-07-02T16:51:45Z", "losses": 9, "model": "gpt-5", "point_rating_method": "sequential_elo", "public_id": "E-5bccb9b671ce5eae", "rated_matches": 38, "raw_elo_rating": 1485.9869743562572, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 27.27333732546178, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 37, "generated_at": "2026-07-02T16:51:45Z", "losses": 7, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-4aa582caf9d9f6da", "rated_matches": 64, "raw_elo_rating": 1597.2143177522778, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 57.273546807227696, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 64, "generated_at": "2026-07-02T16:51:45Z", "losses": 1, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-98ddce22d3eb5886", "rated_matches": 66, "raw_elo_rating": 1488.7746335763547, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 31.56362733585045, "uncertainty": 17.33472217815261, "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": 1461.361568758212, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 25.189567064800336, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 49, "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": 56, "raw_elo_rating": 1495.695527099591, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 32.233838542032025, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 59, "generated_at": "2026-07-02T16:51:45Z", "losses": 1, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-322cbb8be1559087", "rated_matches": 60, "raw_elo_rating": 1485.6404248008662, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 30.2550926089942, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 54, "generated_at": "2026-07-01T00:15:48Z", "losses": 4, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-4f2717a1b63468f4", "rated_matches": 58, "raw_elo_rating": 1481.5576254050702, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 29.074893420469955, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 49, "generated_at": "2026-07-02T16:51:45Z", "losses": 5, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-59f362f57892ab54", "rated_matches": 56, "raw_elo_rating": 1486.3448735458198, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 30.001536704958095, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 48, "generated_at": "2026-07-02T16:51:45Z", "losses": 2, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-6724998b59176607", "rated_matches": 50, "raw_elo_rating": 1479.6499174077858, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 27.67989850465793, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 56, "generated_at": "2026-07-02T06:10:40Z", "losses": 3, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-7ef67fa468b6c12c", "rated_matches": 60, "raw_elo_rating": 1475.6820234756003, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 27.877701826106545, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 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": 1501.07775493319, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 33.94047996889768, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 52, "generated_at": "2026-07-01T00:15:48Z", "losses": 2, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-dd45dfa7984ab9fa", "rated_matches": 56, "raw_elo_rating": 1509.288358746711, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 35.47888477141212, "uncertainty": 22.47661785325219, "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": "2026-07-09T17:30:50Z", "losses": 2, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-038a95fb13c8aa94", "rated_matches": 52, "raw_elo_rating": 1496.4171488213428, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 31.93749801043312, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 58, "generated_at": "2026-07-09T17:30:50Z", "losses": 4, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-1ce420518fc32de1", "rated_matches": 62, "raw_elo_rating": 1469.783695669112, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 26.665219581500377, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 56, "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": 58, "raw_elo_rating": 1476.3347652037166, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 27.828028657999937, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 59, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 51, "generated_at": "2026-07-01T00:15:48Z", "losses": 6, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-6a4ccfcf11c5e3f3", "rated_matches": 59, "raw_elo_rating": 1480.6077266300342, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 28.95215826651564, "uncertainty": 20.79972243679028, "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": 1501.0844310212506, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 34.672692270295386, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 45, "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": 48, "raw_elo_rating": 1476.1930545086254, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 26.58447194893014, "uncertainty": 27.67857142857143, "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": 1493.389893096581, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 33.30518228882905, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 6 }, { "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": 7, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-be95cc83ce87847c", "rated_matches": 56, "raw_elo_rating": 1441.841398262491, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 19.377125367304995, "uncertainty": 22.47661785325219, "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": "2026-07-02T16:51:45Z", "losses": 3, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-d96eaa4f1d20c47b", "rated_matches": 60, "raw_elo_rating": 1484.5501961174168, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 29.99481994688565, "uncertainty": 20.268439966447993, "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": "2026-07-02T16:51:45Z", "losses": 2, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-51e935956fa76015", "rated_matches": 70, "raw_elo_rating": 1501.6155054033272, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 34.962548767694756, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 31, "generated_at": "2026-07-02T16:51:45Z", "losses": 12, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-8460841e3919c568", "rated_matches": 58, "raw_elo_rating": 1535.714251788026, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 42.00382249149155, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 64, "generated_at": "2026-07-10T05:30:29Z", "losses": 6, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-a30e455ba172d80e", "rated_matches": 70, "raw_elo_rating": 1473.0639451591423, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 28.146372762679754, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 62, "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": 62, "raw_elo_rating": 1488.2182531123694, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 31.0661415287832, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 52, "generated_at": "2026-07-10T05:30:29Z", "losses": 0, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-e2dda893ae4363f2", "rated_matches": 52, "raw_elo_rating": 1491.189585591546, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 30.68951048376554, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 46, "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": 58, "raw_elo_rating": 1500.5716831996058, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 33.61416074557098, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 6 }, { "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": 11, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-087d760c91df7f17", "rated_matches": 60, "raw_elo_rating": 1552.434703520284, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 46.201035877446856, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 22 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 11, "generated_at": "2026-07-10T05:30:29Z", "losses": 4, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-33dc9365cfacf9c0", "rated_matches": 58, "raw_elo_rating": 1778.6483184624055, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 100.0, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 43 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 37, "generated_at": "2026-07-10T05:30:29Z", "losses": 10, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-1b12482867c807c9", "rated_matches": 60, "raw_elo_rating": 1549.3008269640052, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 45.45287871885732, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 52, "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": 54, "raw_elo_rating": 1487.5622315860544, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 30.06424289135372, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 63, "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": 68, "raw_elo_rating": 1476.5798481424442, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 28.82265996372679, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "inclusionai/ling-3.0-flash", "point_rating_method": "sequential_elo", "public_id": "E-129026c5e53b35ad", "rated_matches": 0, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 60, "generated_at": "2026-07-24T13:40:00Z", "losses": 2, "model": "inclusionai/ling-3.0-flash", "point_rating_method": "sequential_elo", "public_id": "E-fc495094a55d2f94", "rated_matches": 62, "raw_elo_rating": 1472.6963835500655, "reasoning": "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": 27.360571887099717, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-a00d8e3eb7dd07cf", "rated_matches": 0, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 63, "generated_at": "2026-07-24T13:40:00Z", "losses": 1, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-a0c74818516a7f27", "rated_matches": 64, "raw_elo_rating": 1480.4728086634052, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 29.40359272291873, "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": 59, "generated_at": "2026-07-02T16:51:45Z", "losses": 1, "model": "minimax/minimax-m3", "point_rating_method": "sequential_elo", "public_id": "E-1e46941293882535", "rated_matches": 60, "raw_elo_rating": 1474.9611713998297, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 27.705611244015376, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 28, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 14, "draws": 26, "generated_at": "2026-07-02T16:51:45Z", "losses": 2, "model": "minimax/minimax-m3", "point_rating_method": "sequential_elo", "public_id": "E-cad87bcb23d33fef", "rated_matches": 28, "raw_elo_rating": 1466.6107290752293, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 20.206120407054794, "uncertainty": 49.09766908852594, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 25, "generated_at": "2026-07-02T16:51:45Z", "losses": 5, "model": "moonshotai/kimi-k2.7-code", "point_rating_method": "sequential_elo", "public_id": "E-85c8a9372a607001", "rated_matches": 32, "raw_elo_rating": 1459.7262189302294, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 19.671972150014987, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 28, "generated_at": "2026-07-24T14:00:00Z", "losses": 8, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-1beeecccf3f2c84f", "rated_matches": 40, "raw_elo_rating": 1493.0353624600734, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "score": 29.333630559260232, "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": 1478.1200909901734, "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": 26.123829983792792, "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": 22, "generated_at": "2026-07-18T00:14:00Z", "losses": 6, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-97d6a124a1509fc1", "rated_matches": 32, "raw_elo_rating": 1497.4607645377262, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "score": 28.680422200738533, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 30, "generated_at": "2026-07-17T22:36:00Z", "losses": 3, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-b0de9fa15f139d69", "rated_matches": 34, "raw_elo_rating": 1466.8816147147952, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "score": 21.862129220339213, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 30, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 15, "draws": 24, "generated_at": "2026-07-21T14:43:57Z", "losses": 3, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-be8e56a3b58c5bcc", "rated_matches": 30, "raw_elo_rating": 1513.5650622210796, "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": 31.99718539096118, "uncertainty": 46.05265101338746, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 35, "generated_at": "2026-07-24T14:00:00Z", "losses": 0, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-d3d3da42e99695b1", "rated_matches": 36, "raw_elo_rating": 1507.2663480895285, "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": 31.945574302047177, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 38, "generated_at": "2026-07-21T14:20:15Z", "losses": 1, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-fc3ad6db6543001f", "rated_matches": 42, "raw_elo_rating": 1524.5527886295524, "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": 37.20880876571812, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 47, "generated_at": "2026-07-11T17:22:09Z", "losses": 5, "model": "nex-agi/nex-n2-pro", "point_rating_method": "sequential_elo", "public_id": "E-811f47e902ce0d21", "rated_matches": 54, "raw_elo_rating": 1471.4715871938947, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 26.222888398882304, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 33, "generated_at": "2026-07-02T16:51:45Z", "losses": 6, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-2404d10bab26a254", "rated_matches": 40, "raw_elo_rating": 1470.471675440953, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 23.94695253784734, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 29, "generated_at": "2026-07-11T17:22:09Z", "losses": 4, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-abd2cae3e3ff9bdb", "rated_matches": 34, "raw_elo_rating": 1473.203828704759, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 23.37144510109701, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 54, "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": 56, "raw_elo_rating": 1478.792058417232, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 28.19843674091044, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 34, "generated_at": "2026-07-21T14:20:15Z", "losses": 1, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-e48b0ea99dfc517c", "rated_matches": 36, "raw_elo_rating": 1477.5847832126149, "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": 24.85962983613944, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 41, "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": 42, "raw_elo_rating": 1490.3396386261843, "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": 29.041029137757743, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 50, "generated_at": "2026-07-02T16:51:45Z", "losses": 3, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-8f0c6569aa132f8e", "rated_matches": 54, "raw_elo_rating": 1485.1407076693067, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 29.486147225977007, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 28, "generated_at": "2026-07-02T16:51:45Z", "losses": 4, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-e5b4a3586049e1c9", "rated_matches": 32, "raw_elo_rating": 1451.3652894673198, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 17.675949295316034, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-7164ee63b9dd911a", "rated_matches": 0, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "first_pass", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-ba56689188a301b2", "rated_matches": 0, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 60, "generated_at": "2026-07-24T13:40:00Z", "losses": 2, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-d8c7a78cc7f666dc", "rated_matches": 64, "raw_elo_rating": 1477.5865175875335, "reasoning": "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": 28.71454218394329, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 50, "generated_at": "2026-07-02T16:51:45Z", "losses": 1, "model": "qwen/qwen3.7-max", "point_rating_method": "sequential_elo", "public_id": "E-5f64c2ae9860ba38", "rated_matches": 54, "raw_elo_rating": 1502.383120170803, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 33.60246582139271, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 3 }, { "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": 1503.013853532559, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 30.93036703796877, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 58, "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": 58, "raw_elo_rating": 1495.3686744490708, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 32.37203516308192, "uncertainty": 21.344455490411935, "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": 2, "model": "qwen/qwen3.7-plus", "point_rating_method": "sequential_elo", "public_id": "E-57293d5b71f14882", "rated_matches": 32, "raw_elo_rating": 1497.9406642377191, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 28.794989698694177, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 51, "generated_at": "2026-07-02T16:51:45Z", "losses": 4, "model": "stepfun/step-3.7-flash", "point_rating_method": "sequential_elo", "public_id": "E-0ccea44addccfff0", "rated_matches": 56, "raw_elo_rating": 1495.901542637513, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 32.28302107896658, "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": 62, "generated_at": "2026-07-02T16:51:45Z", "losses": 6, "model": "tencent/hy3-preview", "point_rating_method": "sequential_elo", "public_id": "E-d910e47dd13c2c71", "rated_matches": 68, "raw_elo_rating": 1465.8989139702087, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 26.272777344588157, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 27, "generated_at": "2026-07-02T16:51:45Z", "losses": 5, "model": "tencent/hy3-preview", "point_rating_method": "sequential_elo", "public_id": "E-fbf6af15f65f01d7", "rated_matches": 32, "raw_elo_rating": 1440.1817737672786, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 15.006084296192038, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 63, "generated_at": "2026-07-24T13:40:00Z", "losses": 5, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-63e0985794df5d5b", "rated_matches": 68, "raw_elo_rating": 1476.6106392697473, "reasoning": "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": 28.830010796441194, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 64, "generated_at": "2026-07-24T13:40:00Z", "losses": 1, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-66a4f0abd099d8f1", "rated_matches": 66, "raw_elo_rating": 1498.8766895584683, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 33.97531310705538, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-9468e854340a4e9b", "rated_matches": 0, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 16, "generated_at": "2026-07-24T14:00:00Z", "losses": 7, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-0576181f89efa7a7", "rated_matches": 32, "raw_elo_rating": 1529.5895530689522, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 36.350597686204246, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 30, "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": 56, "raw_elo_rating": 1582.8999468560062, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 53.052339121032695, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 18 }, { "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": 1479.3226256551393, "reasoning": "low", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "low", "repair_status": "repaired", "score": 26.059959111062756, "uncertainty": 34.33688094430304, "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": "2026-07-24T14:00:00Z", "losses": 1, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-1b0da3150a77b47b", "rated_matches": 40, "raw_elo_rating": 1496.3929521312668, "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": 30.135195235787354, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 23, "generated_at": "2026-07-17T22:36:00Z", "losses": 6, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-8728b59f87c3369e", "rated_matches": 34, "raw_elo_rating": 1498.4661201948384, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 29.402366830547656, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 78, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 39, "draws": 52, "generated_at": "2026-07-24T14:00:00Z", "losses": 13, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-da5ea0258e71b6ab", "rated_matches": 78, "raw_elo_rating": 1506.035891887915, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 36.60696862445656, "uncertainty": 12.5043950463012, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 28, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 14, "draws": 25, "generated_at": "2026-07-02T16:51:45Z", "losses": 2, "model": "x-ai/grok-build-0.1", "point_rating_method": "sequential_elo", "public_id": "E-99592fa0331c6679", "rated_matches": 28, "raw_elo_rating": 1495.6428182083175, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 27.13701411766091, "uncertainty": 49.09766908852594, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 57, "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": 60, "raw_elo_rating": 1468.175080615072, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 26.085553048269652, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 28, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 14, "draws": 26, "generated_at": "2026-07-02T16:51:45Z", "losses": 1, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-5b213ae773e821cc", "rated_matches": 28, "raw_elo_rating": 1492.9613856719243, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 26.49686990286792, "uncertainty": 49.09766908852594, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 33, "generated_at": "2026-07-02T06:10:40Z", "losses": 3, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-9077f1e8e006290b", "rated_matches": 38, "raw_elo_rating": 1483.4827683360977, "reasoning": "highest", "reasoning_bracket": "highest", "reasoning_setting": "highest", "repair_status": "repaired", "score": 26.675502781911693, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 28, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 14, "draws": 25, "generated_at": "2026-07-01T00:15:48Z", "losses": 3, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-a5f372b0e5962ee5", "rated_matches": 28, "raw_elo_rating": 1464.5709945048668, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 19.71917014177337, "uncertainty": 49.09766908852594, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 27, "generated_at": "2026-07-02T06:10:40Z", "losses": 3, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-c37f25e181320efb", "rated_matches": 32, "raw_elo_rating": 1484.681792494128, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 25.629670442607463, "uncertainty": 43.288827977848925, "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": 1477.3293696473902, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 28.65315269754207, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 38, "generated_at": "2026-07-11T17:22:09Z", "losses": 2, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-32435b01ac08ed41", "rated_matches": 40, "raw_elo_rating": 1470.374121179378, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 23.923663197046043, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 55, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 45, "generated_at": "2026-07-11T14:00:45Z", "losses": 7, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-4442c0e8a06187bf", "rated_matches": 55, "raw_elo_rating": 1479.8621657148212, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 28.34147388545191, "uncertainty": 23.065310478106092, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 35, "generated_at": "2026-07-02T16:51:45Z", "losses": 3, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-4959351a96fd2b82", "rated_matches": 38, "raw_elo_rating": 1467.0041051022636, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 22.741515708401067, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 37, "generated_at": "2026-07-11T14:00:45Z", "losses": 1, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-925b589068dc7268", "rated_matches": 38, "raw_elo_rating": 1485.7980200777038, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 27.22822786004183, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 56, "generated_at": "2026-07-02T16:51:45Z", "losses": 4, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-98394109d97d67ee", "rated_matches": 60, "raw_elo_rating": 1469.9243196020857, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 26.50315267184008, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 31, "generated_at": "2026-07-01T00:15:48Z", "losses": 4, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-b090ee9c8b9921ad", "rated_matches": 38, "raw_elo_rating": 1489.347643659299, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 28.07563720919052, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 45, "generated_at": "2026-07-02T06:10:40Z", "losses": 8, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-dd5764d86cd88052", "rated_matches": 60, "raw_elo_rating": 1498.5754889140435, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 33.34310856600406, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 7 } ], "GB2-03": [ { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 20, "generated_at": "2026-07-03T17:50:00Z", "losses": 4, "model": "claude-fable-5", "point_rating_method": "sequential_elo", "public_id": "E-04fa5b762ca703f0", "rated_matches": 42, "raw_elo_rating": 1640.207188118948, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 69.09760234044293, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 9, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 37, "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": 54, "raw_elo_rating": 1544.092140040724, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 54.1033903036507, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 0, "model": "claude-opus-4-5", "point_rating_method": "sequential_elo", "public_id": "E-cef4890e88806969", "rated_matches": 0, "reasoning": "legacy_shared_thinking_budget", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "budget", "reasoning_setting": "legacy_shared_thinking_budget", "repair_status": "first_pass", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 20, "capped_draws": 1, "coverage_status": "under_covered", "distinct_rated_opponents": 10, "draws": 4, "losses": 8, "model": "claude-opus-4-5", "point_rating_method": "sequential_elo", "public_id": "E-d5810442d7094396", "rated_matches": 20, "raw_elo_rating": 1470.7017633076605, "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": 36.13060620307745, "uncertainty": 65.3589451179962, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 22, "capped_draws": 3, "coverage_status": "under_covered", "distinct_rated_opponents": 11, "draws": 11, "losses": 6, "model": "claude-opus-4-5", "point_rating_method": "sequential_elo", "public_id": "E-dfb18dba94eee30b", "rated_matches": 22, "raw_elo_rating": 1509.14127488884, "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": 43.256458127648266, "uncertainty": 60.5072070285374, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 5, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 23, "generated_at": "2026-07-02T16:51:45Z", "losses": 10, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-823b961281482cd1", "rated_matches": 40, "raw_elo_rating": 1460.7826005116174, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 38.6391638686108, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 1, "generated_at": "2026-07-25T15:48:00Z", "losses": 2, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-38759212c025e8eb", "rated_matches": 40, "raw_elo_rating": 1825.2086317117496, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 100.0, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 37 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 4, "generated_at": "2026-07-25T15:48:00Z", "losses": 15, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-49aaba66f6b19080", "rated_matches": 42, "raw_elo_rating": 1584.5474115941763, "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": 59.72579535069838, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 0, "generated_at": "2026-07-25T15:48:00Z", "losses": 4, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-7caa6c5081d57676", "rated_matches": 40, "raw_elo_rating": 1813.538468676055, "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": 98.03501698464945, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 36 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 0, "generated_at": "2026-07-25T15:48:00Z", "losses": 9, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-bd02f4c2907d0a7c", "rated_matches": 40, "raw_elo_rating": 1762.0128566539547, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 89.35930678511835, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 31 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "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": 42, "raw_elo_rating": 1798.366804655625, "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": 95.72798953026684, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 36 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 8, "generated_at": "2026-07-25T15:48:00Z", "losses": 15, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-ecf847457e616425", "rated_matches": 40, "raw_elo_rating": 1469.8145918606804, "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": 40.15994036002895, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 1, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 18, "generated_at": "2026-07-19T15:25:00Z", "losses": 7, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-1c251b669239429c", "rated_matches": 38, "raw_elo_rating": 1574.8313346483474, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 57.57597731707655, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 3, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 10, "generated_at": "2026-07-03T16:50:00Z", "losses": 25, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-2e43b0d163a7f12d", "rated_matches": 38, "raw_elo_rating": 1321.3059497167385, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 14.888221042628048, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 2, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 18, "generated_at": "2026-07-19T15:25:00Z", "losses": 12, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-d49e8df479ed0377", "rated_matches": 48, "raw_elo_rating": 1537.466076513104, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 52.44775415955655, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 4, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 13, "generated_at": "2026-07-02T16:51:45Z", "losses": 15, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-e7d1e6857fc48e7a", "rated_matches": 38, "raw_elo_rating": 1485.2660520172667, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 42.495274622791904, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugin_count": 1, "attempted_matches": 22, "capped_draws": 1, "coverage_status": "under_covered", "distinct_rated_opponents": 11, "draws": 11, "generated_at": "2026-07-02T16:51:45Z", "losses": 8, "model": "cohere/north-mini-code", "point_rating_method": "sequential_elo", "public_id": "E-0f669ae82234cf76", "rated_matches": 22, "raw_elo_rating": 1447.213610903655, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 32.829285213351575, "uncertainty": 60.5072070285374, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 30, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 15, "draws": 9, "generated_at": "2026-07-01T00:15:48Z", "losses": 9, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-32e04fe5ad231857", "rated_matches": 30, "raw_elo_rating": 1546.3471653061004, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 51.468109335875496, "uncertainty": 46.05265101338746, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 2, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 20, "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": 50, "raw_elo_rating": 1449.5908015255636, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 37.84215337762568, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 32, "generated_at": "2026-07-02T16:51:45Z", "losses": 21, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-ae9d59ec3a8a1d63", "rated_matches": 72, "raw_elo_rating": 1484.593650623879, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 45.2839963442032, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 15, "generated_at": "2026-07-02T16:51:45Z", "losses": 30, "model": "deepseek/deepseek-v4-pro", "point_rating_method": "sequential_elo", "public_id": "E-f82a334a0fd1fb8e", "rated_matches": 54, "raw_elo_rating": 1345.207385463267, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 20.61584059577335, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 18, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 9, "draws": 13, "generated_at": "2026-07-02T16:51:45Z", "losses": 1, "model": "google/gemini-3.5-flash", "point_rating_method": "sequential_elo", "public_id": "E-46c3bb79de67d970", "rated_matches": 18, "raw_elo_rating": 1530.8652651817986, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 45.50655322042652, "uncertainty": 70.95786693528086, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 14, "generated_at": "2026-07-02T16:51:45Z", "losses": 13, "model": "google/gemini-3.5-flash", "point_rating_method": "sequential_elo", "public_id": "E-8ed795ea8fd1e0aa", "rated_matches": 50, "raw_elo_rating": 1585.7951447614212, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 60.77578508926699, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-21T14:20:15Z", "losses": 0, "model": "google/gemini-3.5-flash", "point_rating_method": "sequential_elo", "public_id": "E-d2c81e6c396a15b0", "rated_matches": 0, "reasoning": "low", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "low", "repair_status": "repaired", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-28274045fbc35ae9", "rated_matches": 0, "reasoning": "minimal", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "minimal", "repair_status": "repaired", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 3, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 21, "generated_at": "2026-07-24T13:40:00Z", "losses": 16, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-36e89f1dca2cd568", "rated_matches": 52, "raw_elo_rating": 1536.9370245972011, "reasoning": "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": 52.728872395868734, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-dc837629b72c2e03", "rated_matches": 0, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 17, "generated_at": "2026-07-24T13:40:00Z", "losses": 16, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-e51f710b50e975e5", "rated_matches": 50, "raw_elo_rating": 1500.157339213247, "reasoning": "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": 46.35637784882347, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-e9957a543416b0ad", "rated_matches": 0, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-6743f1c221046d65", "rated_matches": 0, "reasoning": "minimal", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "minimal", "repair_status": "first_pass", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-80b8c1a18d6dd238", "rated_matches": 0, "reasoning": "minimal", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "minimal", "repair_status": "first_pass", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 2, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 24, "generated_at": "2026-07-24T13:40:00Z", "losses": 12, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-9b5d467ecf278026", "rated_matches": 50, "raw_elo_rating": 1564.288669917894, "reasoning": "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": 57.154596794096086, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-ed24a723621c4481", "rated_matches": 0, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 3, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 13, "generated_at": "2026-07-24T13:40:00Z", "losses": 18, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-f44c7c8e627e08cd", "rated_matches": 54, "raw_elo_rating": 1551.625363472671, "reasoning": "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": 55.37180926655133, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 30, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 15, "draws": 10, "generated_at": "2026-07-02T16:51:45Z", "losses": 10, "model": "gpt-4.1", "point_rating_method": "sequential_elo", "public_id": "E-c7da9914f86ee846", "rated_matches": 30, "raw_elo_rating": 1528.356600835827, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 48.43891826866166, "uncertainty": 46.05265101338746, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-21T14:20:15Z", "losses": 0, "model": "gpt-5", "point_rating_method": "sequential_elo", "public_id": "E-c541923774f0cd7b", "rated_matches": 0, "reasoning": "low", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "low", "repair_status": "repaired", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 22, "capped_draws": 1, "coverage_status": "under_covered", "distinct_rated_opponents": 11, "draws": 7, "generated_at": "2026-07-02T16:51:45Z", "losses": 9, "model": "gpt-5", "point_rating_method": "sequential_elo", "public_id": "E-cc568b7069d5a0fd", "rated_matches": 21, "raw_elo_rating": 1451.1281633788087, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 33.172778902818145, "uncertainty": 62.850358177805205, "unilateral_faults": 1, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 26, "generated_at": "2026-07-02T16:51:45Z", "losses": 11, "model": "gpt-5", "point_rating_method": "sequential_elo", "public_id": "E-e724ba162431d43a", "rated_matches": 42, "raw_elo_rating": 1434.6445964503675, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 34.485660760472555, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 2, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 24, "generated_at": "2026-07-02T16:51:45Z", "losses": 19, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-496f83ad0bd69447", "rated_matches": 54, "raw_elo_rating": 1401.825348329168, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 30.14898379651178, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 7, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 14, "generated_at": "2026-07-02T16:51:45Z", "losses": 18, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-4b75acaf58f14113", "rated_matches": 44, "raw_elo_rating": 1459.0530820785134, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 38.82631568621353, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 2, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 29, "generated_at": "2026-07-02T16:51:45Z", "losses": 8, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-ebd456dc6b320c61", "rated_matches": 50, "raw_elo_rating": 1557.920108094656, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 56.08227965708637, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 55, "generated_at": "2026-07-02T16:51:45Z", "losses": 1, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-35117a2e624d7970", "rated_matches": 56, "raw_elo_rating": 1503.163188021814, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 47.37265857229025, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 7, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 18, "generated_at": "2026-07-01T00:15:48Z", "losses": 12, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-3e164d6fc6c16cbb", "rated_matches": 44, "raw_elo_rating": 1548.3116113141386, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 53.855368269859, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 13, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 25, "generated_at": "2026-07-02T06:10:40Z", "losses": 9, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-7cbcc752e71e2d3b", "rated_matches": 40, "raw_elo_rating": 1467.46537218358, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 39.764386608919374, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 9, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 34, "generated_at": "2026-07-02T16:51:45Z", "losses": 7, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-9e39bdd48b7328c7", "rated_matches": 52, "raw_elo_rating": 1526.9921431629089, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 51.054386525509535, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 21, "generated_at": "2026-07-01T00:15:48Z", "losses": 13, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-a51cd55f211305c2", "rated_matches": 48, "raw_elo_rating": 1519.4452930208924, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 49.41347491451111, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 20, "generated_at": "2026-07-02T06:10:40Z", "losses": 9, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-dfa5098ec9c3cf47", "rated_matches": 52, "raw_elo_rating": 1546.7025778967595, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 54.37316359475259, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 23 }, { "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": 1410.3860603587646, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 31.050446121101896, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 9, "generated_at": "2026-07-01T00:15:48Z", "losses": 25, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-0ecb5b73c09f13b2", "rated_matches": 50, "raw_elo_rating": 1415.921753576121, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 32.17307170658813, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 3, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 13, "generated_at": "2026-07-02T06:10:40Z", "losses": 23, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-6c4158c55a35d268", "rated_matches": 48, "raw_elo_rating": 1424.3051991222185, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 33.39410414668713, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 32, "generated_at": "2026-07-02T06:10:40Z", "losses": 20, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-e4eac938bdd5d40e", "rated_matches": 62, "raw_elo_rating": 1425.120377382622, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 34.66749845510415, "uncertainty": 19.244078834871203, "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": 1511.8331563488234, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 49.64522504637243, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 2, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 20, "generated_at": "2026-07-02T16:51:45Z", "losses": 9, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-446036823932df16", "rated_matches": 46, "raw_elo_rating": 1534.1619524841408, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 51.688836210667226, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 2, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 19, "generated_at": "2026-07-02T16:51:45Z", "losses": 13, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-c002b0ea38b845f8", "rated_matches": 40, "raw_elo_rating": 1470.0062111246496, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 40.192204570731214, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 2, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 20, "generated_at": "2026-07-02T16:51:45Z", "losses": 10, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-e53a932f820d9724", "rated_matches": 39, "raw_elo_rating": 1524.6990353724188, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 49.27053092873559, "uncertainty": 35.30694150420948, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 15, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 32, "generated_at": "2026-07-10T05:30:29Z", "losses": 4, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-0300c20cb034e3a4", "rated_matches": 40, "raw_elo_rating": 1488.4273983408475, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 43.29390245547429, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 2, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 17, "generated_at": "2026-07-10T10:07:13Z", "losses": 20, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-3bca3b4e02f2acf9", "rated_matches": 46, "raw_elo_rating": 1409.099303746516, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 30.63120574976151, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 19, "generated_at": "2026-07-10T05:30:29Z", "losses": 13, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-d192bb239087b778", "rated_matches": 46, "raw_elo_rating": 1480.9188274128549, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 42.723936908981315, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 4, "generated_at": "2026-07-10T05:30:29Z", "losses": 14, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-2ac4e83a1b9ba989", "rated_matches": 46, "raw_elo_rating": 1590.350902249458, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 61.14974362057465, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 10, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 33, "generated_at": "2026-07-10T05:30:29Z", "losses": 18, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-527999604d620080", "rated_matches": 68, "raw_elo_rating": 1496.7556987902174, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 47.10653317662637, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 2, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 12, "generated_at": "2026-07-10T05:30:29Z", "losses": 11, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-b741de451c385e8e", "rated_matches": 46, "raw_elo_rating": 1581.5282621482136, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 59.66421699198599, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 11, "generated_at": "2026-07-10T05:30:29Z", "losses": 13, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-39e763b7d49209b4", "rated_matches": 42, "raw_elo_rating": 1548.6158310169712, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 53.67575600395128, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 10, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 24, "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": 58, "raw_elo_rating": 1502.323955650604, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 47.38385520211626, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 24, "generated_at": "2026-07-10T05:30:29Z", "losses": 8, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-e44c62bb88a3042a", "rated_matches": 38, "raw_elo_rating": 1503.8716525415657, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 45.62802340349199, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 18, "generated_at": "2026-07-24T13:40:00Z", "losses": 22, "model": "inclusionai/ling-3.0-flash", "point_rating_method": "sequential_elo", "public_id": "E-2524de3c7d4a81b7", "rated_matches": 50, "raw_elo_rating": 1391.1702280030038, "reasoning": "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": 28.00549262423692, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "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": 1384.97093175478, "reasoning": "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": 26.96167585855616, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 23, "generated_at": "2026-07-24T13:40:00Z", "losses": 18, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-198e8ddfe9f7ce20", "rated_matches": 48, "raw_elo_rating": 1420.98998690728, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 32.83589980329351, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-3dc5f5cc9bb215b7", "rated_matches": 0, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 5, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 23, "generated_at": "2026-07-24T13:40:00Z", "losses": 14, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-84709c769628f9a2", "rated_matches": 52, "raw_elo_rating": 1450.342959592334, "reasoning": "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": 38.14845338678729, "uncertainty": 24.930281974344517, "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": 1532.5793891002238, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 53.01828026826074, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "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": 34, "raw_elo_rating": 1646.480963646981, "reasoning": "low", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "low", "repair_status": "first_pass", "score": 69.04049963440926, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 20, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 10, "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": 20, "raw_elo_rating": 1635.9359536874997, "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": 63.95218647222154, "uncertainty": 65.3589451179962, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 2, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "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": 34, "raw_elo_rating": 1595.879314119247, "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": 60.520363149032555, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 20, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 10, "draws": 4, "generated_at": "2026-07-24T14:00:00Z", "losses": 8, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-b97350a867368460", "rated_matches": 20, "raw_elo_rating": 1515.946833497835, "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": 43.748819777309976, "uncertainty": 65.3589451179962, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 26, "capped_draws": 2, "coverage_status": "under_covered", "distinct_rated_opponents": 13, "draws": 16, "generated_at": "2026-07-02T16:51:45Z", "losses": 7, "model": "nex-agi/nex-n2-pro", "point_rating_method": "sequential_elo", "public_id": "E-57ad2863cbf32d58", "rated_matches": 26, "raw_elo_rating": 1476.4776317441515, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 38.8386060326366, "uncertainty": 52.475044864937615, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 2, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 31, "generated_at": "2026-07-02T16:51:45Z", "losses": 13, "model": "nex-agi/nex-n2-pro", "point_rating_method": "sequential_elo", "public_id": "E-a05d4cef5f788f16", "rated_matches": 50, "raw_elo_rating": 1423.1096514863327, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 33.38334591324993, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 30, "capped_draws": 4, "coverage_status": "under_covered", "distinct_rated_opponents": 15, "draws": 18, "generated_at": "2026-07-02T16:51:45Z", "losses": 9, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-eb6e8a61f620acfd", "rated_matches": 30, "raw_elo_rating": 1419.179191434123, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 30.055991271142776, "uncertainty": 46.05265101338746, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 21, "generated_at": "2026-07-21T14:20:15Z", "losses": 9, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-08888c30d05ca8cb", "rated_matches": 34, "raw_elo_rating": 1451.000231276127, "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": 36.12610779925329, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 4, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 28, "generated_at": "2026-07-02T16:51:45Z", "losses": 11, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-87b4bd61da369b42", "rated_matches": 46, "raw_elo_rating": 1431.1372881816976, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 34.34188785207999, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 1, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 24, "generated_at": "2026-07-21T14:20:15Z", "losses": 8, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-c90a449ff5e7b79a", "rated_matches": 36, "raw_elo_rating": 1467.5326664526883, "reasoning": "low", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "low", "repair_status": "first_pass", "score": 39.2217430159087, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-08762a3df1a52f6b", "rated_matches": 0, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "first_pass", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 15, "generated_at": "2026-07-24T13:40:00Z", "losses": 18, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-467272d131a1a99b", "rated_matches": 50, "raw_elo_rating": 1445.2282376124174, "reasoning": "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": 37.10759945867067, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 7, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 30, "generated_at": "2026-07-24T13:40:00Z", "losses": 13, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-91efdb0c216f8504", "rated_matches": 52, "raw_elo_rating": 1502.0964642833512, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 46.86253539161154, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-936fb7956df3d03b", "rated_matches": 0, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 3, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 43, "generated_at": "2026-07-02T16:51:45Z", "losses": 7, "model": "qwen/qwen3.7-max", "point_rating_method": "sequential_elo", "public_id": "E-3325ebad2ef000c1", "rated_matches": 54, "raw_elo_rating": 1440.381307433771, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 36.64090722117748, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 6, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 21, "generated_at": "2026-07-21T14:20:15Z", "losses": 10, "model": "stepfun/step-3.7-flash", "point_rating_method": "sequential_elo", "public_id": "E-02b2a2f01700292d", "rated_matches": 40, "raw_elo_rating": 1526.648010167357, "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": 49.72936122718848, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 24, "generated_at": "2026-07-02T16:51:45Z", "losses": 20, "model": "tencent/hy3-preview", "point_rating_method": "sequential_elo", "public_id": "E-2346cd049910cc0a", "rated_matches": 70, "raw_elo_rating": 1437.0101184596929, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 37.16178607693494, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 4, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 25, "generated_at": "2026-07-24T13:40:00Z", "losses": 14, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-78048b7c08122f1c", "rated_matches": 48, "raw_elo_rating": 1437.6364882122498, "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": 35.638782010613795, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 8, "coverage_status": "rated", "distinct_rated_opponents": 25, "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": 50, "raw_elo_rating": 1608.1811038061967, "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": 64.54505799237667, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 8, "generated_at": "2026-07-24T14:00:00Z", "losses": 24, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-02f7e54245bd5c85", "rated_matches": 34, "raw_elo_rating": 1315.633820214499, "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": 13.333564304232562, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 5, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 31, "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": 56, "raw_elo_rating": 1491.9596146765782, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 45.48623836828051, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 29, "generated_at": "2026-07-21T14:20:15Z", "losses": 6, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-3c1904811d11cd84", "rated_matches": 44, "raw_elo_rating": 1517.811112552577, "reasoning": "low", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "low", "repair_status": "repaired", "score": 48.71979631230576, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 18, "capped_draws": 2, "coverage_status": "under_covered", "distinct_rated_opponents": 9, "draws": 9, "generated_at": "2026-07-24T14:00:00Z", "losses": 5, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-c0c60ca46f3ce498", "rated_matches": 18, "raw_elo_rating": 1496.1041348226042, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 39.65359036624168, "uncertainty": 70.95786693528086, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 4, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 22, "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": 62, "raw_elo_rating": 1535.7451687642574, "reasoning": "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": 53.29413078892297, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 7, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 19, "generated_at": "2026-07-17T22:36:00Z", "losses": 9, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-d5ed477108214e1c", "rated_matches": 42, "raw_elo_rating": 1542.785659806102, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 52.69409127734003, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 20, "capped_draws": 1, "coverage_status": "under_covered", "distinct_rated_opponents": 10, "draws": 10, "generated_at": "2026-07-02T16:51:45Z", "losses": 5, "model": "x-ai/grok-build-0.1", "point_rating_method": "sequential_elo", "public_id": "E-2a93343a8a88fd59", "rated_matches": 20, "raw_elo_rating": 1528.5673152215754, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 45.87381427454535, "uncertainty": 65.3589451179962, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 2, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 30, "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": 50, "raw_elo_rating": 1530.1875388618716, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 51.412762414887055, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 4, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 31, "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": 50, "raw_elo_rating": 1453.2674122393996, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 38.461208791388664, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugin_count": 1, "attempted_matches": 30, "capped_draws": 6, "coverage_status": "under_covered", "distinct_rated_opponents": 15, "draws": 19, "generated_at": "2026-07-11T17:22:09Z", "losses": 6, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-40aa28533b1afda1", "rated_matches": 30, "raw_elo_rating": 1484.357755308563, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 41.03053983455878, "uncertainty": 46.05265101338746, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 30, "capped_draws": 1, "coverage_status": "under_covered", "distinct_rated_opponents": 15, "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": 30, "raw_elo_rating": 1496.216497101582, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 43.02727511027319, "uncertainty": 46.05265101338746, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 4, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 16, "generated_at": "2026-07-11T14:00:45Z", "losses": 8, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-583be34ca1fb2631", "rated_matches": 32, "raw_elo_rating": 1501.165649912756, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 44.232887527949885, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 16, "generated_at": "2026-07-19T14:50:00Z", "losses": 14, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-714519b339aeb2e2", "rated_matches": 50, "raw_elo_rating": 1550.6088266920624, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 54.85123055069407, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 7, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 22, "generated_at": "2026-07-11T15:43:48Z", "losses": 17, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-bd2653f21938737f", "rated_matches": 46, "raw_elo_rating": 1432.536774486679, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 34.577528674842526, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 30, "capped_draws": 5, "coverage_status": "under_covered", "distinct_rated_opponents": 15, "draws": 9, "generated_at": "2026-07-02T06:10:40Z", "losses": 14, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-f1af7b938699d971", "rated_matches": 30, "raw_elo_rating": 1370.673621540632, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 21.88878566321076, "uncertainty": 46.05265101338746, "unilateral_faults": 0, "wins": 7 } ], "GB2-04": [ { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 9, "generated_at": "2026-07-03T17:50:00Z", "losses": 1, "model": "claude-fable-5", "point_rating_method": "sequential_elo", "public_id": "E-0ca15b39b465b370", "rated_matches": 56, "raw_elo_rating": 1821.3947826255776, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 100.0, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 46 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "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": 58, "raw_elo_rating": 1570.2329284352627, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 50.169539127004974, "uncertainty": 21.344455490411935, "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": "2026-07-02T16:51:45Z", "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": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 34, "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": 54, "raw_elo_rating": 1531.367240999507, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 42.06024334765576, "uncertainty": 23.66998624632421, "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": 1447.733998189398, "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": 25.949218893160513, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 0, "model": "claude-opus-4-5", "point_rating_method": "sequential_elo", "public_id": "E-e3449ff084425b16", "rated_matches": 0, "reasoning": "legacy_shared_thinking_budget", "reasoning_bracket": "highest", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "budget", "reasoning_setting": "legacy_shared_thinking_budget", "repair_status": "first_pass", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 17, "losses": 11, "model": "claude-opus-4-5", "point_rating_method": "sequential_elo", "public_id": "E-f40463f635c43598", "rated_matches": 32, "raw_elo_rating": 1424.5711000569015, "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": 17.67005637452803, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 30, "generated_at": "2026-07-03T17:20:00Z", "losses": 10, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-6344242dae68be1b", "rated_matches": 66, "raw_elo_rating": 1578.4078028250656, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 52.43603009561291, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 39, "generated_at": "2026-07-02T16:51:45Z", "losses": 8, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-688a139ef8557587", "rated_matches": 52, "raw_elo_rating": 1482.9701197438192, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 32.22275482443267, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 43, "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": 54, "raw_elo_rating": 1469.453330167729, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 29.732078673060073, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 29, "generated_at": "2026-07-25T15:48:00Z", "losses": 11, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-048d3dcf802043b4", "rated_matches": 54, "raw_elo_rating": 1540.3795707782112, "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": 43.854759056984896, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 10, "generated_at": "2026-07-25T15:48:00Z", "losses": 8, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-4c98514bdb0eaf10", "rated_matches": 40, "raw_elo_rating": 1641.3226623696942, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 62.25515491431247, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 22 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 26, "generated_at": "2026-07-25T15:48:00Z", "losses": 14, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-72e9307528761b35", "rated_matches": 56, "raw_elo_rating": 1518.0882324573904, "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": 39.60625250250319, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 12, "generated_at": "2026-07-25T15:48:00Z", "losses": 17, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-9e7782014171d35f", "rated_matches": 52, "raw_elo_rating": 1604.4941766592642, "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": 56.42036349510957, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 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": 1752.5900684317492, "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": 84.41048134127871, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 27 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 18, "generated_at": "2026-07-25T15:48:00Z", "losses": 14, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-d0f0a2b1c4bbddae", "rated_matches": 50, "raw_elo_rating": 1535.2546073345477, "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": 42.42107514802987, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 43, "generated_at": "2026-07-03T16:50:00Z", "losses": 8, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-8e980ad934b3251e", "rated_matches": 62, "raw_elo_rating": 1533.9773873174586, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 43.2849917916824, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 36, "generated_at": "2026-07-02T16:51:45Z", "losses": 7, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-b1fc5b99a5deb881", "rated_matches": 52, "raw_elo_rating": 1492.460996966201, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 34.11255787082396, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 9 }, { "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": 2, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-be938b7d5557f479", "rated_matches": 38, "raw_elo_rating": 1524.5933624248837, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 38.697311929291594, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 20, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 10, "draws": 14, "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": 20, "raw_elo_rating": 1479.6801213452768, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 25.127602707860607, "uncertainty": 65.3589451179962, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 34, "generated_at": "2026-07-01T00:15:48Z", "losses": 4, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-5d143d6301429619", "rated_matches": 40, "raw_elo_rating": 1474.9614593543852, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 29.129670210091273, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 26, "generated_at": "2026-07-02T16:51:45Z", "losses": 21, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-81bc9a578754f220", "rated_matches": 48, "raw_elo_rating": 1344.1040186798332, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 4.134248861158849, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 65, "generated_at": "2026-07-01T00:15:48Z", "losses": 1, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-a43d18fadfcc5a89", "rated_matches": 70, "raw_elo_rating": 1515.3888515107851, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 40.16590248575036, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 58, "generated_at": "2026-07-02T06:10:40Z", "losses": 0, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-cb48b9466ec54175", "rated_matches": 58, "raw_elo_rating": 1508.100473988519, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 37.797858518143734, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 22, "generated_at": "2026-07-02T16:51:45Z", "losses": 19, "model": "deepseek/deepseek-v4-pro", "point_rating_method": "sequential_elo", "public_id": "E-38bc194a470fbf62", "rated_matches": 48, "raw_elo_rating": 1440.214332474687, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 23.27152769675579, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 18, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 9, "draws": 14, "generated_at": "2026-07-02T16:51:45Z", "losses": 4, "model": "google/gemini-3.1-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-2be6f5c895691cb3", "rated_matches": 18, "raw_elo_rating": 1449.9540436634004, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 18.316733886011004, "uncertainty": 70.95786693528086, "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": 2, "model": "google/gemini-3.1-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-860c31323fa5eda7", "rated_matches": 44, "raw_elo_rating": 1496.4002724512168, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 33.96421938799026, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 33, "generated_at": "2026-07-02T16:51:45Z", "losses": 8, "model": "google/gemini-3.5-flash", "point_rating_method": "sequential_elo", "public_id": "E-32cfa6c9dfb1d16f", "rated_matches": 54, "raw_elo_rating": 1537.8145480172825, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 43.34401724523379, "uncertainty": 23.66998624632421, "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": 1479.6173364839724, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 28.630744502168437, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 52, "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": 63, "raw_elo_rating": 1504.0838388637048, "reasoning": "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": 37.4113566914359, "uncertainty": 18.75, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 50, "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": 65, "raw_elo_rating": 1471.9723967515329, "reasoning": "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": 31.169402731335655, "uncertainty": 17.79574548966636, "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": 65, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 39, "generated_at": "2026-07-24T13:40:00Z", "losses": 10, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-1ff96286ae16ecd4", "rated_matches": 64, "raw_elo_rating": 1498.584656594851, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 36.39325198178922, "uncertainty": 18.26736729460423, "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": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 48, "generated_at": "2026-07-24T13:40:00Z", "losses": 8, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-d109ab12db58a65f", "rated_matches": 64, "raw_elo_rating": 1476.6296215757122, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 32.02161266008875, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 24, "generated_at": "2026-07-02T16:51:45Z", "losses": 4, "model": "google/gemma-4-31b-it", "point_rating_method": "sequential_elo", "public_id": "E-62ca2464f2212fc9", "rated_matches": 32, "raw_elo_rating": 1518.6101743659633, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 36.3949144614059, "uncertainty": 43.288827977848925, "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": 5, "model": "google/gemma-4-31b-it", "point_rating_method": "sequential_elo", "public_id": "E-ec0cf4b37c805eee", "rated_matches": 52, "raw_elo_rating": 1489.2296172501635, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 33.4691324962955, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 23, "generated_at": "2026-07-02T16:51:45Z", "losses": 9, "model": "gpt-4.1", "point_rating_method": "sequential_elo", "public_id": "E-ecb06954153be8d5", "rated_matches": 34, "raw_elo_rating": 1459.143974925331, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 24.956096391857447, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 44, "generated_at": "2026-07-02T16:51:45Z", "losses": 8, "model": "gpt-5", "point_rating_method": "sequential_elo", "public_id": "E-6f1aae863396df76", "rated_matches": 68, "raw_elo_rating": 1551.1716734247516, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 47.15488856869603, "uncertainty": 16.4429265428846, "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": 1469.0066409376975, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 25.5926504889775, "uncertainty": 49.09766908852594, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 40, "generated_at": "2026-07-02T16:51:45Z", "losses": 7, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-0b4132559ee98caf", "rated_matches": 58, "raw_elo_rating": 1514.0229127508078, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 38.977121778303186, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 49, "generated_at": "2026-07-02T16:51:45Z", "losses": 8, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-8d62bf1b340a70dc", "rated_matches": 68, "raw_elo_rating": 1495.1061108254105, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 35.99123440741221, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 27, "generated_at": "2026-07-02T16:51:45Z", "losses": 13, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-9279285adff8ed29", "rated_matches": 68, "raw_elo_rating": 1617.2220685254226, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 60.3067010884318, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 36, "generated_at": "2026-07-02T06:10:40Z", "losses": 12, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-040a4b654fceeb0c", "rated_matches": 56, "raw_elo_rating": 1477.4284617057842, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 31.510166457816872, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 42, "generated_at": "2026-07-02T16:51:45Z", "losses": 12, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-0880cdf1a43cb90c", "rated_matches": 70, "raw_elo_rating": 1490.652343272743, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 35.24042220294854, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 37, "generated_at": "2026-07-01T00:15:48Z", "losses": 5, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-6d633c9c2680eb32", "rated_matches": 54, "raw_elo_rating": 1554.76847532534, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 46.71984676281586, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 31, "generated_at": "2026-07-02T16:51:45Z", "losses": 7, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-74f5bcc8ad3796a5", "rated_matches": 56, "raw_elo_rating": 1565.524282873785, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 49.05161677023061, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 54, "generated_at": "2026-07-02T06:10:40Z", "losses": 4, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-c9bf6a0be0c43fd1", "rated_matches": 64, "raw_elo_rating": 1469.424915746871, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 30.587027141314085, "uncertainty": 18.26736729460423, "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": 1531.2344187539643, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 43.185025327321505, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 43, "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": 56, "raw_elo_rating": 1473.3753217645994, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 30.703113955837612, "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": 15, "generated_at": "2026-07-09T17:30:50Z", "losses": 21, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-3403c285ceec6345", "rated_matches": 66, "raw_elo_rating": 1534.1070795948144, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 43.614965429384334, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 30 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 43, "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": 62, "raw_elo_rating": 1472.5352153209826, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 31.05075873870246, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 34, "generated_at": "2026-07-09T17:30:50Z", "losses": 8, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-a32cb67d48c62b3b", "rated_matches": 58, "raw_elo_rating": 1559.5720195351737, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 48.04676189107393, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 26, "generated_at": "2026-07-02T06:10:40Z", "losses": 22, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-bbf36865f2b7fe63", "rated_matches": 56, "raw_elo_rating": 1378.718853491191, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 11.855321711525466, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 49, "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": 64, "raw_elo_rating": 1498.8576559280334, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 36.44761102146728, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 43, "generated_at": "2026-07-01T00:15:48Z", "losses": 13, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-fd2be90162c92ecf", "rated_matches": 70, "raw_elo_rating": 1532.8060282037686, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 43.63397322386019, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 42, "generated_at": "2026-07-02T16:51:45Z", "losses": 13, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-64bf5daf186f8119", "rated_matches": 66, "raw_elo_rating": 1470.3598482849127, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 30.921753926830576, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 40, "generated_at": "2026-07-02T16:51:45Z", "losses": 13, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-9e7bdad81107b7e4", "rated_matches": 62, "raw_elo_rating": 1453.9356837685343, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 27.3472600456232, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 48, "generated_at": "2026-07-02T16:51:45Z", "losses": 12, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-ba1aa87056709e9a", "rated_matches": 66, "raw_elo_rating": 1498.700299003465, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 36.564843479998515, "uncertainty": 17.33472217815261, "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": 1512.8853854171534, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 39.08519776719661, "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": 50, "generated_at": "2026-07-10T05:30:29Z", "losses": 13, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-71a01107bf3f9fc1", "rated_matches": 70, "raw_elo_rating": 1494.4916414654292, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 36.004894996193826, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 33, "generated_at": "2026-07-10T05:30:29Z", "losses": 15, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-e348813cda8b38b7", "rated_matches": 60, "raw_elo_rating": 1514.736546987583, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 39.29062220793382, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 26, "generated_at": "2026-07-10T05:30:29Z", "losses": 2, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-270a233119b6cc62", "rated_matches": 54, "raw_elo_rating": 1653.789369331552, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 66.43667406598968, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 50, "generated_at": "2026-07-10T05:30:29Z", "losses": 4, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-c81bf4d15f3d48f1", "rated_matches": 58, "raw_elo_rating": 1490.518146546648, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 34.29690331835047, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 49, "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": 56, "raw_elo_rating": 1480.4876650964738, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 32.11930845299747, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 76, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 38, "draws": 71, "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": 76, "raw_elo_rating": 1520.0291620852558, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 41.465613636603344, "uncertainty": 13.230288229818967, "unilateral_faults": 0, "wins": 4 }, { "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": 5, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-89c18d144e85d89f", "rated_matches": 64, "raw_elo_rating": 1509.8215591763649, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 38.630719839920246, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 27, "generated_at": "2026-07-10T05:30:29Z", "losses": 12, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-b85c80e7475ef9ec", "rated_matches": 58, "raw_elo_rating": 1561.4093381266223, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 48.412604814752626, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "inclusionai/ling-3.0-flash", "point_rating_method": "sequential_elo", "public_id": "E-20e94e7276184071", "rated_matches": 0, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 56, "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": 62, "raw_elo_rating": 1475.5058004589516, "reasoning": "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": 31.642255258124266, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-46a1c9f4e3ff6058", "rated_matches": 0, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-4ccf296e55b59be3", "rated_matches": 0, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 36, "generated_at": "2026-07-24T13:40:00Z", "losses": 13, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-9e1d4bf411e97fa6", "rated_matches": 64, "raw_elo_rating": 1565.1896956500836, "reasoning": "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": 49.655504012060575, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 20, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 10, "draws": 19, "generated_at": "2026-07-02T16:51:45Z", "losses": 1, "model": "minimax/minimax-m3", "point_rating_method": "sequential_elo", "public_id": "E-c60620c3c72a6064", "rated_matches": 20, "raw_elo_rating": 1485.6322009222465, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 26.312767983246804, "uncertainty": 65.3589451179962, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 24, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 12, "draws": 19, "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": 24, "raw_elo_rating": 1478.974085801931, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 26.438021268193044, "uncertainty": 56.25, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 20, "generated_at": "2026-07-21T14:43:57Z", "losses": 8, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-0f7ca9245c7db7c7", "rated_matches": 40, "raw_elo_rating": 1503.8515619886705, "reasoning": "high", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 34.88220526976701, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugin_count": 1, "attempted_matches": 30, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 15, "draws": 15, "generated_at": "2026-07-17T22:36:00Z", "losses": 7, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-2a7239d6b25916b0", "rated_matches": 30, "raw_elo_rating": 1533.6610234761592, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "score": 38.95154594834624, "uncertainty": 46.05265101338746, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 27, "generated_at": "2026-07-24T14:00:00Z", "losses": 6, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-35e5c9532c697b2c", "rated_matches": 36, "raw_elo_rating": 1479.9548503177186, "reasoning": "high", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 29.46882779889735, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 19, "generated_at": "2026-07-24T14:00:00Z", "losses": 6, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-3c06949f23d4a77f", "rated_matches": 34, "raw_elo_rating": 1534.8297093158149, "reasoning": "low", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "low", "repair_status": "repaired", "score": 40.02647693394225, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 11, "generated_at": "2026-07-24T14:00:00Z", "losses": 7, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-601725df2c678708", "rated_matches": 32, "raw_elo_rating": 1573.6723557360497, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "score": 47.35877751178312, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 8, "generated_at": "2026-07-17T22:36:00Z", "losses": 10, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-6f3da6d3b01bcfad", "rated_matches": 32, "raw_elo_rating": 1540.1574056912934, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "score": 40.68535278926445, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 27, "generated_at": "2026-07-21T14:20:15Z", "losses": 7, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-818ed7ee27b56509", "rated_matches": 40, "raw_elo_rating": 1494.7605140992057, "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": 33.072015379639225, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 51, "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": 56, "raw_elo_rating": 1491.0471982021531, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 34.22189995892514, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 26, "generated_at": "2026-07-11T17:22:09Z", "losses": 5, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-958dea26b779a042", "rated_matches": 32, "raw_elo_rating": 1453.633991580523, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 23.45699678597452, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 29, "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": 40, "raw_elo_rating": 1495.9339395098796, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 33.30566532198333, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 44, "generated_at": "2026-07-02T16:51:45Z", "losses": 7, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-7e92e17a121661f4", "rated_matches": 54, "raw_elo_rating": 1459.8799045162689, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 27.82583876113024, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 18, "generated_at": "2026-07-21T14:20:15Z", "losses": 9, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-a4643af0a1bcc24c", "rated_matches": 34, "raw_elo_rating": 1475.8102858634056, "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": 28.274656356852365, "uncertainty": 40.76542547285167, "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": 1458.6554530564592, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 24.858822968717504, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 38, "generated_at": "2026-07-02T16:51:45Z", "losses": 4, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-f1288f2abfdbbfe4", "rated_matches": 46, "raw_elo_rating": 1479.5119436507632, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 30.856816919223707, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 24, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 12, "draws": 11, "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": 24, "raw_elo_rating": 1401.6541457347726, "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": 11.042241208882738, "uncertainty": 56.25, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-e996fd38983e3b7f", "rated_matches": 0, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 24, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 12, "draws": 14, "generated_at": "2026-07-02T16:51:45Z", "losses": 6, "model": "qwen/qwen3.7-max", "point_rating_method": "sequential_elo", "public_id": "E-ea08328e287de1ad", "rated_matches": 24, "raw_elo_rating": 1495.2123365460154, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "first_pass", "score": 29.67134680862549, "uncertainty": 56.25, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 40, "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": 46, "raw_elo_rating": 1507.7518112619032, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 36.47987858051721, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 42, "generated_at": "2026-07-02T16:51:45Z", "losses": 3, "model": "stepfun/step-3.7-flash", "point_rating_method": "sequential_elo", "public_id": "E-25e56c6bfae33c62", "rated_matches": 50, "raw_elo_rating": 1527.025896067843, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 40.78259187031759, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 28, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 14, "draws": 16, "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": 28, "raw_elo_rating": 1539.8999918600214, "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": 39.70878194898091, "uncertainty": 49.09766908852594, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 34, "generated_at": "2026-07-02T16:51:45Z", "losses": 6, "model": "tencent/hy3-preview", "point_rating_method": "sequential_elo", "public_id": "E-3fd10f7865cc280e", "rated_matches": 50, "raw_elo_rating": 1521.129620533277, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 39.60853817575416, "uncertainty": 26.26400420140049, "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": 1437.5787582504663, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 15.852593688498793, "uncertainty": 70.95786693528086, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 30, "generated_at": "2026-07-24T13:40:00Z", "losses": 16, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-646ff33c7bab8b13", "rated_matches": 52, "raw_elo_rating": 1434.289539016747, "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": 22.529582359703383, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 50, "generated_at": "2026-07-24T13:40:00Z", "losses": 6, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-7ca32267720b2e1a", "rated_matches": 60, "raw_elo_rating": 1497.2594850671685, "reasoning": "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": 35.81062725222203, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 40, "generated_at": "2026-07-24T13:40:00Z", "losses": 12, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-d9e91f86e4e39739", "rated_matches": 58, "raw_elo_rating": 1444.8493223540486, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 25.20342533290631, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 52, "generated_at": "2026-07-24T13:40:00Z", "losses": 6, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-ddc16fa197bfc7c5", "rated_matches": 62, "raw_elo_rating": 1509.229278499366, "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": 38.35720162634748, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 14, "generated_at": "2026-07-24T14:00:00Z", "losses": 12, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-07caaa12175b0b3c", "rated_matches": 34, "raw_elo_rating": 1490.7798276084395, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 31.25535929189119, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 52, "generated_at": "2026-07-17T22:36:00Z", "losses": 6, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-1a7064508fe2a12f", "rated_matches": 68, "raw_elo_rating": 1507.4097653694373, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 38.441111620470615, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugin_count": 1, "attempted_matches": 28, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 14, "draws": 21, "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": 28, "raw_elo_rating": 1533.5405814547744, "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": 38.44250983571969, "uncertainty": 49.09766908852594, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 35, "generated_at": "2026-07-24T14:00:00Z", "losses": 4, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-617354569710a53d", "rated_matches": 44, "raw_elo_rating": 1529.50537203445, "reasoning": "low", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "low", "repair_status": "repaired", "score": 40.55603556868472, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 24, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 12, "draws": 15, "generated_at": "2026-07-17T22:36:00Z", "losses": 9, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-70da8ff73f18e636", "rated_matches": 24, "raw_elo_rating": 1401.1566928359573, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 10.943189458281616, "uncertainty": 56.25, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 42, "generated_at": "2026-07-17T22:36:00Z", "losses": 9, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-83f4cc0ffc20bde5", "rated_matches": 58, "raw_elo_rating": 1505.116815543511, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 37.20375886996048, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 82, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 41, "draws": 58, "generated_at": "2026-07-24T14:00:00Z", "losses": 12, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-ba6a8e6d7fc9a48d", "rated_matches": 82, "raw_elo_rating": 1502.9746588577696, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 38.40398226010029, "uncertainty": 11.132129994845172, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugin_count": 1, "attempted_matches": 20, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 10, "draws": 11, "generated_at": "2026-07-17T22:36:00Z", "losses": 6, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-dac812d348a29158", "rated_matches": 20, "raw_elo_rating": 1465.438200124379, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 22.291782005613324, "uncertainty": 65.3589451179962, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 26, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 13, "draws": 21, "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": 26, "raw_elo_rating": 1490.591586720057, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 29.35260180166352, "uncertainty": 52.475044864937615, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 25, "generated_at": "2026-07-02T06:10:40Z", "losses": 5, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-00e6914e513b1656", "rated_matches": 32, "raw_elo_rating": 1470.073185800368, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 26.730333758832895, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 30, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 15, "draws": 19, "generated_at": "2026-07-01T00:15:48Z", "losses": 10, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-23e877112cb95491", "rated_matches": 30, "raw_elo_rating": 1420.5057556493118, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 16.42031254980346, "uncertainty": 46.05265101338746, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 28, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 14, "draws": 22, "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": 28, "raw_elo_rating": 1445.8371871373347, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 20.979198713214263, "uncertainty": 49.09766908852594, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 42, "generated_at": "2026-07-01T00:15:48Z", "losses": 5, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-7ad356726cce2b22", "rated_matches": 58, "raw_elo_rating": 1484.624320346856, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 33.123337330055804, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 48, "generated_at": "2026-07-02T06:10:40Z", "losses": 2, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-d58c55e107783a21", "rated_matches": 52, "raw_elo_rating": 1508.239089106963, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 37.254257620509655, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 30, "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": 40, "raw_elo_rating": 1495.9190911735002, "reasoning": "highest", "reasoning_bracket": "highest", "reasoning_setting": "highest", "repair_status": "repaired", "score": 33.302708753199845, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 30, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 15, "draws": 13, "generated_at": "2026-07-02T16:51:45Z", "losses": 8, "model": "xiaomi/mimo-v2.5-pro", "point_rating_method": "sequential_elo", "public_id": "E-ffdebde8a72ed049", "rated_matches": 30, "raw_elo_rating": 1489.877627090251, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 30.233490289979848, "uncertainty": 46.05265101338746, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 27, "generated_at": "2026-07-02T16:51:45Z", "losses": 5, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-1d5f5ff0402ff944", "rated_matches": 38, "raw_elo_rating": 1541.791950099912, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 42.1218576925904, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 37, "generated_at": "2026-07-02T06:10:40Z", "losses": 1, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-3efc86009429a22c", "rated_matches": 40, "raw_elo_rating": 1499.4200524361283, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 33.99981262509591, "uncertainty": 34.33688094430304, "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": 1514.4116043081467, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 40.57400938510051, "uncertainty": 11.805555555555554, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 26, "generated_at": "2026-07-11T17:22:09Z", "losses": 8, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-912f31ad14c4bf0a", "rated_matches": 40, "raw_elo_rating": 1466.3555284012216, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 27.416075760258096, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 11, "generated_at": "2026-07-01T00:15:48Z", "losses": 12, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-947248ef34168cde", "rated_matches": 34, "raw_elo_rating": 1520.1832423700175, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 37.11010395761048, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 30, "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": 40, "raw_elo_rating": 1486.846732114631, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 31.49624014279844, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 18, "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": 40, "raw_elo_rating": 1505.5790197351166, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 35.22617293842966, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 25, "generated_at": "2026-07-02T06:10:40Z", "losses": 16, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-f9359f32abb5e3c8", "rated_matches": 50, "raw_elo_rating": 1438.546321559748, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 23.164729418732747, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 9 } ], "GB2-05": [ { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 8, "model": "claude-fable-5", "point_rating_method": "sequential_elo", "public_id": "E-5aa4402ccce7b855", "rated_matches": 64, "raw_elo_rating": 1897.678809124274, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 92.3708669015868, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 56 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 24, "model": "claude-fable-5", "point_rating_method": "sequential_elo", "public_id": "E-ad7cf41c05ec3f64", "rated_matches": 54, "raw_elo_rating": 1563.8549313784958, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 52.92663955035931, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 30 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 0, "model": "claude-opus-4-5", "point_rating_method": "sequential_elo", "public_id": "E-7e9bc3ebc12ef500", "rated_matches": 0, "reasoning": "legacy_shared_thinking_budget", "reasoning_bracket": "highest", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "budget", "reasoning_setting": "legacy_shared_thinking_budget", "repair_status": "first_pass", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 24, "model": "claude-opus-4-5", "point_rating_method": "sequential_elo", "public_id": "E-934b5bc34a7e20b9", "rated_matches": 66, "raw_elo_rating": 1537.0274446215944, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 50.38845226238323, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 42 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 0, "losses": 20, "model": "claude-opus-4-5", "point_rating_method": "sequential_elo", "public_id": "E-a75e9d71efa4a6bc", "rated_matches": 40, "raw_elo_rating": 1497.5258968771657, "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": 44.194033844161495, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 0, "losses": 20, "model": "claude-opus-4-5", "point_rating_method": "sequential_elo", "public_id": "E-ccacc93776fb7c88", "rated_matches": 42, "raw_elo_rating": 1491.063764692389, "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": 43.61171795005389, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 22 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 0, "model": "claude-opus-4-5", "point_rating_method": "sequential_elo", "public_id": "E-ff0722d17402bafa", "rated_matches": 0, "reasoning": "legacy_shared_thinking_budget", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "budget", "reasoning_setting": "legacy_shared_thinking_budget", "repair_status": "first_pass", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 36, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-233f9cae6335e53d", "rated_matches": 66, "raw_elo_rating": 1402.501367016649, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 34.69618438144857, "uncertainty": 17.33472217815261, "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": "2026-07-02T16:51:45Z", "losses": 35, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-6774d700e60de31a", "rated_matches": 64, "raw_elo_rating": 1539.0151173817317, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 50.53327801033048, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 28, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-924d7e6ee41b562e", "rated_matches": 60, "raw_elo_rating": 1526.9858286719375, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 48.94334155048709, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 0, "generated_at": "2026-07-25T10:50:00Z", "losses": 15, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-09963ffe0b0fa5fd", "rated_matches": 60, "raw_elo_rating": 1828.041975577455, "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": 84.06109558414614, "uncertainty": 20.268439966447993, "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": 17, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-32c377b229530444", "rated_matches": 58, "raw_elo_rating": 1769.415445775125, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 77.12198514337373, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 41 }, { "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": 1975.937162276245, "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": 1742.2952393168755, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 72.74601543009426, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 0, "generated_at": "2026-07-25T10:50:00Z", "losses": 14, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-b53cb955b1d8baab", "rated_matches": 58, "raw_elo_rating": 1819.349185874928, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 82.94668203406992, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 44 }, { "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": 11, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-d7111b534ebcaba2", "rated_matches": 58, "raw_elo_rating": 1828.2244902143957, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 83.98197315159396, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 47 }, { "admitted_plugin_count": 1, "attempted_matches": 76, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 38, "draws": 0, "generated_at": "2026-07-03T16:50:00Z", "losses": 38, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-c902807aab849f31", "rated_matches": 76, "raw_elo_rating": 1550.6378956784858, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 52.35911215449047, "uncertainty": 13.230288229818967, "unilateral_faults": 0, "wins": 38 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 27, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-e0a09b1ea3f11175", "rated_matches": 62, "raw_elo_rating": 1521.6286930837043, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 48.414031779727786, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 35 }, { "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": 27, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-e619c51e7d5d70d2", "rated_matches": 48, "raw_elo_rating": 1433.5767315502376, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 37.35580390238191, "uncertainty": 27.67857142857143, "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": 16, "model": "cohere/north-mini-code", "point_rating_method": "sequential_elo", "public_id": "E-a0518a43c688d1e2", "rated_matches": 38, "raw_elo_rating": 1495.5568486203565, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "first_pass", "score": 43.77983769266278, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 22 }, { "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": 28, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-06a41d0e11b18b77", "rated_matches": 48, "raw_elo_rating": 1413.4014704079275, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 35.00238954548179, "uncertainty": 27.67857142857143, "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": 41, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-0dca18c79b6ac9d7", "rated_matches": 66, "raw_elo_rating": 1462.271811781849, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 41.66831831500828, "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": "2026-07-02T06:10:40Z", "losses": 28, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-2c1cbd253f3a9d69", "rated_matches": 48, "raw_elo_rating": 1361.191173568771, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 28.912135679988577, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 57, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-b306c8f5ffbbec38", "rated_matches": 70, "raw_elo_rating": 1282.17152675321, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 20.822787568784545, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 13 }, { "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": 29, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-b3d889b0631db85f", "rated_matches": 72, "raw_elo_rating": 1561.569551356425, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 53.49053600554524, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 43 }, { "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": 41, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-b8554f0ccf0845da", "rated_matches": 64, "raw_elo_rating": 1397.1418637639106, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 33.98397291984452, "uncertainty": 18.26736729460423, "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": 47, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-efa8d9109b008ee9", "rated_matches": 84, "raw_elo_rating": 1438.4527555048498, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 39.529291228691534, "uncertainty": 10.482614454664043, "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": "2026-07-02T16:51:45Z", "losses": 23, "model": "deepseek/deepseek-v4-pro", "point_rating_method": "sequential_elo", "public_id": "E-0ca4798825ceaccb", "rated_matches": 72, "raw_elo_rating": 1760.1833865422625, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 76.6585459712308, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 49 }, { "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": 1403.244405392198, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 35.48079904046824, "uncertainty": 9.855626741889738, "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": 37, "model": "google/gemini-3.1-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-7603462aff103041", "rated_matches": 64, "raw_elo_rating": 1318.8709361070892, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 24.85378503399073, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 27 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 34, "model": "google/gemini-3.1-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-a72dd193e1dc4331", "rated_matches": 38, "raw_elo_rating": 1231.4676614197515, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 12.974224804876902, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 4 }, { "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": 32, "model": "google/gemini-3.1-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-d979b43c3aeea657", "rated_matches": 48, "raw_elo_rating": 1296.6134001853593, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 21.379233976999053, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-21T14:20:15Z", "losses": 0, "model": "google/gemini-3.5-flash", "point_rating_method": "sequential_elo", "public_id": "E-84cd6ee956650b32", "rated_matches": 0, "reasoning": "low", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "low", "repair_status": "repaired", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 37, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 40, "model": "google/gemini-3.5-flash", "point_rating_method": "sequential_elo", "public_id": "E-a7ce764239377b3f", "rated_matches": 74, "raw_elo_rating": 1471.8580015094933, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 43.09912275717949, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 18, "model": "google/gemini-3.5-flash", "point_rating_method": "sequential_elo", "public_id": "E-b50da126631c1ea1", "rated_matches": 38, "raw_elo_rating": 1496.535066946335, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 43.89394541282078, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-214f636367cbdac4", "rated_matches": 0, "reasoning": "minimal", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "minimal", "repair_status": "repaired", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-27023858537764ac", "rated_matches": 0, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-2aebd7296279d5e5", "rated_matches": 0, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-a870d09d3e1a40d4", "rated_matches": 0, "reasoning": "minimal", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "minimal", "repair_status": "first_pass", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "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-c311887ca24f8a76", "rated_matches": 70, "raw_elo_rating": 1370.5699340132535, "reasoning": "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": 31.134330963710465, "uncertainty": 15.58908290969266, "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": "2026-07-24T13:40:00Z", "losses": 34, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-e3c1bc55ae62b8db", "rated_matches": 66, "raw_elo_rating": 1368.7640467794815, "reasoning": "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": 30.760775900267603, "uncertainty": 17.33472217815261, "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": "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": 74, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 37, "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": 74, "raw_elo_rating": 1815.797658505252, "reasoning": "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": 83.21917478384927, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 59 }, { "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": 40, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-c7d3f2597dfefeb3", "rated_matches": 76, "raw_elo_rating": 1600.5420889346544, "reasoning": "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": 58.18036244960011, "uncertainty": 13.230288229818967, "unilateral_faults": 0, "wins": 36 }, { "admitted_plugin_count": 1, "attempted_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": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 40, "model": "google/gemma-4-31b-it", "point_rating_method": "sequential_elo", "public_id": "E-e8e17fbbdd12faa4", "rated_matches": 64, "raw_elo_rating": 1296.022394286137, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 22.18853644184757, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 18, "model": "google/gemma-4-31b-it", "point_rating_method": "sequential_elo", "public_id": "E-fd1bc1e2e6ac48fb", "rated_matches": 32, "raw_elo_rating": 1490.7546387691116, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 42.568791506466454, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 29, "model": "gpt-4.1", "point_rating_method": "sequential_elo", "public_id": "E-1b9f1f7b70f02927", "rated_matches": 48, "raw_elo_rating": 1339.63995352344, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 26.39821775319491, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 31, "model": "gpt-5", "point_rating_method": "sequential_elo", "public_id": "E-9e5b308c41a36374", "rated_matches": 58, "raw_elo_rating": 1570.3013243910782, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 53.89561753299053, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 27 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 14, "model": "gpt-5", "point_rating_method": "sequential_elo", "public_id": "E-c5ad048b6fb4e93d", "rated_matches": 38, "raw_elo_rating": 1613.0836013006249, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 57.48915947673398, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-21T14:20:15Z", "losses": 0, "model": "gpt-5", "point_rating_method": "sequential_elo", "public_id": "E-d03d2c6a69fc3e16", "rated_matches": 0, "reasoning": "low", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "low", "repair_status": "repaired", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 84, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 42, "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": 84, "raw_elo_rating": 1752.4021108928348, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 76.1510189524612, "uncertainty": 10.482614454664043, "unilateral_faults": 0, "wins": 59 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 32, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-cafab3c275850d3b", "rated_matches": 64, "raw_elo_rating": 1528.5904299300091, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 49.31725364553898, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 4, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-f6403f7a30e19e82", "rated_matches": 64, "raw_elo_rating": 1933.7094741760584, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 96.57379066170128, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 60 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 30, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-0791f6b66243ec1a", "rated_matches": 58, "raw_elo_rating": 1469.5509985868252, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 42.143241118250984, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 41, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-427bdffeacc6c394", "rated_matches": 62, "raw_elo_rating": 1311.6911384019315, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 23.925126691680777, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 34, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-481582e8f8e3217e", "rated_matches": 64, "raw_elo_rating": 1550.7619638532972, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 51.903530268255835, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 30 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 33, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-539afc540807da47", "rated_matches": 58, "raw_elo_rating": 1384.0918030499022, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 32.17455242138175, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 0, "generated_at": "2026-07-01T00:15:48Z", "losses": 28, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-8ed627956c0a0292", "rated_matches": 64, "raw_elo_rating": 1409.3463288872344, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 35.407605716313434, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 36 }, { "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": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-95d1a872f51b78e7", "rated_matches": 82, "raw_elo_rating": 1447.8287691287428, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 40.56237732200695, "uncertainty": 11.132129994845172, "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": "2026-07-02T06:10:40Z", "losses": 46, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-cdd304da89074d54", "rated_matches": 76, "raw_elo_rating": 1367.284453130071, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 30.971204407632033, "uncertainty": 13.230288229818967, "unilateral_faults": 0, "wins": 30 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 0, "generated_at": "2026-07-01T00:15:48Z", "losses": 32, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-ce84b7a3c6105fb2", "rated_matches": 56, "raw_elo_rating": 1414.7593062675958, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 35.646219238554934, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugin_count": 1, "attempted_matches": 76, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 38, "draws": 0, "generated_at": "2026-07-09T17:30:50Z", "losses": 53, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-3311575b341ee4a8", "rated_matches": 76, "raw_elo_rating": 1333.8464687908915, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 27.07071301599414, "uncertainty": 13.230288229818967, "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": "2026-07-01T00:15:48Z", "losses": 48, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-49b3c6006a3b9fcc", "rated_matches": 72, "raw_elo_rating": 1385.3452388274272, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 32.934230725765595, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugin_count": 1, "attempted_matches": 69, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 35, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-54b9ca4996a5589d", "rated_matches": 69, "raw_elo_rating": 1570.947088336314, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 54.46861652336368, "uncertainty": 16.01143046671968, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 45, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-6c37eeef15b82287", "rated_matches": 62, "raw_elo_rating": 1268.0317786889311, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 18.83232698827737, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 45, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-83cfa14483bf0d43", "rated_matches": 58, "raw_elo_rating": 1261.1637541853777, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 17.835177430254863, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 16, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-8e40431df091d53f", "rated_matches": 68, "raw_elo_rating": 1741.5666304104925, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 74.33086692052227, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 52 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 0, "generated_at": "2026-07-09T17:30:50Z", "losses": 40, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-a0d8c8fd6b01598c", "rated_matches": 66, "raw_elo_rating": 1403.2268012896968, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 34.78080521590199, "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": 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": 68, "raw_elo_rating": 1662.473619841533, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 65.10478427948581, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 41 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 0, "generated_at": "2026-07-01T00:15:48Z", "losses": 40, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-ff2b4db95370e3d6", "rated_matches": 62, "raw_elo_rating": 1324.2741283816072, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 25.392913852502083, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 22 }, { "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": 25, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-6f42dbbf02274b56", "rated_matches": 64, "raw_elo_rating": 1589.5434120737496, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 56.42732881438667, "uncertainty": 18.26736729460423, "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": 15, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-762e9d80a60b41ed", "rated_matches": 68, "raw_elo_rating": 1822.9563803754577, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 83.82486081338791, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 53 }, { "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": 23, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-ffa82d1e96e897ab", "rated_matches": 60, "raw_elo_rating": 1648.4542713590818, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 63.11245564094769, "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": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 31, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-25a83ddaeb1268a4", "rated_matches": 66, "raw_elo_rating": 1576.596774461676, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 55.00415603353663, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 35 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 57, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-59156a669808a24f", "rated_matches": 62, "raw_elo_rating": 1106.586721726533, "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": 19.244078834871203, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 29, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-e917387a1c57aa23", "rated_matches": 54, "raw_elo_rating": 1567.9046996706184, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 53.39903902878851, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 25, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-471e9297eea18ffd", "rated_matches": 68, "raw_elo_rating": 1600.385772117564, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 57.86232872007845, "uncertainty": 16.4429265428846, "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": "2026-07-10T05:30:29Z", "losses": 21, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-af9c2c2998294ad0", "rated_matches": 76, "raw_elo_rating": 1723.892992498132, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 72.56906281561947, "uncertainty": 13.230288229818967, "unilateral_faults": 0, "wins": 55 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 20, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-d61f8454991c5422", "rated_matches": 60, "raw_elo_rating": 1642.6315145680098, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 62.43323967778432, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 40 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 25, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-012ecb9ce0709c05", "rated_matches": 68, "raw_elo_rating": 1618.9193174279271, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 60.024239354593, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 43 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 26, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-1f00b423eab1c19d", "rated_matches": 64, "raw_elo_rating": 1584.708544050022, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 55.863348614056285, "uncertainty": 18.26736729460423, "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": "2026-07-10T05:30:29Z", "losses": 28, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-9664e98d37ece097", "rated_matches": 60, "raw_elo_rating": 1552.729583417106, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 51.946312445904134, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 37, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 58, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-067ab716d64e3e9a", "rated_matches": 74, "raw_elo_rating": 1251.2405254174005, "reasoning": "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": 17.364420640765804, "uncertainty": 13.985026918962571, "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": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 43, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-8cc657b7db4428cb", "rated_matches": 70, "raw_elo_rating": 1352.959444081681, "reasoning": "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": 29.080093373194575, "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": "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": 76, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 38, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 41, "model": "minimax/minimax-m3", "point_rating_method": "sequential_elo", "public_id": "E-33797d7b77c7800c", "rated_matches": 76, "raw_elo_rating": 1461.8308552065046, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 41.99990230008747, "uncertainty": 13.230288229818967, "unilateral_faults": 0, "wins": 35 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 28, "model": "minimax/minimax-m3", "point_rating_method": "sequential_elo", "public_id": "E-fb8ac45946e32e22", "rated_matches": 32, "raw_elo_rating": 1259.3102294143223, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 15.571143646654498, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 34, "model": "mistralai/mistral-medium-3-5", "point_rating_method": "sequential_elo", "public_id": "E-1954b83d439b455c", "rated_matches": 38, "raw_elo_rating": 1194.7598086768326, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 8.692308102693845, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 4 }, { "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": 51, "model": "mistralai/mistral-medium-3-5", "point_rating_method": "sequential_elo", "public_id": "E-4a7d37b86196302f", "rated_matches": 92, "raw_elo_rating": 1425.928615167466, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 38.2909369413615, "uncertainty": 8.09758473652126, "unilateral_faults": 0, "wins": 41 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 17, "model": "moonshotai/kimi-k2.7-code", "point_rating_method": "sequential_elo", "public_id": "E-952fba19b28982d5", "rated_matches": 32, "raw_elo_rating": 1544.7036702952114, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 48.86186620021212, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 0, "generated_at": "2026-07-18T00:14:00Z", "losses": 27, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-288f9a63e6b6cae3", "rated_matches": 52, "raw_elo_rating": 1497.0639330934057, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "score": 45.01795913236869, "uncertainty": 24.930281974344517, "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": "2026-07-24T14:00:00Z", "losses": 11, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-4419230379dcd41e", "rated_matches": 42, "raw_elo_rating": 1666.7344489808431, "reasoning": "low", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "low", "repair_status": "first_pass", "score": 64.10344331483314, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 31 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 0, "generated_at": "2026-07-21T14:43:57Z", "losses": 18, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-4a1443311507f194", "rated_matches": 36, "raw_elo_rating": 1546.5622745419068, "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": 49.53027058545425, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 0, "generated_at": "2026-07-21T14:20:15Z", "losses": 14, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-91be72471ad409b6", "rated_matches": 42, "raw_elo_rating": 1641.280898786558, "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": 61.13432435083197, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 45, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 0, "generated_at": "2026-07-17T22:08:39Z", "losses": 20, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-95ac38f534c0080f", "rated_matches": 45, "raw_elo_rating": 1510.4006181260008, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "score": 46.10327191283094, "uncertainty": 29.97097807744857, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 24, "model": "nex-agi/nex-n2-pro", "point_rating_method": "sequential_elo", "public_id": "E-5f76f577111bee8d", "rated_matches": 32, "raw_elo_rating": 1337.024714262499, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 24.63642330230389, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 86, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 43, "draws": 0, "generated_at": "2026-07-11T17:22:09Z", "losses": 46, "model": "nex-agi/nex-n2-pro", "point_rating_method": "sequential_elo", "public_id": "E-962a9da8812a74d4", "rated_matches": 86, "raw_elo_rating": 1467.516113452013, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 42.97799867637564, "uncertainty": 9.855626741889738, "unilateral_faults": 0, "wins": 40 }, { "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": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-4477e0de2e04aad4", "rated_matches": 50, "raw_elo_rating": 1540.701516438078, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 49.983757275316115, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 33 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 30, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-48ed5c5e00ef38fb", "rated_matches": 38, "raw_elo_rating": 1303.4501134184768, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 21.370871310899688, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-11T17:22:09Z", "losses": 25, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-da3b98638ff53ea9", "rated_matches": 38, "raw_elo_rating": 1360.358923076814, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 28.009199743891315, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 32, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-343b92f3dda3dcb5", "rated_matches": 68, "raw_elo_rating": 1502.312238039986, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 46.42219609913933, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 36 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 0, "generated_at": "2026-07-03T16:00:00Z", "losses": 25, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-4fc62dc65156d576", "rated_matches": 46, "raw_elo_rating": 1464.7366162584292, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 40.85021390602501, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 0, "generated_at": "2026-07-21T14:20:15Z", "losses": 12, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-b556333d605791f4", "rated_matches": 42, "raw_elo_rating": 1632.2043690442968, "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": 60.075560587845395, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 30 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 0, "generated_at": "2026-07-21T14:20:15Z", "losses": 22, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-172336d3fd38632a", "rated_matches": 42, "raw_elo_rating": 1403.3905933062547, "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": 33.3847722466155, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 29, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-5ef540286ecbb63d", "rated_matches": 62, "raw_elo_rating": 1444.0802873129855, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 39.3681250027, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 33 }, { "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": 20, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-1ca53619662c7f6f", "rated_matches": 70, "raw_elo_rating": 1710.148150878068, "reasoning": "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": 70.74562745316447, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 50 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 36, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-21623e96b2b104e9", "rated_matches": 66, "raw_elo_rating": 1395.5116389588086, "reasoning": "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": 33.88084294690067, "uncertainty": 17.33472217815261, "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": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-53ce0020411c86d4", "rated_matches": 0, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "first_pass", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-62e15a037ee860c1", "rated_matches": 0, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 19, "model": "qwen/qwen3.7-max", "point_rating_method": "sequential_elo", "public_id": "E-435ec29661cdc285", "rated_matches": 34, "raw_elo_rating": 1513.158475478824, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 45.41764683991974, "uncertainty": 40.76542547285167, "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": "2026-07-02T16:51:45Z", "losses": 36, "model": "qwen/qwen3.7-max", "point_rating_method": "sequential_elo", "public_id": "E-c577c41440c17864", "rated_matches": 68, "raw_elo_rating": 1535.2272824362703, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 50.261687320285, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 20, "model": "qwen/qwen3.7-plus", "point_rating_method": "sequential_elo", "public_id": "E-6cc7454f585005c4", "rated_matches": 44, "raw_elo_rating": 1492.0034128052926, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 43.881245652912995, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 24 }, { "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": 38, "model": "qwen/qwen3.7-plus", "point_rating_method": "sequential_elo", "public_id": "E-94daaf1196d89c6c", "rated_matches": 72, "raw_elo_rating": 1414.093697253425, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 36.28769585919104, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 22, "model": "stepfun/step-3.7-flash", "point_rating_method": "sequential_elo", "public_id": "E-358338a9fbdbcb6a", "rated_matches": 38, "raw_elo_rating": 1467.120892265347, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 40.4628254633776, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 16 }, { "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": 24, "model": "stepfun/step-3.7-flash", "point_rating_method": "sequential_elo", "public_id": "E-386b7a319dfe25ad", "rated_matches": 42, "raw_elo_rating": 1409.8102664408416, "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": 34.13361761793311, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 24, "model": "stepfun/step-3.7-flash", "point_rating_method": "sequential_elo", "public_id": "E-7b9b33921ba865f5", "rated_matches": 56, "raw_elo_rating": 1572.4768033532573, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 54.04373188325387, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugin_count": 1, "attempted_matches": 90, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 45, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 58, "model": "tencent/hy3-preview", "point_rating_method": "sequential_elo", "public_id": "E-1bb81f8a4ae78954", "rated_matches": 90, "raw_elo_rating": 1354.5945266252224, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 29.9170413033881, "uncertainty": 8.664241836095918, "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": "2026-07-03T19:10:00Z", "losses": 20, "model": "tencent/hy3-preview", "point_rating_method": "sequential_elo", "public_id": "E-92dc0ac61d798488", "rated_matches": 46, "raw_elo_rating": 1503.968198223127, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 45.426519887314186, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 36, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-01a1df4eac0e6aef", "rated_matches": 66, "raw_elo_rating": 1350.1703423314248, "reasoning": "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": 28.591847791364597, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 30 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 40, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-0f05573125dedc2b", "rated_matches": 72, "raw_elo_rating": 1436.418304167105, "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": 38.89182821971972, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 42, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-ae60ed096a69eeff", "rated_matches": 70, "raw_elo_rating": 1390.450499005188, "reasoning": "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": 33.453369450760626, "uncertainty": 15.58908290969266, "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": "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": 72, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 47, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-f7a1d86c7e241f8d", "rated_matches": 72, "raw_elo_rating": 1465.2847904158946, "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": 42.25906112401628, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugin_count": 1, "attempted_matches": 84, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 42, "draws": 0, "generated_at": "2026-07-24T14:00:00Z", "losses": 31, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-824ec3caceabd338", "rated_matches": 84, "raw_elo_rating": 1649.6080495823956, "reasoning": "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": 64.16024381524471, "uncertainty": 10.482614454664043, "unilateral_faults": 0, "wins": 53 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-18T00:06:00Z", "losses": 20, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-87d1c39ddc685d7b", "rated_matches": 38, "raw_elo_rating": 1526.5340720250022, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 47.39328496272123, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 0, "generated_at": "2026-07-18T00:06:00Z", "losses": 18, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-9f28818a3063ee74", "rated_matches": 64, "raw_elo_rating": 1752.648082819719, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 75.45324729462128, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 46 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 0, "generated_at": "2026-07-18T00:06:00Z", "losses": 23, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-bd7fcc801178eba2", "rated_matches": 48, "raw_elo_rating": 1509.86634976789, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 46.25487497409825, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 0, "generated_at": "2026-07-18T00:06:00Z", "losses": 26, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-c0bc4ff29a3cbf96", "rated_matches": 66, "raw_elo_rating": 1704.7531988551875, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 69.95341329317, "uncertainty": 17.33472217815261, "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": "2026-07-24T14:00:00Z", "losses": 18, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-f1d32edccc2b8ba2", "rated_matches": 42, "raw_elo_rating": 1585.4726493848916, "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": 54.62437464317196, "uncertainty": 32.49928516630233, "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": "2026-07-21T14:20:15Z", "losses": 3, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-fcfafa8fb4ccd299", "rated_matches": 42, "raw_elo_rating": 1828.4405960558256, "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": 82.96622607838233, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 39 }, { "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": 1586.0835428623882, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 54.33964261459866, "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": 28, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-09d406abc15f7c9a", "rated_matches": 68, "raw_elo_rating": 1600.1680494446266, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 57.836931692466315, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 40 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 0, "generated_at": "2026-07-01T00:15:48Z", "losses": 42, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-9490f08c56c27d13", "rated_matches": 68, "raw_elo_rating": 1324.696058522038, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 25.70353159478331, "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": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 18, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-ad48cf51fe7da3cc", "rated_matches": 38, "raw_elo_rating": 1474.0777369811203, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 41.27433110473413, "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": "2026-07-02T06:10:40Z", "losses": 33, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-be8fc9653466bbe1", "rated_matches": 68, "raw_elo_rating": 1428.7666841039816, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 37.843216065211045, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 35 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 20, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-faaa866ee28d6401", "rated_matches": 34, "raw_elo_rating": 1432.5369643456804, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 36.01326686994626, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 22, "model": "xiaomi/mimo-v2.5-pro", "point_rating_method": "sequential_elo", "public_id": "E-9c228ad72a159b33", "rated_matches": 36, "raw_elo_rating": 1436.26694114023, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 36.66448315917693, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 14 }, { "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": 48, "model": "xiaomi/mimo-v2.5-pro", "point_rating_method": "sequential_elo", "public_id": "E-af55f57b03605914", "rated_matches": 82, "raw_elo_rating": 1349.7941697138317, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 29.12678637185235, "uncertainty": 11.132129994845172, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 0, "generated_at": "2026-07-01T00:15:48Z", "losses": 19, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-1a8c2012f200fd88", "rated_matches": 48, "raw_elo_rating": 1641.0847219724617, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 61.56130391482155, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 0, "generated_at": "2026-07-11T14:00:45Z", "losses": 40, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-235e4beedf22bc99", "rated_matches": 72, "raw_elo_rating": 1565.520646932364, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 53.95142545764748, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 32 }, { "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": 24, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-38e323f4ce233fa1", "rated_matches": 48, "raw_elo_rating": 1444.1826238143783, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 38.592965540395134, "uncertainty": 27.67857142857143, "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": "2026-07-11T17:22:09Z", "losses": 25, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-3916ba303b2ff700", "rated_matches": 48, "raw_elo_rating": 1541.8603284877404, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 49.98692524708084, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 39, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-503ecd021099d8f9", "rated_matches": 66, "raw_elo_rating": 1422.304523945283, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 37.006193332463226, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 27 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 31, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-51c8f79c1671819e", "rated_matches": 72, "raw_elo_rating": 1571.046296112905, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 54.59598425770226, "uncertainty": 14.770573598065289, "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": "2026-07-01T00:15:48Z", "losses": 28, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-6370c4b68d38a97e", "rated_matches": 48, "raw_elo_rating": 1369.1095988048637, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 29.8358082660935, "uncertainty": 27.67857142857143, "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": "2026-07-02T06:10:40Z", "losses": 28, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-a6655b3c71893984", "rated_matches": 48, "raw_elo_rating": 1423.806776959368, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 36.21615315693525, "uncertainty": 27.67857142857143, "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": "2026-07-02T16:51:45Z", "losses": 22, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-d8655d29a4806df8", "rated_matches": 48, "raw_elo_rating": 1582.8898901773864, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 54.77296290263492, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 26 } ], "GB2-06": [ { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 9, "generated_at": "2026-07-02T16:51:45Z", "losses": 11, "model": "claude-fable-5", "point_rating_method": "sequential_elo", "public_id": "E-499fbc92ee0778fb", "rated_matches": 58, "raw_elo_rating": 1705.5493909205152, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 80.12004893199418, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 38 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 25, "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": 50, "raw_elo_rating": 1656.6232412385289, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 73.07850759598226, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 30 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 3, "losses": 19, "model": "claude-opus-4-5", "point_rating_method": "sequential_elo", "public_id": "E-1ff6d6f973c7157d", "rated_matches": 46, "raw_elo_rating": 1497.0547906982, "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": 51.511920225446495, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 24 }, { "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": 35, "model": "claude-opus-4-5", "point_rating_method": "sequential_elo", "public_id": "E-40a259ca8a40b5b4", "rated_matches": 64, "raw_elo_rating": 1471.0980280128524, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 49.2174811242672, "uncertainty": 18.26736729460423, "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": "2026-07-02T16:51:45Z", "losses": 0, "model": "claude-opus-4-5", "point_rating_method": "sequential_elo", "public_id": "E-41f8f2b491917557", "rated_matches": 0, "reasoning": "legacy_shared_thinking_budget", "reasoning_bracket": "highest", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "budget", "reasoning_setting": "legacy_shared_thinking_budget", "repair_status": "repaired", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 0, "model": "claude-opus-4-5", "point_rating_method": "sequential_elo", "public_id": "E-8e040f66441f7747", "rated_matches": 0, "reasoning": "legacy_shared_thinking_budget", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "budget", "reasoning_setting": "legacy_shared_thinking_budget", "repair_status": "first_pass", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 6, "losses": 19, "model": "claude-opus-4-5", "point_rating_method": "sequential_elo", "public_id": "E-df9bde92610963b7", "rated_matches": 46, "raw_elo_rating": 1481.726873918583, "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": 49.47013990825629, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 1, "generated_at": "2026-07-02T16:51:45Z", "losses": 21, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-39e283268f14261d", "rated_matches": 58, "raw_elo_rating": 1683.650875040015, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 77.20302117516688, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 36 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 3, "generated_at": "2026-07-02T16:51:45Z", "losses": 31, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-db414178442322d3", "rated_matches": 68, "raw_elo_rating": 1511.7733406383302, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 54.83012501610077, "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": 3, "generated_at": "2026-07-03T17:20:00Z", "losses": 16, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-e804041031295d93", "rated_matches": 56, "raw_elo_rating": 1703.484096247477, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 79.72428872775545, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 37 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 13, "generated_at": "2026-07-25T10:50:00Z", "losses": 7, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-ca8985adf5006428", "rated_matches": 56, "raw_elo_rating": 1774.1459218022244, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 89.13691320039523, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 36 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 3, "generated_at": "2026-07-02T16:51:45Z", "losses": 32, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-01597b81edc004dd", "rated_matches": 68, "raw_elo_rating": 1477.208213223521, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 50.22582047612717, "uncertainty": 16.4429265428846, "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": "2026-07-02T16:51:45Z", "losses": 22, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-500304c7462c6005", "rated_matches": 44, "raw_elo_rating": 1514.184208348665, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 53.62283719668116, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 84, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 42, "draws": 10, "generated_at": "2026-07-03T16:50:00Z", "losses": 33, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-51f3682dc3b76107", "rated_matches": 84, "raw_elo_rating": 1514.0458901456975, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 55.76800622889098, "uncertainty": 10.482614454664043, "unilateral_faults": 0, "wins": 41 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 1, "generated_at": "2026-07-02T16:51:45Z", "losses": 25, "model": "cohere/north-mini-code", "point_rating_method": "sequential_elo", "public_id": "E-78dfcb6ce8b3efaa", "rated_matches": 32, "raw_elo_rating": 1301.5429160745794, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "first_pass", "score": 23.96519429729421, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 6 }, { "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": 46, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-5f5fd61f4544b8d7", "rated_matches": 68, "raw_elo_rating": 1323.215703235196, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 29.712995386485055, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 22 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 2, "generated_at": "2026-07-02T06:10:40Z", "losses": 24, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-6f20412107151172", "rated_matches": 42, "raw_elo_rating": 1378.06013360163, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 35.30758687991579, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 0, "generated_at": "2026-07-01T00:15:48Z", "losses": 33, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-8daa317358045ed1", "rated_matches": 54, "raw_elo_rating": 1357.6100610068163, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 33.52439839431363, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 0, "generated_at": "2026-07-01T00:15:48Z", "losses": 31, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-d8ca2fcf88af96c7", "rated_matches": 44, "raw_elo_rating": 1268.5345160222116, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 20.90066666774462, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 13 }, { "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": 46, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-db0efb02339d9e80", "rated_matches": 60, "raw_elo_rating": 1201.9135524183437, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 13.147076218822994, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 43, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-f527097ad30176f4", "rated_matches": 60, "raw_elo_rating": 1339.904328244146, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 31.52836404063522, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 6, "generated_at": "2026-07-02T16:51:45Z", "losses": 12, "model": "deepseek/deepseek-v4-pro", "point_rating_method": "sequential_elo", "public_id": "E-945bebaa34963e03", "rated_matches": 60, "raw_elo_rating": 1674.832336171311, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 76.1429991599217, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 42 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 2, "generated_at": "2026-07-02T16:51:45Z", "losses": 34, "model": "deepseek/deepseek-v4-pro", "point_rating_method": "sequential_elo", "public_id": "E-c9778645f1bbd12c", "rated_matches": 62, "raw_elo_rating": 1418.4552403692137, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 42.10102860564115, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 35, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 30, "model": "google/gemini-3.1-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-6238c7d8dc9e77d9", "rated_matches": 35, "raw_elo_rating": 1274.142055028033, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 20.710094817582146, "uncertainty": 39.583333333333336, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 35, "model": "google/gemini-3.1-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-a10101fbca309818", "rated_matches": 58, "raw_elo_rating": 1407.6659693492472, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 40.43999875124963, "uncertainty": 21.344455490411935, "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": "2026-07-02T16:51:45Z", "losses": 19, "model": "google/gemini-3.1-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-dc1c0f46738d1091", "rated_matches": 42, "raw_elo_rating": 1423.8254161871469, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 41.40382647576317, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 22 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "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": 52, "raw_elo_rating": 1734.2297854950075, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 83.55834325082338, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 31 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 6, "generated_at": "2026-07-02T16:51:45Z", "losses": 11, "model": "google/gemini-3.5-flash", "point_rating_method": "sequential_elo", "public_id": "E-5dcb27eaa0273049", "rated_matches": 36, "raw_elo_rating": 1612.9721687195993, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 65.96534432177022, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-21T14:20:15Z", "losses": 0, "model": "google/gemini-3.5-flash", "point_rating_method": "sequential_elo", "public_id": "E-6537016fe84c175c", "rated_matches": 0, "reasoning": "low", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "low", "repair_status": "repaired", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 1, "generated_at": "2026-07-24T13:40:00Z", "losses": 38, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-100ff33157ca87e5", "rated_matches": 64, "raw_elo_rating": 1330.8077323554674, "reasoning": "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": 30.52988198835926, "uncertainty": 18.26736729460423, "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-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": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 1, "generated_at": "2026-07-24T13:40:00Z", "losses": 34, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-92d447632fa55355", "rated_matches": 64, "raw_elo_rating": 1486.224379305521, "reasoning": "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": 51.2324115798752, "uncertainty": 18.26736729460423, "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-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": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 10, "generated_at": "2026-07-24T13:40:00Z", "losses": 26, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-aa5fab059f4d0186", "rated_matches": 66, "raw_elo_rating": 1548.9340975746195, "reasoning": "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": 59.68515016624557, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 30 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-bb2e288b40b1a588", "rated_matches": 0, "reasoning": "minimal", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "minimal", "repair_status": "first_pass", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 4, "generated_at": "2026-07-24T13:40:00Z", "losses": 14, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-dd9886be3d9e45b5", "rated_matches": 66, "raw_elo_rating": 1851.5830446880557, "reasoning": "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": 17.33472217815261, "unilateral_faults": 0, "wins": 48 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 23, "model": "google/gemma-4-31b-it", "point_rating_method": "sequential_elo", "public_id": "E-41987f96551bf9d3", "rated_matches": 32, "raw_elo_rating": 1347.8582691700228, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 30.134706938421203, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 34, "model": "google/gemma-4-31b-it", "point_rating_method": "sequential_elo", "public_id": "E-da266f7bbd330107", "rated_matches": 58, "raw_elo_rating": 1390.6201022386813, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 38.16937604000977, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 8, "generated_at": "2026-07-02T16:51:45Z", "losses": 16, "model": "gpt-4.1", "point_rating_method": "sequential_elo", "public_id": "E-4dcd6d3653c67437", "rated_matches": 44, "raw_elo_rating": 1506.0471700351973, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 52.53892965023924, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 3, "generated_at": "2026-07-02T16:51:45Z", "losses": 15, "model": "gpt-5", "point_rating_method": "sequential_elo", "public_id": "E-1b082700b3692175", "rated_matches": 42, "raw_elo_rating": 1579.3828175389745, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 62.12510548843214, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 7, "generated_at": "2026-07-02T16:51:45Z", "losses": 25, "model": "gpt-5", "point_rating_method": "sequential_elo", "public_id": "E-816d262cd933cdb9", "rated_matches": 54, "raw_elo_rating": 1499.5581163462753, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 52.43282213007789, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 22 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 6, "generated_at": "2026-07-02T16:51:45Z", "losses": 15, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-00a57c19a4229948", "rated_matches": 58, "raw_elo_rating": 1638.165952256158, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 71.14412736694287, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 37 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 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": 54, "raw_elo_rating": 1795.322614521401, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 91.83061764137966, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 39 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 8, "generated_at": "2026-07-02T16:51:45Z", "losses": 9, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-6e5bbab022d4d9fa", "rated_matches": 54, "raw_elo_rating": 1779.224826819665, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 89.6862854041758, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 37 }, { "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": 1424.1759694354694, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 43.72752008171095, "uncertainty": 11.132129994845172, "unilateral_faults": 0, "wins": 35 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 8, "generated_at": "2026-07-02T06:10:40Z", "losses": 16, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-0b7e07d12feb8fb5", "rated_matches": 58, "raw_elo_rating": 1635.094107106265, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 70.73493719095964, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 37, "draws": 4, "generated_at": "2026-07-02T16:51:45Z", "losses": 36, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-144154b792c9e9a6", "rated_matches": 74, "raw_elo_rating": 1430.085237613073, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 44.210653995549066, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 5, "generated_at": "2026-07-02T16:51:45Z", "losses": 19, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-3ccfe46cbdc271eb", "rated_matches": 54, "raw_elo_rating": 1502.0217575555882, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 52.76099550171851, "uncertainty": 23.66998624632421, "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": "2026-07-01T00:15:48Z", "losses": 33, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-ac7c887de3c2e7af", "rated_matches": 70, "raw_elo_rating": 1582.8885785230168, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 64.39413713675378, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 37 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 1, "generated_at": "2026-07-02T06:10:40Z", "losses": 27, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-e726e4bfd20b0da9", "rated_matches": 58, "raw_elo_rating": 1362.71123706275, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 34.451729838595895, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 30 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 39, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-eca073d7ce610515", "rated_matches": 62, "raw_elo_rating": 1447.969206663917, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 46.032484936541564, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 2, "generated_at": "2026-07-02T06:10:40Z", "losses": 21, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-3d7e23d6ea4c2792", "rated_matches": 62, "raw_elo_rating": 1615.1312453994922, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 68.29957872227698, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 39 }, { "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": 1574.870566908514, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 62.59211241806533, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 5, "generated_at": "2026-07-02T06:10:40Z", "losses": 34, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-962a93f9cc008820", "rated_matches": 70, "raw_elo_rating": 1498.7809459308949, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 53.190441864841645, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 31 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 8, "generated_at": "2026-07-01T00:15:48Z", "losses": 29, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-9b6b064b63e4164b", "rated_matches": 56, "raw_elo_rating": 1502.5118592815368, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 52.95345198336451, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 78, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 39, "draws": 2, "generated_at": "2026-07-09T17:30:50Z", "losses": 35, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-9c5263dcfd4c2ec7", "rated_matches": 78, "raw_elo_rating": 1498.797118661646, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 53.52131690856485, "uncertainty": 12.5043950463012, "unilateral_faults": 0, "wins": 41 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 0, "generated_at": "2026-07-09T17:30:50Z", "losses": 38, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-a1fb59d78d39d217", "rated_matches": 66, "raw_elo_rating": 1396.2987934543962, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 39.3531139122755, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 28 }, { "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": 18, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-d5866895bf388f66", "rated_matches": 60, "raw_elo_rating": 1646.446024495557, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 72.36175391371486, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 42 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 5, "generated_at": "2026-07-02T06:10:40Z", "losses": 19, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-f9bb09fb2842dd1f", "rated_matches": 56, "raw_elo_rating": 1693.7457177478934, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 78.42707203303546, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 32, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-1ea2c2c23d752166", "rated_matches": 58, "raw_elo_rating": 1450.542154271933, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 46.151391350129174, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "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": 66, "raw_elo_rating": 1718.0303169897015, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 82.20988966457762, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 38 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 13, "generated_at": "2026-07-10T05:30:29Z", "losses": 15, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-9eafeacabdedfdba", "rated_matches": 56, "raw_elo_rating": 1679.089981134785, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 76.4748305783871, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 46, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-ae522f9c5c491f57", "rated_matches": 56, "raw_elo_rating": 1174.1929957595082, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 9.219198794244829, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 6, "generated_at": "2026-07-10T10:07:13Z", "losses": 24, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-f4c50b1a9cf2c2e6", "rated_matches": 58, "raw_elo_rating": 1593.8608666300522, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 65.24239570415726, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 84, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 42, "draws": 1, "generated_at": "2026-07-10T05:30:29Z", "losses": 49, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-992b9a5ebbb74c80", "rated_matches": 84, "raw_elo_rating": 1406.6038581939165, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 41.45601398414009, "uncertainty": 10.482614454664043, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 9, "generated_at": "2026-07-10T10:07:13Z", "losses": 13, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-acdece52463a2698", "rated_matches": 54, "raw_elo_rating": 1677.6556396548986, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 76.15659509023824, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 6, "generated_at": "2026-07-10T05:30:29Z", "losses": 21, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-eb315c759774ef38", "rated_matches": 56, "raw_elo_rating": 1676.3558507059174, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 76.11062624621614, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 1, "generated_at": "2026-07-10T05:30:29Z", "losses": 42, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-22ffdca36d9bac9c", "rated_matches": 72, "raw_elo_rating": 1356.4473281980904, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 34.31788335875319, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 9, "generated_at": "2026-07-10T05:30:29Z", "losses": 19, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-a3722334e358f0fe", "rated_matches": 56, "raw_elo_rating": 1498.4965294796054, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 52.41858338546655, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 78, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 39, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 29, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-e6571a10c1120fab", "rated_matches": 78, "raw_elo_rating": 1635.2207187307338, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 71.69384651100232, "uncertainty": 12.5043950463012, "unilateral_faults": 0, "wins": 49 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 3, "generated_at": "2026-07-24T13:40:00Z", "losses": 36, "model": "inclusionai/ling-3.0-flash", "point_rating_method": "sequential_elo", "public_id": "E-6807fffacebac165", "rated_matches": 66, "raw_elo_rating": 1384.4414912461937, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 37.77364250648877, "uncertainty": 17.33472217815261, "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": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 59, "model": "inclusionai/ling-3.0-flash", "point_rating_method": "sequential_elo", "public_id": "E-9bde0475193e2c4a", "rated_matches": 62, "raw_elo_rating": 1102.3972113195412, "reasoning": "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": 19.244078834871203, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 2, "generated_at": "2026-07-24T13:40:00Z", "losses": 40, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-3e8b2d11481a50d7", "rated_matches": 66, "raw_elo_rating": 1456.7679027076622, "reasoning": "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": 47.40800087744506, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "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": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 11, "generated_at": "2026-07-24T13:40:00Z", "losses": 28, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-e3023ff7ecf82fc4", "rated_matches": 68, "raw_elo_rating": 1533.2515897825635, "reasoning": "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": 57.69117045240684, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 23, "model": "minimax/minimax-m3", "point_rating_method": "sequential_elo", "public_id": "E-ef8c1a9fa3580f83", "rated_matches": 32, "raw_elo_rating": 1327.362474639063, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 27.40453098168996, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 27, "model": "mistralai/mistral-medium-3-5", "point_rating_method": "sequential_elo", "public_id": "E-6c35f5ff426e7ada", "rated_matches": 34, "raw_elo_rating": 1302.1263042354692, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 24.311812653475105, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 5, "generated_at": "2026-07-02T16:51:45Z", "losses": 34, "model": "mistralai/mistral-medium-3-5", "point_rating_method": "sequential_elo", "public_id": "E-cf0bc4a1e7a8d72a", "rated_matches": 64, "raw_elo_rating": 1330.3542233252822, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 30.469471573505537, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 3, "generated_at": "2026-07-17T22:36:00Z", "losses": 8, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-026a38fa3b1622ee", "rated_matches": 36, "raw_elo_rating": 1662.31724131217, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "score": 72.53843572214959, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "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": 32, "raw_elo_rating": 1731.7390831320631, "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": 81.270180947318, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 3, "generated_at": "2026-07-24T14:00:00Z", "losses": 16, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-1640f1438f9390d7", "rated_matches": 36, "raw_elo_rating": 1487.165419107651, "reasoning": "high", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 49.20704971327303, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 0, "generated_at": "2026-07-21T14:20:15Z", "losses": 5, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-2f8c760ee4329d00", "rated_matches": 36, "raw_elo_rating": 1759.3228885332007, "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": 85.46023220629932, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 31 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 3, "generated_at": "2026-07-17T22:36:00Z", "losses": 13, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-3f2124a8621f4c67", "rated_matches": 36, "raw_elo_rating": 1565.9239776958489, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "score": 59.69821280136425, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 25, "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": 50, "raw_elo_rating": 1504.3686423432716, "reasoning": "low", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "low", "repair_status": "first_pass", "score": 52.7971838064758, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 3, "generated_at": "2026-07-02T16:51:45Z", "losses": 21, "model": "nex-agi/nex-n2-pro", "point_rating_method": "sequential_elo", "public_id": "E-209380b737b62580", "rated_matches": 32, "raw_elo_rating": 1333.7245417304796, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 28.25200057267649, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 2, "generated_at": "2026-07-11T17:22:09Z", "losses": 43, "model": "nex-agi/nex-n2-pro", "point_rating_method": "sequential_elo", "public_id": "E-973417dedd770061", "rated_matches": 66, "raw_elo_rating": 1329.3201234614855, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 30.43111022257915, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 4, "generated_at": "2026-07-02T16:51:45Z", "losses": 26, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-1ea0c8193f35ca72", "rated_matches": 62, "raw_elo_rating": 1556.571475807063, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 60.49902848103273, "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": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 26, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-6e76a1c11ba24bc6", "rated_matches": 44, "raw_elo_rating": 1368.7430753287372, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 34.249112314196054, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 35, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 2, "generated_at": "2026-07-11T17:22:09Z", "losses": 19, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-ba2fb1c121873708", "rated_matches": 35, "raw_elo_rating": 1441.077477665935, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 42.947001834010294, "uncertainty": 39.583333333333336, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 4, "generated_at": "2026-07-03T16:00:00Z", "losses": 15, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-4162fe183e6383e1", "rated_matches": 36, "raw_elo_rating": 1473.8682311793768, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 47.435775966404, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 10, "generated_at": "2026-07-02T16:51:45Z", "losses": 24, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-69e964db7b91b1bb", "rated_matches": 60, "raw_elo_rating": 1533.5732183679058, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 57.32634647961873, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 1, "generated_at": "2026-07-21T14:20:15Z", "losses": 4, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-e4a4a86669325de4", "rated_matches": 36, "raw_elo_rating": 1768.0118763760397, "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": 86.61766309589059, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 31 }, { "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": 1547.9448102788183, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 58.87825112775808, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 1, "generated_at": "2026-07-21T14:20:15Z", "losses": 33, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-b75de88bfc62ab22", "rated_matches": 58, "raw_elo_rating": 1478.406710872713, "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": 49.8631353550523, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 24 }, { "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": 37, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-f225b6990e542d31", "rated_matches": 58, "raw_elo_rating": 1362.013744309396, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 34.35881917136978, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 2, "generated_at": "2026-07-24T13:40:00Z", "losses": 33, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-a29031412bc33c39", "rated_matches": 64, "raw_elo_rating": 1345.579754559503, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 32.49761345604342, "uncertainty": 18.26736729460423, "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": "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": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 36, "model": "qwen/qwen3.7-max", "point_rating_method": "sequential_elo", "public_id": "E-0c7e9f6c7d4cb892", "rated_matches": 56, "raw_elo_rating": 1341.8150715027673, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 31.547572564793132, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 2, "generated_at": "2026-07-02T16:51:45Z", "losses": 17, "model": "qwen/qwen3.7-max", "point_rating_method": "sequential_elo", "public_id": "E-8283efe6f68a787e", "rated_matches": 34, "raw_elo_rating": 1497.2801393778354, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 50.307599631372334, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 15 }, { "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": 47, "model": "qwen/qwen3.7-plus", "point_rating_method": "sequential_elo", "public_id": "E-2fb82a23fdec2792", "rated_matches": 64, "raw_elo_rating": 1346.5858526769046, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 32.63163240739917, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 5, "generated_at": "2026-07-02T16:51:45Z", "losses": 12, "model": "qwen/qwen3.7-plus", "point_rating_method": "sequential_elo", "public_id": "E-b6dd11ebe2b80c7b", "rated_matches": 32, "raw_elo_rating": 1552.0019476545383, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 57.328000756584736, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 24, "model": "stepfun/step-3.7-flash", "point_rating_method": "sequential_elo", "public_id": "E-2d684425ca56be18", "rated_matches": 36, "raw_elo_rating": 1377.7162538693242, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 34.627693984144734, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 1, "generated_at": "2026-07-02T16:51:45Z", "losses": 35, "model": "stepfun/step-3.7-flash", "point_rating_method": "sequential_elo", "public_id": "E-6526762dce98da7c", "rated_matches": 56, "raw_elo_rating": 1384.0385830541572, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 37.17202473580983, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-21T14:20:15Z", "losses": 25, "model": "stepfun/step-3.7-flash", "point_rating_method": "sequential_elo", "public_id": "E-8a88dceef8a0239c", "rated_matches": 38, "raw_elo_rating": 1359.2957907129323, "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": 32.401527305050784, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 29, "model": "tencent/hy3-preview", "point_rating_method": "sequential_elo", "public_id": "E-3627e3dbf7a48738", "rated_matches": 34, "raw_elo_rating": 1263.5377986641415, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 19.171567421318443, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 39, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-02be9616e86c7055", "rated_matches": 66, "raw_elo_rating": 1421.3056015259317, "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": 42.684186833033415, "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": "2026-07-24T13:40:00Z", "losses": 37, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-0825a2443d50c563", "rated_matches": 64, "raw_elo_rating": 1353.884883080069, "reasoning": "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": 33.60391173446151, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 27 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-56e54327930d2f64", "rated_matches": 0, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "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": 58, "raw_elo_rating": 1715.3059958637307, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 81.41969351005898, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 39 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "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": 38, "raw_elo_rating": 1570.6476467281004, "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": 60.55499824424813, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 80, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 40, "draws": 7, "generated_at": "2026-07-24T14:00:00Z", "losses": 41, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-3baaff3521870bef", "rated_matches": 80, "raw_elo_rating": 1482.1377042576466, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 51.37664431378333, "uncertainty": 11.805555555555554, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 4, "generated_at": "2026-07-24T14:00:00Z", "losses": 21, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-5a1e23bce371a184", "rated_matches": 44, "raw_elo_rating": 1507.7875135985614, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 52.77075497157389, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 2, "generated_at": "2026-07-17T22:36:00Z", "losses": 23, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-5bedcf6c046c3b54", "rated_matches": 52, "raw_elo_rating": 1562.2705478444366, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 60.65223070845501, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 27 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 3, "generated_at": "2026-07-17T22:36:00Z", "losses": 33, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-8cb8510a257ade6a", "rated_matches": 66, "raw_elo_rating": 1509.8353687552262, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 54.476939808739395, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 30 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "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": 38, "raw_elo_rating": 1571.930757481107, "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": 60.725917118478186, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 0, "generated_at": "2026-07-17T22:36:00Z", "losses": 21, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-cc9d4b5c56aea8b6", "rated_matches": 42, "raw_elo_rating": 1486.110635704911, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 49.700631390071806, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 21, "model": "x-ai/grok-build-0.1", "point_rating_method": "sequential_elo", "public_id": "E-133675db0ee21fd5", "rated_matches": 36, "raw_elo_rating": 1401.8647815875509, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 37.84443826147298, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 6, "generated_at": "2026-07-02T06:10:40Z", "losses": 19, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-51421c7ae2af8f7b", "rated_matches": 42, "raw_elo_rating": 1501.76159895558, "reasoning": "highest", "reasoning_bracket": "highest", "reasoning_setting": "highest", "repair_status": "repaired", "score": 51.785443642756896, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 3, "generated_at": "2026-07-02T16:51:45Z", "losses": 22, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-7b4c450b6850f156", "rated_matches": 32, "raw_elo_rating": 1337.069511253292, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 28.697572729119944, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 32, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-d572bc902e0e416b", "rated_matches": 54, "raw_elo_rating": 1371.8471393219586, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 35.420871783105014, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 22 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 45, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-d79ad8bc05d1b933", "rated_matches": 68, "raw_elo_rating": 1398.996868656436, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 39.807549930033865, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 0, "generated_at": "2026-07-01T00:15:48Z", "losses": 22, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-ff7683792b6b3363", "rated_matches": 60, "raw_elo_rating": 1605.0497655291583, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 66.84749728131351, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 38 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 17, "model": "xiaomi/mimo-v2.5-pro", "point_rating_method": "sequential_elo", "public_id": "E-530f82d65699c577", "rated_matches": 34, "raw_elo_rating": 1536.234900827742, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 55.49663257908679, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 17 }, { "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": 38, "model": "xiaomi/mimo-v2.5-pro", "point_rating_method": "sequential_elo", "public_id": "E-6b662c734cdcff91", "rated_matches": 72, "raw_elo_rating": 1453.7533405191086, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 47.279690469131054, "uncertainty": 14.770573598065289, "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": "2026-07-01T00:15:48Z", "losses": 35, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-18454080fac44f8c", "rated_matches": 42, "raw_elo_rating": 1190.1011190442018, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 10.270197789171506, "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": 4, "generated_at": "2026-07-11T14:00:45Z", "losses": 19, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-657c61c9039ce566", "rated_matches": 42, "raw_elo_rating": 1469.4176086881623, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 47.47700932275704, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 6, "generated_at": "2026-07-02T06:10:40Z", "losses": 19, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-6954e92d5890c32a", "rated_matches": 42, "raw_elo_rating": 1504.6005016612066, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 52.16360433804945, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 6, "generated_at": "2026-07-02T06:10:40Z", "losses": 15, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-72584b5bdb2d01e3", "rated_matches": 44, "raw_elo_rating": 1678.108239443182, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 75.45860685902264, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 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": 42, "raw_elo_rating": 1600.9472964442882, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 64.99763730161912, "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": 3, "generated_at": "2026-07-02T16:51:45Z", "losses": 18, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-ec1479c855f477b4", "rated_matches": 42, "raw_elo_rating": 1591.4136790455657, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 63.72769614547851, "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": 6, "generated_at": "2026-07-11T14:00:45Z", "losses": 17, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-f94d63d03c820dac", "rated_matches": 54, "raw_elo_rating": 1625.082997776762, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 69.153570024744, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 31 } ], "GB2-07": [ { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 25, "model": "claude-fable-5", "point_rating_method": "sequential_elo", "public_id": "E-babd82321b910e7b", "rated_matches": 62, "raw_elo_rating": 1604.40868111242, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 61.39391405879897, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 37 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 15, "model": "claude-fable-5", "point_rating_method": "sequential_elo", "public_id": "E-bc12a8303ec2def7", "rated_matches": 56, "raw_elo_rating": 1720.961634672591, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 75.98738578456185, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 41 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 33, "model": "claude-opus-4-5", "point_rating_method": "sequential_elo", "public_id": "E-ca22621c58b6f244", "rated_matches": 64, "raw_elo_rating": 1489.8456094590335, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 46.82415975623741, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 31 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 0, "losses": 22, "model": "claude-opus-4-5", "point_rating_method": "sequential_elo", "public_id": "E-e7848fdc8b4ffd95", "rated_matches": 40, "raw_elo_rating": 1473.496250165205, "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": 43.084461444723864, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 0, "losses": 20, "model": "claude-opus-4-5", "point_rating_method": "sequential_elo", "public_id": "E-e8719bed57f17312", "rated_matches": 40, "raw_elo_rating": 1489.6048435123837, "reasoning": "legacy_shared_thinking_budget", "reasoning_bracket": "intensive", "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "legacy_shared_thinking_budget", "repair_status": "first_pass", "score": 45.147167857390414, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 0, "model": "claude-opus-4-5", "point_rating_method": "sequential_elo", "public_id": "E-ed9657bcd9dfeda4", "rated_matches": 0, "reasoning": "legacy_shared_thinking_budget", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "budget", "reasoning_setting": "legacy_shared_thinking_budget", "repair_status": "first_pass", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 0, "model": "claude-opus-4-5", "point_rating_method": "sequential_elo", "public_id": "E-f2d7a3f3bae22998", "rated_matches": 0, "reasoning": "legacy_shared_thinking_budget", "reasoning_bracket": "highest", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "budget", "reasoning_setting": "legacy_shared_thinking_budget", "repair_status": "first_pass", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 20, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-0bf7b9ed307db853", "rated_matches": 58, "raw_elo_rating": 1658.4015620035889, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 68.09254323204925, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 38 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 0, "generated_at": "2026-07-03T17:20:00Z", "losses": 20, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-5e09cecd1172d99b", "rated_matches": 54, "raw_elo_rating": 1619.730475331812, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 62.90248060999168, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 25, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-76804598cce96e62", "rated_matches": 66, "raw_elo_rating": 1614.8782657464328, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 62.93013963759991, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 41 }, { "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": 1910.1513048995253, "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": 98.99816924724276, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 39 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 0, "generated_at": "2026-07-25T10:50:00Z", "losses": 4, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-54bca3ce32fa85ae", "rated_matches": 54, "raw_elo_rating": 1909.441531822003, "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": 23.66998624632421, "unilateral_faults": 0, "wins": 50 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 0, "generated_at": "2026-07-25T10:50:00Z", "losses": 19, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-914b104a64ab3110", "rated_matches": 54, "raw_elo_rating": 1742.0788730945349, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 78.56920080122724, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 35 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 0, "generated_at": "2026-07-25T10:50:00Z", "losses": 20, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-de5e72176c4f0dc9", "rated_matches": 56, "raw_elo_rating": 1765.129143808681, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 81.64303816605788, "uncertainty": 22.47661785325219, "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": "2026-07-03T16:50:00Z", "losses": 39, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-2146a36b46e938d6", "rated_matches": 66, "raw_elo_rating": 1413.3656681646023, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 37.12643857527608, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 27 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 30, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-9e40526fba9fa8b9", "rated_matches": 66, "raw_elo_rating": 1489.3871953975538, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 46.86100001987165, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 36 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 20, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-cd6f193a087d8c8d", "rated_matches": 44, "raw_elo_rating": 1564.596224581565, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 55.113612498782416, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 18, "model": "cohere/north-mini-code", "point_rating_method": "sequential_elo", "public_id": "E-1c961fde1b53f0eb", "rated_matches": 36, "raw_elo_rating": 1490.8332481397597, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 44.88316889166992, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 41, "model": "cohere/north-mini-code", "point_rating_method": "sequential_elo", "public_id": "E-3b908f26a42804a4", "rated_matches": 70, "raw_elo_rating": 1445.8745630141473, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 41.46802802496643, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 0, "generated_at": "2026-07-11T17:22:09Z", "losses": 56, "model": "cohere/north-mini-code", "point_rating_method": "sequential_elo", "public_id": "E-c7f5dc6d5d3c2a8d", "rated_matches": 70, "raw_elo_rating": 1212.5244825073055, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 11.5875352293604, "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": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 37, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-20285efe5ad468c1", "rated_matches": 64, "raw_elo_rating": 1414.8050025004843, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 37.21520521577782, "uncertainty": 18.26736729460423, "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": "2026-07-01T00:15:48Z", "losses": 33, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-8f2f6c973751f183", "rated_matches": 44, "raw_elo_rating": 1386.7591014543962, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 32.341557460914714, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "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": 1389.6179735971475, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 34.1769003514353, "uncertainty": 16.4429265428846, "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": "2026-07-02T16:51:45Z", "losses": 40, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-c394c0713cfcfaa4", "rated_matches": 72, "raw_elo_rating": 1434.5302003634831, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 40.09922979490467, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugin_count": 1, "attempted_matches": 76, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 38, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 41, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-c8fd55a5d257c569", "rated_matches": 76, "raw_elo_rating": 1408.808537777866, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 36.96335616112706, "uncertainty": 13.230288229818967, "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": "2026-07-02T16:51:45Z", "losses": 25, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-ecf2a6ea6f9fe06c", "rated_matches": 60, "raw_elo_rating": 1615.0471532159254, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 62.651235487949734, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 35 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 27, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-edc2d085c4253ed3", "rated_matches": 46, "raw_elo_rating": 1482.2601478061813, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 44.73469458474547, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 36, "model": "deepseek/deepseek-v4-pro", "point_rating_method": "sequential_elo", "public_id": "E-f398fd6ac8c8bada", "rated_matches": 70, "raw_elo_rating": 1591.641725509094, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 60.13352254421294, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 31, "model": "deepseek/deepseek-v4-pro", "point_rating_method": "sequential_elo", "public_id": "E-f76d96b0f3163d4b", "rated_matches": 66, "raw_elo_rating": 1443.3127110418286, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 40.96115933902756, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 35 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 26, "model": "google/gemini-3.1-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-0d43f308cfa4da52", "rated_matches": 38, "raw_elo_rating": 1405.0073937310488, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 34.1119149241441, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 46, "model": "google/gemini-3.1-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-1b3c52da51dfbdd4", "rated_matches": 56, "raw_elo_rating": 1176.0530232290791, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 6.21180309294096, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 10 }, { "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": 40, "model": "google/gemini-3.1-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-3d6a15fe821fe6ad", "rated_matches": 44, "raw_elo_rating": 1134.1894705301404, "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": 30.785599249992988, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 26, "model": "google/gemini-3.5-flash", "point_rating_method": "sequential_elo", "public_id": "E-5447c508e2b0ab6c", "rated_matches": 54, "raw_elo_rating": 1477.2974094270803, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 44.66391737325167, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-21T14:20:15Z", "losses": 0, "model": "google/gemini-3.5-flash", "point_rating_method": "sequential_elo", "public_id": "E-610847658aa43657", "rated_matches": 0, "reasoning": "low", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "low", "repair_status": "repaired", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 20, "model": "google/gemini-3.5-flash", "point_rating_method": "sequential_elo", "public_id": "E-f7f306cca2bb9532", "rated_matches": 38, "raw_elo_rating": 1599.944227917813, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 59.07358906140703, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 36, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-2950a4947ff48aa6", "rated_matches": 64, "raw_elo_rating": 1302.173020784396, "reasoning": "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": 22.792672723342108, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "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": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 43, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-42943e41c64d22d2", "rated_matches": 66, "raw_elo_rating": 1222.9692098369603, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 12.746159858375425, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-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": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 32, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-5f208f03ea700603", "rated_matches": 68, "raw_elo_rating": 1492.3363740837954, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 47.32999813075001, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 36 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 26, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-65c6c8e09fe2c210", "rated_matches": 70, "raw_elo_rating": 1442.8756213391898, "reasoning": "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": 41.084013350883716, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 44 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-8e9b51be911dad38", "rated_matches": 0, "reasoning": "minimal", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "minimal", "repair_status": "first_pass", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-a2d90fcdc2f4ef9d", "rated_matches": 0, "reasoning": "minimal", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "minimal", "repair_status": "first_pass", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 37, "model": "google/gemma-4-31b-it", "point_rating_method": "sequential_elo", "public_id": "E-3f820f7e8ff15839", "rated_matches": 60, "raw_elo_rating": 1350.8159516092887, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 28.816413152201964, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 17, "model": "google/gemma-4-31b-it", "point_rating_method": "sequential_elo", "public_id": "E-f417d302c870dfa6", "rated_matches": 36, "raw_elo_rating": 1459.4391274346103, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 40.86314971911562, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 19 }, { "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": 20, "model": "gpt-4.1", "point_rating_method": "sequential_elo", "public_id": "E-fcfa606d3cbb0ba0", "rated_matches": 46, "raw_elo_rating": 1507.3262272831655, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 47.944407671620375, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 21, "model": "gpt-5", "point_rating_method": "sequential_elo", "public_id": "E-15dad0db253c0497", "rated_matches": 46, "raw_elo_rating": 1534.7451158394265, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 51.45539811220371, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 25, "model": "gpt-5", "point_rating_method": "sequential_elo", "public_id": "E-4d8b4cfcff519db6", "rated_matches": 66, "raw_elo_rating": 1570.8705167678413, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 57.29494455453205, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 41 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-21T14:20:15Z", "losses": 0, "model": "gpt-5", "point_rating_method": "sequential_elo", "public_id": "E-a67f59519ca31035", "rated_matches": 0, "reasoning": "low", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "low", "repair_status": "first_pass", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 24, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-22466ae84d7027e5", "rated_matches": 58, "raw_elo_rating": 1565.920523238979, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 56.25034027872709, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 6, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-80aa3ec3ac4ad97f", "rated_matches": 64, "raw_elo_rating": 1841.7924577346591, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 91.89097628140996, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 58 }, { "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": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-c8176c382cf75e88", "rated_matches": 76, "raw_elo_rating": 1369.3333503741408, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 31.908555878820593, "uncertainty": 13.230288229818967, "unilateral_faults": 0, "wins": 33 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "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-022243613d51f0fb", "rated_matches": 66, "raw_elo_rating": 1362.071311220552, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 30.55819287425519, "uncertainty": 17.33472217815261, "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": "2026-07-02T06:10:40Z", "losses": 21, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-1b33882368041bb3", "rated_matches": 62, "raw_elo_rating": 1625.5679651607013, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 64.1033617401179, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 41 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 48, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-6a87ebc54bdde781", "rated_matches": 64, "raw_elo_rating": 1250.3650623117942, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 16.15866031360461, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 69, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 0, "generated_at": "2026-07-01T00:15:48Z", "losses": 40, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-946bc9bcbefb4ad1", "rated_matches": 69, "raw_elo_rating": 1448.845291037242, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 41.80516463367432, "uncertainty": 16.01143046671968, "unilateral_faults": 0, "wins": 29 }, { "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": 38, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-b96fbceba82aa188", "rated_matches": 68, "raw_elo_rating": 1511.1183237689709, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 49.73502799419104, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 30 }, { "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": 46, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-c2ab31787514c10c", "rated_matches": 62, "raw_elo_rating": 1263.5146220810454, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 17.742407906208506, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 29, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-e453890c6dd35fa3", "rated_matches": 64, "raw_elo_rating": 1655.8031190639394, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 68.0750295196216, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 35 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 28, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-f4d7ac8a0f5d2974", "rated_matches": 58, "raw_elo_rating": 1503.1946272282405, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 48.218285266036176, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 30 }, { "admitted_plugin_count": 1, "attempted_matches": 80, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 40, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 47, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-4e14ae758717169e", "rated_matches": 80, "raw_elo_rating": 1450.3222942234418, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 42.42514502852104, "uncertainty": 11.805555555555554, "unilateral_faults": 0, "wins": 33 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 47, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-acb1779a65c941b4", "rated_matches": 54, "raw_elo_rating": 1180.574922681668, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 6.668583888759279, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 0, "generated_at": "2026-07-09T17:30:50Z", "losses": 32, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-b9e3f57bc887c6ae", "rated_matches": 66, "raw_elo_rating": 1614.0817686577604, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 62.82814813424107, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 49, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-bea6d7d9558897f9", "rated_matches": 58, "raw_elo_rating": 1179.3520510017056, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 6.750222581722012, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 0, "generated_at": "2026-07-01T00:15:48Z", "losses": 51, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-c4ad375a0a870e69", "rated_matches": 66, "raw_elo_rating": 1286.244368785162, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 20.848548025484437, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 55, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 0, "generated_at": "2026-07-09T17:30:50Z", "losses": 28, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-ce04fd14b6f43868", "rated_matches": 55, "raw_elo_rating": 1568.9574262357626, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 56.46293142915195, "uncertainty": 23.065310478106092, "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": "2026-07-02T06:10:40Z", "losses": 37, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-ce2925d9379d2a5d", "rated_matches": 66, "raw_elo_rating": 1332.8504775262977, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 26.816463243023417, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 39, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-e0e874b71d913c12", "rated_matches": 62, "raw_elo_rating": 1373.8370593378063, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 31.869203082298856, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 23 }, { "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": 28, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-4edfe4117ad3e936", "rated_matches": 62, "raw_elo_rating": 1459.9750388104458, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 42.899176885906776, "uncertainty": 19.244078834871203, "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": 8, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-6201278165db862a", "rated_matches": 66, "raw_elo_rating": 1810.87837198572, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 88.02796582947613, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 58 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 26, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-640b3078b8bce40e", "rated_matches": 58, "raw_elo_rating": 1638.802982390646, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 65.58294385391025, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 40, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-45c76cf9faaba10a", "rated_matches": 72, "raw_elo_rating": 1496.630215711361, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 48.05114074851961, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugin_count": 1, "attempted_matches": 54, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 27, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 21, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-73a7b73c1df452ad", "rated_matches": 54, "raw_elo_rating": 1627.6157786139568, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 63.912194201697034, "uncertainty": 23.66998624632421, "unilateral_faults": 0, "wins": 33 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 49, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-ea529147555b5f2e", "rated_matches": 64, "raw_elo_rating": 1231.8599986467784, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 13.7890857228278, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 78, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 39, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 28, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-1b522c9c14f3860c", "rated_matches": 78, "raw_elo_rating": 1544.1316071761985, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 54.36584442360475, "uncertainty": 12.5043950463012, "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": "2026-07-10T05:30:29Z", "losses": 31, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-bef852aad169a609", "rated_matches": 64, "raw_elo_rating": 1592.027897449992, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 59.90860829604776, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 33 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 25, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-cc78d54d18d4c3f1", "rated_matches": 58, "raw_elo_rating": 1613.041766542292, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 62.284218510036965, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 33 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 26, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-65bf9818e3e1b632", "rated_matches": 68, "raw_elo_rating": 1685.24753254842, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 72.0322843616957, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 42 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 36, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-8ebe8776c7d44d46", "rated_matches": 64, "raw_elo_rating": 1494.7496459810498, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 47.45212194783904, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 0, "generated_at": "2026-07-10T05:30:29Z", "losses": 27, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-aca193dd2a8774fb", "rated_matches": 56, "raw_elo_rating": 1421.3527923761658, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 37.622454286388646, "uncertainty": 22.47661785325219, "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": "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": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "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": 68, "raw_elo_rating": 1353.2540341715787, "reasoning": "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": 29.520495572548967, "uncertainty": 16.4429265428846, "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": "2026-07-24T13:40:00Z", "losses": 37, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-e2db910734ca5315", "rated_matches": 66, "raw_elo_rating": 1492.4680851538344, "reasoning": "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": 47.25550815103084, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 29 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 31, "model": "minimax/minimax-m3", "point_rating_method": "sequential_elo", "public_id": "E-24e15c4d7490cdf3", "rated_matches": 62, "raw_elo_rating": 1436.3423615846004, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 39.873011049349245, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 31 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 18, "model": "minimax/minimax-m3", "point_rating_method": "sequential_elo", "public_id": "E-4547f4cedca403f9", "rated_matches": 34, "raw_elo_rating": 1528.05635018843, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 49.41234532497391, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 38, "model": "mistralai/mistral-medium-3-5", "point_rating_method": "sequential_elo", "public_id": "E-d0d0df9d83b6e37e", "rated_matches": 38, "raw_elo_rating": 1159.6470831593338, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 2.6935113973845364, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 18, "model": "moonshotai/kimi-k2.7-code", "point_rating_method": "sequential_elo", "public_id": "E-d35e87ebfc251f60", "rated_matches": 34, "raw_elo_rating": 1499.914270711031, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 45.80875024049249, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 0, "generated_at": "2026-07-24T14:00:00Z", "losses": 22, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-1d1372c78963efdf", "rated_matches": 46, "raw_elo_rating": 1557.566963460809, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "score": 54.377737165834944, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 0, "generated_at": "2026-07-21T14:43:57Z", "losses": 12, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-3d2d4c8b0819b60b", "rated_matches": 32, "raw_elo_rating": 1611.6429141200556, "reasoning": "high", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 59.85711272242997, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 52, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 26, "draws": 0, "generated_at": "2026-07-17T22:36:00Z", "losses": 26, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-49105fbc7f72e6fe", "rated_matches": 52, "raw_elo_rating": 1541.026511259736, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "score": 52.69532819673755, "uncertainty": 24.930281974344517, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 0, "generated_at": "2026-07-24T14:00:00Z", "losses": 17, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-4cc8f48bf8bccc77", "rated_matches": 36, "raw_elo_rating": 1497.419808549579, "reasoning": "high", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 45.72657837516344, "uncertainty": 38.449493652678655, "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": 29, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-4d8815930b656774", "rated_matches": 50, "raw_elo_rating": 1429.3321694188307, "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": 38.256233977072846, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 0, "generated_at": "2026-07-17T22:36:00Z", "losses": 15, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-77d9c422124dcbfe", "rated_matches": 42, "raw_elo_rating": 1514.0936270512832, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "score": 48.47120156822998, "uncertainty": 32.49928516630233, "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": "2026-07-21T14:20:15Z", "losses": 15, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-c00660d2a8eb25c9", "rated_matches": 40, "raw_elo_rating": 1577.9650499245272, "reasoning": "low", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "low", "repair_status": "first_pass", "score": 56.46169796332241, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 0, "generated_at": "2026-07-11T17:22:09Z", "losses": 22, "model": "nex-agi/nex-n2-pro", "point_rating_method": "sequential_elo", "public_id": "E-1006c453b0c3a745", "rated_matches": 68, "raw_elo_rating": 1667.1651313142668, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 69.71683172233598, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 46 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 15, "model": "nex-agi/nex-n2-pro", "point_rating_method": "sequential_elo", "public_id": "E-d1f432cda667f27f", "rated_matches": 34, "raw_elo_rating": 1481.492286152561, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 43.449813934644574, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 0, "generated_at": "2026-07-03T18:15:00Z", "losses": 34, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-0e1c7f89e1c19b69", "rated_matches": 44, "raw_elo_rating": 1299.8016849909914, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 21.20665469801167, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 45, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-459f395cc0af6d2e", "rated_matches": 62, "raw_elo_rating": 1169.348522168338, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 5.6844327646508575, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-03T16:00:00Z", "losses": 27, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-312d25e3a9eeeee3", "rated_matches": 38, "raw_elo_rating": 1346.6875431579392, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 26.64405431271601, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 0, "generated_at": "2026-07-21T14:20:15Z", "losses": 22, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-3fae70801895971d", "rated_matches": 46, "raw_elo_rating": 1400.5331075430531, "reasoning": "low", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "low", "repair_status": "first_pass", "score": 34.26954183020419, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 30, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-f1e3e54a3d40556f", "rated_matches": 64, "raw_elo_rating": 1539.179287904116, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 53.14134044954261, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 27, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-29bc7f4fdf0f7b14", "rated_matches": 38, "raw_elo_rating": 1341.462164017372, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 25.974944178170976, "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": "2026-07-21T14:20:15Z", "losses": 24, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-759d747bb732d949", "rated_matches": 40, "raw_elo_rating": 1389.7423245669345, "reasoning": "low", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "low", "repair_status": "first_pass", "score": 32.35976589284266, "uncertainty": 34.33688094430304, "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": "2026-07-24T13:40:00Z", "losses": 39, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-069a963abdd14cdf", "rated_matches": 66, "raw_elo_rating": 1495.9916626938689, "reasoning": "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": 47.706702481330936, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 27 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 28, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-d8e68d23876f6d21", "rated_matches": 68, "raw_elo_rating": 1585.1752235655044, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 59.21801876937681, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 40 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 22, "model": "qwen/qwen3.7-max", "point_rating_method": "sequential_elo", "public_id": "E-3142a09c7f192060", "rated_matches": 68, "raw_elo_rating": 1755.2492100095503, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 80.99600365638999, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 46 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 7, "model": "qwen/qwen3.7-max", "point_rating_method": "sequential_elo", "public_id": "E-59c7745eb1e91d63", "rated_matches": 32, "raw_elo_rating": 1700.7910446154003, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 71.27253655781962, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 39, "model": "qwen/qwen3.7-plus", "point_rating_method": "sequential_elo", "public_id": "E-737a66790985a5e6", "rated_matches": 64, "raw_elo_rating": 1257.5505253206957, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 17.078759313374523, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 19, "model": "qwen/qwen3.7-plus", "point_rating_method": "sequential_elo", "public_id": "E-9d091700cb41ece2", "rated_matches": 44, "raw_elo_rating": 1492.425929607229, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 45.872201592244586, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 0, "generated_at": "2026-07-21T14:20:15Z", "losses": 27, "model": "stepfun/step-3.7-flash", "point_rating_method": "sequential_elo", "public_id": "E-1140a7c92290e8f4", "rated_matches": 50, "raw_elo_rating": 1408.2743046740543, "reasoning": "low", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "low", "repair_status": "repaired", "score": 35.55977304408127, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 30, "model": "stepfun/step-3.7-flash", "point_rating_method": "sequential_elo", "public_id": "E-6a5e44fe2dde4257", "rated_matches": 38, "raw_elo_rating": 1290.2573125898307, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 19.41815966428748, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 27, "model": "tencent/hy3-preview", "point_rating_method": "sequential_elo", "public_id": "E-dfed1e345a939bcd", "rated_matches": 38, "raw_elo_rating": 1342.1997504917822, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 26.06939217359004, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 44, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-062d41f517db2ccb", "rated_matches": 68, "raw_elo_rating": 1354.4160981986215, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 29.66929794584434, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-38e756fc6f3a2db6", "rated_matches": 0, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 32, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-6df2b00898e4ba3c", "rated_matches": 70, "raw_elo_rating": 1639.8223969946982, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 66.30306062230608, "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": "2026-07-24T13:40:00Z", "losses": 33, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-8ad2285ad59d87bf", "rated_matches": 64, "raw_elo_rating": 1439.7429822122815, "reasoning": "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": 40.40851511949337, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 31 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-17T22:36:00Z", "losses": 17, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-0929811cef80813b", "rated_matches": 38, "raw_elo_rating": 1479.0889751496873, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 43.59806618262557, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 21 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 0, "generated_at": "2026-07-17T22:36:00Z", "losses": 24, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-3cfeaacb3dbbab07", "rated_matches": 58, "raw_elo_rating": 1573.4651002521898, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 57.216423849812585, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 0, "generated_at": "2026-07-24T14:00:00Z", "losses": 25, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-436a3933a93e10cd", "rated_matches": 42, "raw_elo_rating": 1539.6947107510462, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 51.74942198019185, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 17 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 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": 40, "raw_elo_rating": 1695.4365075568585, "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": 71.5039256576441, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 33 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-17T22:36:00Z", "losses": 13, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-8e7f3829f3e45642", "rated_matches": 38, "raw_elo_rating": 1679.6525385132904, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 69.28024335235449, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 0, "generated_at": "2026-07-17T22:36:00Z", "losses": 18, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-a1728c5ac67e11f3", "rated_matches": 66, "raw_elo_rating": 1689.9554461696157, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 72.54377741255473, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 48 }, { "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": 5, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-ca54791ad3682b4f", "rated_matches": 42, "raw_elo_rating": 1756.547345722592, "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": 79.51741581546919, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 37 }, { "admitted_plugin_count": 1, "attempted_matches": 82, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 41, "draws": 0, "generated_at": "2026-07-24T14:00:00Z", "losses": 34, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-e58f3df122cf1d29", "rated_matches": 82, "raw_elo_rating": 1653.7600244886946, "reasoning": "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": 68.54434520363635, "uncertainty": 11.132129994845172, "unilateral_faults": 0, "wins": 48 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 21, "model": "x-ai/grok-build-0.1", "point_rating_method": "sequential_elo", "public_id": "E-37ae0129627ee16f", "rated_matches": 32, "raw_elo_rating": 1338.8974387107648, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 24.93203707943055, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 11 }, { "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": 35, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-0984b025e9005f5b", "rated_matches": 60, "raw_elo_rating": 1326.9005822633198, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 25.754048571506956, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 0, "generated_at": "2026-07-01T00:15:48Z", "losses": 14, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-345a5b25cbac7f3b", "rated_matches": 32, "raw_elo_rating": 1498.5587594562753, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "first_pass", "score": 45.37667945500192, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 18 }, { "admitted_plugin_count": 1, "attempted_matches": 76, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 38, "draws": 0, "generated_at": "2026-07-01T00:15:48Z", "losses": 44, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-47d67dcf0077af42", "rated_matches": 76, "raw_elo_rating": 1451.7215822177934, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 42.458374257712485, "uncertainty": 13.230288229818967, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 19, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-fa1a93f7e4d57000", "rated_matches": 32, "raw_elo_rating": 1398.5568164387994, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 32.571424229076754, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 36, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 18, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 21, "model": "xiaomi/mimo-v2.5-pro", "point_rating_method": "sequential_elo", "public_id": "E-3b160130ae038271", "rated_matches": 36, "raw_elo_rating": 1493.9649146612849, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 45.284178990879795, "uncertainty": 38.449493652678655, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 22, "model": "xiaomi/mimo-v2.5-pro", "point_rating_method": "sequential_elo", "public_id": "E-83580d03385c6759", "rated_matches": 60, "raw_elo_rating": 1653.249574240341, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 67.54305795364324, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 38 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 16, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-1d66fd51bbcbb370", "rated_matches": 44, "raw_elo_rating": 1675.4486719786005, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 69.30827550737436, "uncertainty": 30.785599249992988, "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": "2026-07-11T14:00:45Z", "losses": 21, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-62e8714f035ebc68", "rated_matches": 48, "raw_elo_rating": 1533.9355228025909, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 51.5057917564914, "uncertainty": 27.67857142857143, "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": "2026-07-11T14:00:45Z", "losses": 28, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-c81741d135c9dc9c", "rated_matches": 76, "raw_elo_rating": 1580.50015200578, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 58.94847838975526, "uncertainty": 13.230288229818967, "unilateral_faults": 0, "wins": 48 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 0, "generated_at": "2026-07-02T06:10:40Z", "losses": 27, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-cb438d112c0ea172", "rated_matches": 60, "raw_elo_rating": 1543.579363142568, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 53.49978037909996, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 33 }, { "admitted_plugin_count": 1, "attempted_matches": 78, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 39, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 37, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-d96269dd04d644e0", "rated_matches": 78, "raw_elo_rating": 1584.3015958519711, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 59.509614053419874, "uncertainty": 12.5043950463012, "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": "2026-07-01T00:15:48Z", "losses": 21, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-e10fd023695e8b0a", "rated_matches": 48, "raw_elo_rating": 1659.926528762448, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 67.63894816131332, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 27 }, { "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": 24, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-e31f275ab7ef3741", "rated_matches": 46, "raw_elo_rating": 1537.094717810298, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 51.75626479547493, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 22 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 0, "generated_at": "2026-07-11T17:22:09Z", "losses": 18, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-ecd98326faa92bf4", "rated_matches": 44, "raw_elo_rating": 1518.816948995505, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 49.25157331985353, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 0, "generated_at": "2026-07-01T00:15:48Z", "losses": 18, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-f7579fbfcb1dcbb9", "rated_matches": 46, "raw_elo_rating": 1592.179295886225, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 58.80984855585626, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 28 } ], "GB2-08": [ { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 1, "generated_at": "2026-07-02T16:51:45Z", "losses": 4, "model": "claude-fable-5", "point_rating_method": "sequential_elo", "public_id": "E-12891afa894223fd", "rated_matches": 66, "raw_elo_rating": 1912.1873848057296, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 100.0, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 61 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 31, "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": 62, "raw_elo_rating": 1748.30238195533, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 74.41108271929163, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 50 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 6, "coverage_status": "rated", "distinct_rated_opponents": 37, "draws": 6, "generated_at": "2026-07-02T16:51:45Z", "losses": 19, "model": "claude-opus-4-5", "point_rating_method": "sequential_elo", "public_id": "E-01b57d5e6655f927", "rated_matches": 74, "raw_elo_rating": 1645.4486548697253, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 59.15070675443215, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 49 }, { "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": 34, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 0, "losses": 11, "model": "claude-opus-4-5", "point_rating_method": "sequential_elo", "public_id": "E-72233463ddce5549", "rated_matches": 34, "raw_elo_rating": 1642.8403192893627, "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": 55.43291245207798, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 28, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 28, "losses": 24, "model": "claude-opus-4-5", "point_rating_method": "sequential_elo", "public_id": "E-877eec51affacb3a", "rated_matches": 64, "raw_elo_rating": 1441.5606549724548, "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": 27.079745333579883, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 0, "generated_at": "2026-07-03T17:20:00Z", "losses": 20, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-22dc6fe5ae5fb8b1", "rated_matches": 66, "raw_elo_rating": 1686.1260261745642, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 65.02884715553996, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 46 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 49, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 49, "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": 62, "raw_elo_rating": 1446.6514940291925, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 27.74641003392749, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 4 }, { "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": 21, "model": "claude-opus-4-8", "point_rating_method": "sequential_elo", "public_id": "E-c9d7578e8375d994", "rated_matches": 74, "raw_elo_rating": 1657.365116897373, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 60.99415499988833, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 53 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 0, "generated_at": "2026-07-25T10:50:00Z", "losses": 24, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-35a5bf9b35d5e1e8", "rated_matches": 58, "raw_elo_rating": 1689.429497650715, "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": 65.04364936989096, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 0, "generated_at": "2026-07-25T10:50:00Z", "losses": 25, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-5a7942274854aaa6", "rated_matches": 58, "raw_elo_rating": 1571.8431949043122, "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": 46.853328871691126, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 33 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 0, "generated_at": "2026-07-25T15:48:01Z", "losses": 10, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-a40851c4f03704e5", "rated_matches": 40, "raw_elo_rating": 1796.884681881971, "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": 80.0587922281817, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 30 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 0, "generated_at": "2026-07-25T10:50:00Z", "losses": 16, "model": "claude-opus-5", "point_rating_method": "sequential_elo", "public_id": "E-e73b6fb78880341d", "rated_matches": 60, "raw_elo_rating": 1782.1362327088805, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 79.51832573176307, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 44 }, { "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": 1582.4905656280778, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 46.89253394385154, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 24 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 45, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 45, "generated_at": "2026-07-02T16:51:45Z", "losses": 9, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-130fb40b1c7a4d39", "rated_matches": 60, "raw_elo_rating": 1442.873384161387, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 27.035172472656587, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 80, "capped_draws": 42, "coverage_status": "rated", "distinct_rated_opponents": 40, "draws": 42, "generated_at": "2026-07-03T16:50:00Z", "losses": 28, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-b5805acb90227d50", "rated_matches": 80, "raw_elo_rating": 1464.6642579295235, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 31.45351907819096, "uncertainty": 11.805555555555554, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 44, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 44, "generated_at": "2026-07-02T16:51:45Z", "losses": 2, "model": "claude-sonnet-5", "point_rating_method": "sequential_elo", "public_id": "E-cf0ed4bbe4aaadd7", "rated_matches": 46, "raw_elo_rating": 1444.104133950512, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "omitted", "reasoning_setting": "none", "repair_status": "first_pass", "score": 26.12237999875593, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 51, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 51, "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": 64, "raw_elo_rating": 1449.4863124214994, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 28.305825631962907, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 24, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 24, "generated_at": "2026-07-02T16:51:45Z", "losses": 8, "model": "cohere/north-mini-code", "point_rating_method": "sequential_elo", "public_id": "E-efd7b75d5cd3b538", "rated_matches": 32, "raw_elo_rating": 1430.593099567464, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "first_pass", "score": 22.28648246143083, "uncertainty": 43.288827977848925, "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": 1425.4281094231785, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 24.915538389642823, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 42, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 42, "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": 46, "raw_elo_rating": 1442.4608897065534, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 25.86817403465741, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 58, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 58, "generated_at": "2026-07-02T06:10:40Z", "losses": 8, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-95b070e1c29e44f0", "rated_matches": 66, "raw_elo_rating": 1415.6944083866397, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 23.19372107781717, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 48, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 48, "generated_at": "2026-07-02T16:51:45Z", "losses": 14, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-a7310645c3b96434", "rated_matches": 66, "raw_elo_rating": 1432.1969593602666, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 25.746626341753977, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 58, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 58, "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": 72, "raw_elo_rating": 1444.3940064125673, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 27.95081455535383, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 41, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 41, "generated_at": "2026-07-01T00:15:48Z", "losses": 4, "model": "deepseek/deepseek-v4-flash", "point_rating_method": "sequential_elo", "public_id": "E-d28ef17ff6995c62", "rated_matches": 46, "raw_elo_rating": 1444.0628033322878, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 26.11598625072297, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 54, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 54, "generated_at": "2026-07-02T16:51:45Z", "losses": 10, "model": "deepseek/deepseek-v4-pro", "point_rating_method": "sequential_elo", "public_id": "E-3a5b5c4507a989d3", "rated_matches": 70, "raw_elo_rating": 1440.883097011328, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 27.30638809711645, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 59, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 59, "generated_at": "2026-07-02T16:51:45Z", "losses": 8, "model": "deepseek/deepseek-v4-pro", "point_rating_method": "sequential_elo", "public_id": "E-c296a7abab6975d7", "rated_matches": 70, "raw_elo_rating": 1445.9523521591466, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 28.090589774286613, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 29, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 29, "generated_at": "2026-07-02T16:51:45Z", "losses": 6, "model": "google/gemini-3.1-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-b335c9f92035f80b", "rated_matches": 38, "raw_elo_rating": 1424.855704467417, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 22.26210300852069, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 76, "capped_draws": 25, "coverage_status": "rated", "distinct_rated_opponents": 38, "draws": 25, "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": 76, "raw_elo_rating": 1453.0417625819548, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 29.47922458032685, "uncertainty": 13.230288229818967, "unilateral_faults": 0, "wins": 23 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-21T14:20:15Z", "losses": 0, "model": "google/gemini-3.5-flash", "point_rating_method": "sequential_elo", "public_id": "E-5aa593158b0d8b3a", "rated_matches": 0, "reasoning": "low", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "low", "repair_status": "first_pass", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 57, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 57, "generated_at": "2026-07-02T16:51:45Z", "losses": 5, "model": "google/gemini-3.5-flash", "point_rating_method": "sequential_elo", "public_id": "E-bd0bbefbbd252fc5", "rated_matches": 62, "raw_elo_rating": 1399.4738925482284, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 20.44814764085012, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 25, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 25, "generated_at": "2026-07-02T16:51:45Z", "losses": 13, "model": "google/gemini-3.5-flash", "point_rating_method": "sequential_elo", "public_id": "E-fa332e578ae97122", "rated_matches": 38, "raw_elo_rating": 1374.5261450195408, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 14.4762402378837, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-0d09401e4a31ea61", "rated_matches": 0, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.5-flash-lite", "point_rating_method": "sequential_elo", "public_id": "E-284d554eca16e6f6", "rated_matches": 0, "reasoning": "minimal", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "minimal", "repair_status": "first_pass", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 2, "attempted_matches": 72, "capped_draws": 57, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 57, "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": 72, "raw_elo_rating": 1428.8659054082534, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 25.548654376833127, "uncertainty": 14.770573598065289, "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": 72, "capped_draws": 52, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 52, "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": 72, "raw_elo_rating": 1377.0586399667216, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 17.534194014479326, "uncertainty": 14.770573598065289, "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": 70, "capped_draws": 41, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 41, "generated_at": "2026-07-24T13:40:00Z", "losses": 16, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-679bf377de51ec1e", "rated_matches": 70, "raw_elo_rating": 1436.078774527812, "reasoning": "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": 26.56317087103918, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-c694a36a5e4e3f09", "rated_matches": 0, "reasoning": "minimal", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "minimal", "repair_status": "first_pass", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "google/gemini-3.6-flash", "point_rating_method": "sequential_elo", "public_id": "E-ee7ca879a02fdaf7", "rated_matches": 0, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 45, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 45, "generated_at": "2026-07-02T16:51:45Z", "losses": 10, "model": "google/gemma-4-31b-it", "point_rating_method": "sequential_elo", "public_id": "E-8546650b7690a81a", "rated_matches": 56, "raw_elo_rating": 1436.727549023724, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 25.811146558890066, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 29, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 29, "generated_at": "2026-07-02T16:51:45Z", "losses": 14, "model": "gpt-4.1", "point_rating_method": "sequential_elo", "public_id": "E-eabc996d553eebe0", "rated_matches": 50, "raw_elo_rating": 1417.0774072462827, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 22.30259680139711, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 49, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 49, "generated_at": "2026-07-02T16:51:45Z", "losses": 11, "model": "gpt-5", "point_rating_method": "sequential_elo", "public_id": "E-04ae9f2b42e0e036", "rated_matches": 68, "raw_elo_rating": 1438.5140773232674, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 26.83423634499792, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-21T14:20:15Z", "losses": 0, "model": "gpt-5", "point_rating_method": "sequential_elo", "public_id": "E-ae3a897b3420bcfb", "rated_matches": 0, "reasoning": "low", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "low", "repair_status": "first_pass", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 27, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 27, "generated_at": "2026-07-02T16:51:45Z", "losses": 10, "model": "gpt-5", "point_rating_method": "sequential_elo", "public_id": "E-ebca8ea756b4a4ad", "rated_matches": 42, "raw_elo_rating": 1424.0251709745728, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 22.605732802891488, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 51, "coverage_status": "rated", "distinct_rated_opponents": 37, "draws": 51, "generated_at": "2026-07-02T16:51:45Z", "losses": 13, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-95f891d54f35bb4a", "rated_matches": 74, "raw_elo_rating": 1450.5903871925957, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 29.006597636421393, "uncertainty": 13.985026918962571, "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": 1455.9222743715295, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 29.41687597028761, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 19 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 15, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 15, "generated_at": "2026-07-02T16:51:45Z", "losses": 28, "model": "gpt-5.4", "point_rating_method": "sequential_elo", "public_id": "E-ddc1f3e68bf1e74a", "rated_matches": 68, "raw_elo_rating": 1526.706490224709, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 40.47739221194158, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 25 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 34, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 34, "generated_at": "2026-07-02T06:10:40Z", "losses": 25, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-00b5df785d927901", "rated_matches": 70, "raw_elo_rating": 1436.789657201984, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 26.67314272471412, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 4, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 4, "generated_at": "2026-07-02T16:51:45Z", "losses": 30, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-1e5d07fc67fd8710", "rated_matches": 64, "raw_elo_rating": 1539.8645730727508, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 42.287126930820214, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 30 }, { "admitted_plugin_count": 1, "attempted_matches": 80, "capped_draws": 57, "coverage_status": "rated", "distinct_rated_opponents": 40, "draws": 57, "generated_at": "2026-07-01T00:15:48Z", "losses": 20, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-7ff0b78720f446ad", "rated_matches": 80, "raw_elo_rating": 1420.764326523804, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 24.662304425908992, "uncertainty": 11.805555555555554, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 47, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 47, "generated_at": "2026-07-02T06:10:40Z", "losses": 7, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-8cc872d6760c46c1", "rated_matches": 56, "raw_elo_rating": 1433.0414693201265, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 25.240918822969498, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 40, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 40, "generated_at": "2026-07-01T00:15:48Z", "losses": 17, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-acdb5996d6e8fdfc", "rated_matches": 66, "raw_elo_rating": 1443.508756483802, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 27.496534369149785, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 9 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 25, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 25, "generated_at": "2026-07-02T16:51:45Z", "losses": 27, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-b5171a15f0048555", "rated_matches": 66, "raw_elo_rating": 1441.820798825804, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 27.23541134657634, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 14 }, { "admitted_plugin_count": 1, "attempted_matches": 80, "capped_draws": 48, "coverage_status": "rated", "distinct_rated_opponents": 40, "draws": 48, "generated_at": "2026-07-02T06:10:40Z", "losses": 20, "model": "gpt-5.4-mini", "point_rating_method": "sequential_elo", "public_id": "E-b63acb1096519102", "rated_matches": 80, "raw_elo_rating": 1435.7608686525116, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 26.98223371456328, "uncertainty": 11.805555555555554, "unilateral_faults": 0, "wins": 12 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 57, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 57, "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": 64, "raw_elo_rating": 1432.9306505001732, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 25.744704231128832, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 65, "coverage_status": "rated", "distinct_rated_opponents": 37, "draws": 65, "generated_at": "2026-07-09T17:30:50Z", "losses": 9, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-024aff0a983df40d", "rated_matches": 74, "raw_elo_rating": 1410.5597559530413, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 22.813954488493017, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 45, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 45, "generated_at": "2026-07-02T16:51:45Z", "losses": 18, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-26fa12e871bd8f3a", "rated_matches": 68, "raw_elo_rating": 1393.6433229913866, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 19.89283770222214, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 76, "capped_draws": 60, "coverage_status": "rated", "distinct_rated_opponents": 38, "draws": 60, "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": 76, "raw_elo_rating": 1417.5690820683249, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 23.99168553536854, "uncertainty": 13.230288229818967, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 0, "generated_at": "2026-07-02T16:51:45Z", "losses": 15, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-98e55f26cfe52488", "rated_matches": 70, "raw_elo_rating": 1750.5108418795649, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 75.20506152028769, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 55 }, { "admitted_plugin_count": 1, "attempted_matches": 76, "capped_draws": 58, "coverage_status": "rated", "distinct_rated_opponents": 38, "draws": 58, "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": 76, "raw_elo_rating": 1434.2406436791346, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 26.57073634165292, "uncertainty": 13.230288229818967, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 49, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 49, "generated_at": "2026-07-09T17:30:50Z", "losses": 14, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-bb4437fab8180bfc", "rated_matches": 70, "raw_elo_rating": 1428.0616564555903, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 25.32294183245682, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 56, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 56, "generated_at": "2026-07-01T00:15:48Z", "losses": 11, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-c320ceaf4558afab", "rated_matches": 72, "raw_elo_rating": 1461.1213257667816, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 30.538490951516476, "uncertainty": 14.770573598065289, "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": "2026-07-09T17:30:50Z", "losses": 23, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-e361d8cbba2abd67", "rated_matches": 62, "raw_elo_rating": 1682.4425779165422, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 64.22272816240137, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 39 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 48, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 48, "generated_at": "2026-07-02T06:10:40Z", "losses": 7, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-f26c38927e48d019", "rated_matches": 60, "raw_elo_rating": 1463.259224663276, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 30.188813361887515, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 3, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 3, "generated_at": "2026-07-02T16:51:45Z", "losses": 23, "model": "gpt-5.4-nano", "point_rating_method": "sequential_elo", "public_id": "E-fd5a36e5fd795426", "rated_matches": 70, "raw_elo_rating": 1604.1522009988105, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 52.563728957568706, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 44 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 25, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 25, "generated_at": "2026-07-02T16:51:45Z", "losses": 22, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-0d83a3c5c5e66085", "rated_matches": 62, "raw_elo_rating": 1541.9180516740412, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 42.483919215225825, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 9, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 9, "generated_at": "2026-07-02T16:51:45Z", "losses": 16, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-3e859a6b27767128", "rated_matches": 68, "raw_elo_rating": 1690.1796710479507, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 65.76630327200057, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 43 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 46, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 46, "generated_at": "2026-07-02T16:51:45Z", "losses": 10, "model": "gpt-5.5", "point_rating_method": "sequential_elo", "public_id": "E-c42fbee03a029c83", "rated_matches": 60, "raw_elo_rating": 1442.9671606777888, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 27.049679476012503, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 5, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 5, "generated_at": "2026-07-10T05:30:29Z", "losses": 29, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-0fb7de4e8156a229", "rated_matches": 66, "raw_elo_rating": 1548.27072293001, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 43.70296063793118, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 32 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 53, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 53, "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": 62, "raw_elo_rating": 1439.1437448693234, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 26.58497915083693, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 49, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 49, "generated_at": "2026-07-10T05:30:29Z", "losses": 6, "model": "gpt-5.6-luna", "point_rating_method": "sequential_elo", "public_id": "E-e6198d88365e0492", "rated_matches": 62, "raw_elo_rating": 1463.521515251263, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 30.356162068590265, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 5, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 5, "generated_at": "2026-07-10T05:30:29Z", "losses": 17, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-0385f0602a8e29e2", "rated_matches": 62, "raw_elo_rating": 1669.5691004601476, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 62.23123191335946, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 40 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 12, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 12, "generated_at": "2026-07-10T05:30:29Z", "losses": 32, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-3ae62f195160add3", "rated_matches": 64, "raw_elo_rating": 1369.9378527645924, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "first_pass", "score": 15.99986870925893, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 20 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 5, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 5, "generated_at": "2026-07-10T05:30:29Z", "losses": 25, "model": "gpt-5.6-sol", "point_rating_method": "sequential_elo", "public_id": "E-994624d0bc2e266d", "rated_matches": 64, "raw_elo_rating": 1508.549910317883, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 37.44282331296946, "uncertainty": 18.26736729460423, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 55, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 55, "generated_at": "2026-07-10T05:30:29Z", "losses": 9, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-44cace55a6126cdf", "rated_matches": 68, "raw_elo_rating": 1443.099914328351, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 27.543654388822937, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 10, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 10, "generated_at": "2026-07-10T05:30:29Z", "losses": 31, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-b061663dc342c859", "rated_matches": 68, "raw_elo_rating": 1548.5237946011143, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 43.85247714738262, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 27 }, { "admitted_plugin_count": 1, "attempted_matches": 60, "capped_draws": 33, "coverage_status": "rated", "distinct_rated_opponents": 30, "draws": 33, "generated_at": "2026-07-10T05:30:29Z", "losses": 14, "model": "gpt-5.6-terra", "point_rating_method": "sequential_elo", "public_id": "E-d004e78844cdd202", "rated_matches": 60, "raw_elo_rating": 1492.409453460546, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 34.69828421039091, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 13 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 56, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 56, "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": 68, "raw_elo_rating": 1417.7904354977372, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 23.628338396923972, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 57, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 57, "generated_at": "2026-07-24T13:40:00Z", "losses": 11, "model": "inclusionai/ling-3.0-flash", "point_rating_method": "sequential_elo", "public_id": "E-28bcc8394e411616", "rated_matches": 72, "raw_elo_rating": 1424.1762047851312, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 24.823168879094652, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-4289b162cf8180f0", "rated_matches": 0, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 57, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 57, "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": 68, "raw_elo_rating": 1421.2556708046552, "reasoning": "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": 24.164402031567377, "uncertainty": 16.4429265428846, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 58, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 58, "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": 72, "raw_elo_rating": 1431.4718888272553, "reasoning": "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": 25.951793794413707, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "meituan/longcat-2.0", "point_rating_method": "sequential_elo", "public_id": "E-fffc7436e4cd7fbe", "rated_matches": 0, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 29, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 29, "generated_at": "2026-07-02T16:51:45Z", "losses": 6, "model": "minimax/minimax-m3", "point_rating_method": "sequential_elo", "public_id": "E-d169e7b29be70652", "rated_matches": 38, "raw_elo_rating": 1460.665880280986, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 27.80185177118549, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 70, "capped_draws": 7, "coverage_status": "rated", "distinct_rated_opponents": 35, "draws": 7, "generated_at": "2026-07-02T16:51:45Z", "losses": 33, "model": "minimax/minimax-m3", "point_rating_method": "sequential_elo", "public_id": "E-e67e41d4491d7ad3", "rated_matches": 70, "raw_elo_rating": 1513.6287669745502, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 38.55996968426065, "uncertainty": 15.58908290969266, "unilateral_faults": 0, "wins": 30 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 53, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 53, "generated_at": "2026-07-02T16:51:45Z", "losses": 5, "model": "mistralai/mistral-medium-3-5", "point_rating_method": "sequential_elo", "public_id": "E-ba85be2fa53925f5", "rated_matches": 58, "raw_elo_rating": 1437.5092940470956, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 26.072194902063597, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 2, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "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": 32, "raw_elo_rating": 1581.6368914228988, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 45.65259670212887, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 25, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 25, "generated_at": "2026-07-18T00:14:00Z", "losses": 11, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-134262cb96978830", "rated_matches": 38, "raw_elo_rating": 1388.9362846288373, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "score": 16.705454455820554, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 37, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 37, "generated_at": "2026-07-24T14:00:00Z", "losses": 3, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-151c4ee6a2d1838e", "rated_matches": 42, "raw_elo_rating": 1465.6007059014808, "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": 29.037368865431898, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 0, "generated_at": "2026-07-24T14:00:00Z", "losses": 1, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-3e1be56b9d966ded", "rated_matches": 40, "raw_elo_rating": 1808.9160748580327, "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": 81.92002001715609, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 39 }, { "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": 1508.6650791446625, "reasoning": "high", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 36.109804191190086, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 16 }, { "admitted_plugin_count": 1, "attempted_matches": 50, "capped_draws": 33, "coverage_status": "rated", "distinct_rated_opponents": 25, "draws": 33, "generated_at": "2026-07-17T22:36:00Z", "losses": 14, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-b06cbc77b01de3b3", "rated_matches": 50, "raw_elo_rating": 1428.8251492988911, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "score": 24.11994446924585, "uncertainty": 26.26400420140049, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 14, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 14, "generated_at": "2026-07-21T14:20:15Z", "losses": 15, "model": "moonshotai/kimi-k3", "point_rating_method": "sequential_elo", "public_id": "E-b88e77144afeb8fd", "rated_matches": 40, "raw_elo_rating": 1498.091938504907, "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": 33.836267685615866, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 11 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 50, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 50, "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": 58, "raw_elo_rating": 1441.5298755363042, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "repaired", "score": 26.69416926616589, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 8, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 8, "generated_at": "2026-07-02T16:51:45Z", "losses": 21, "model": "nex-agi/nex-n2-pro", "point_rating_method": "sequential_elo", "public_id": "E-92332f4d765b2297", "rated_matches": 32, "raw_elo_rating": 1309.805103448781, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 3.6008676371193116, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 56, "capped_draws": 42, "coverage_status": "rated", "distinct_rated_opponents": 28, "draws": 42, "generated_at": "2026-07-02T16:51:45Z", "losses": 11, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-15cf0dede27b7e1b", "rated_matches": 56, "raw_elo_rating": 1432.7695118803483, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 25.19884765587022, "uncertainty": 22.47661785325219, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 28, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 28, "generated_at": "2026-07-11T17:22:09Z", "losses": 10, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-2e3c01d0103fc439", "rated_matches": 42, "raw_elo_rating": 1438.964107250163, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 24.91675060350417, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 42, "capped_draws": 28, "coverage_status": "rated", "distinct_rated_opponents": 21, "draws": 28, "generated_at": "2026-07-02T16:51:45Z", "losses": 8, "model": "nvidia/nemotron-3-ultra-550b-a55b", "point_rating_method": "sequential_elo", "public_id": "E-8c24e8bcbe9b1228", "rated_matches": 42, "raw_elo_rating": 1429.4122086278544, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 23.439094675493273, "uncertainty": 32.49928516630233, "unilateral_faults": 0, "wins": 6 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 40, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 40, "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": 46, "raw_elo_rating": 1452.3787650864267, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 27.40244569391851, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 1, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 1, "generated_at": "2026-07-03T16:00:00Z", "losses": 15, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-1b6fc7dfefb8cea4", "rated_matches": 38, "raw_elo_rating": 1613.100257778122, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 51.3830862930041, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 22 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 38, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 38, "generated_at": "2026-07-02T16:51:45Z", "losses": 18, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-35de956c8305ff90", "rated_matches": 66, "raw_elo_rating": 1458.1375092603982, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 29.75956752250197, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 10 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 19, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 19, "generated_at": "2026-07-21T14:20:15Z", "losses": 13, "model": "o3", "point_rating_method": "sequential_elo", "public_id": "E-cbb72b5e25b55cee", "rated_matches": 40, "raw_elo_rating": 1494.8376381329836, "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": 33.33283518216888, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 8 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 32, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 32, "generated_at": "2026-07-02T16:51:45Z", "losses": 7, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-24a75273941e6ea3", "rated_matches": 44, "raw_elo_rating": 1440.0315846686565, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 25.29396931156561, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 58, "capped_draws": 45, "coverage_status": "rated", "distinct_rated_opponents": 29, "draws": 45, "generated_at": "2026-07-02T16:51:45Z", "losses": 10, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-6e65dec497ff2de3", "rated_matches": 58, "raw_elo_rating": 1462.8759114421637, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 29.996350093562853, "uncertainty": 21.344455490411935, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 33, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 33, "generated_at": "2026-07-21T14:20:15Z", "losses": 5, "model": "openai/gpt-oss-120b", "point_rating_method": "sequential_elo", "public_id": "E-f6e9da46c61ad315", "rated_matches": 40, "raw_elo_rating": 1434.1465689714887, "reasoning": "low", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "low", "repair_status": "first_pass", "score": 23.944071579260378, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 0, "capped_draws": 0, "coverage_status": "pending", "distinct_rated_opponents": 0, "draws": 0, "generated_at": "2026-07-24T13:40:00Z", "losses": 0, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-0fab95afbec0dd98", "rated_matches": 0, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "first_pass", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 62, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 62, "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": 72, "raw_elo_rating": 1417.7751810997115, "reasoning": "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": 23.8329457864827, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 57, "coverage_status": "rated", "distinct_rated_opponents": 37, "draws": 57, "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": 74, "raw_elo_rating": 1413.9267753590686, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 23.33482435759152, "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": "2026-07-24T13:40:00Z", "losses": 0, "model": "poolside/laguna-s-2.1", "point_rating_method": "sequential_elo", "public_id": "E-f72c72b8f264c57a", "rated_matches": 0, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "first_pass", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 20, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 20, "generated_at": "2026-07-02T16:51:45Z", "losses": 9, "model": "qwen/qwen3.7-max", "point_rating_method": "sequential_elo", "public_id": "E-64624689e7cbd439", "rated_matches": 32, "raw_elo_rating": 1474.3822256759502, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 29.060555798589352, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 76, "capped_draws": 49, "coverage_status": "rated", "distinct_rated_opponents": 38, "draws": 49, "generated_at": "2026-07-02T16:51:45Z", "losses": 22, "model": "qwen/qwen3.7-max", "point_rating_method": "sequential_elo", "public_id": "E-a667eb7d15f7f43e", "rated_matches": 76, "raw_elo_rating": 1456.1357275132184, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 29.95785357363107, "uncertainty": 13.230288229818967, "unilateral_faults": 0, "wins": 5 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 29, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 29, "generated_at": "2026-07-02T16:51:45Z", "losses": 3, "model": "qwen/qwen3.7-plus", "point_rating_method": "sequential_elo", "public_id": "E-6c2a9942e92223c8", "rated_matches": 32, "raw_elo_rating": 1459.6484452884602, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "first_pass", "score": 26.781275124406115, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 44, "capped_draws": 28, "coverage_status": "rated", "distinct_rated_opponents": 22, "draws": 28, "generated_at": "2026-07-02T16:51:45Z", "losses": 13, "model": "stepfun/step-3.7-flash", "point_rating_method": "sequential_elo", "public_id": "E-8b265019ada47f24", "rated_matches": 44, "raw_elo_rating": 1425.956256611796, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "repaired", "score": 23.116549641999313, "uncertainty": 30.785599249992988, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 32, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 32, "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": 40, "raw_elo_rating": 1405.907367827263, "reasoning": "low", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "low", "repair_status": "first_pass", "score": 19.57553453515884, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 80, "capped_draws": 65, "coverage_status": "rated", "distinct_rated_opponents": 40, "draws": 65, "generated_at": "2026-07-02T16:51:45Z", "losses": 14, "model": "tencent/hy3-preview", "point_rating_method": "sequential_elo", "public_id": "E-56487337fad4192f", "rated_matches": 80, "raw_elo_rating": 1448.1797497732612, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 28.903404995054014, "uncertainty": 11.805555555555554, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 9, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 9, "generated_at": "2026-07-02T16:51:45Z", "losses": 22, "model": "tencent/hy3-preview", "point_rating_method": "sequential_elo", "public_id": "E-81a5e5ef15f371dc", "rated_matches": 46, "raw_elo_rating": 1431.7219769582784, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 24.206889853330413, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 15 }, { "admitted_plugin_count": 1, "attempted_matches": 68, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 34, "draws": 1, "generated_at": "2026-07-24T13:40:00Z", "losses": 38, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-68669040dc891a7d", "rated_matches": 68, "raw_elo_rating": 1639.5524233506335, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 57.934388839397826, "uncertainty": 16.4429265428846, "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": "2026-07-24T13:40:00Z", "losses": 39, "model": "thinkingmachines/inkling", "point_rating_method": "sequential_elo", "public_id": "E-9c877cdf80f00ddf", "rated_matches": 72, "raw_elo_rating": 1605.3208067268397, "reasoning": "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": 52.84580662581403, "uncertainty": 14.770573598065289, "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-d21921560d198b28", "rated_matches": 0, "reasoning": "max", "reasoning_bracket": "intensive", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "max", "repair_status": "repaired", "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-17T22:36:00Z", "losses": 13, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-1c7222840add0cf9", "rated_matches": 38, "raw_elo_rating": 1634.515679078594, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 54.69600087540841, "uncertainty": 36.31407690254356, "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": "2026-07-17T22:36:00Z", "losses": 13, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-34ecad20175c262b", "rated_matches": 58, "raw_elo_rating": 1792.5148238948805, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 80.99070339953418, "uncertainty": 21.344455490411935, "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": "2026-07-17T22:36:00Z", "losses": 10, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-60939cc4ea338b18", "rated_matches": 38, "raw_elo_rating": 1671.2557038089158, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 60.37959504706703, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 28 }, { "admitted_plugin_count": 1, "attempted_matches": 38, "capped_draws": 0, "coverage_status": "under_covered", "distinct_rated_opponents": 19, "draws": 0, "generated_at": "2026-07-24T14:00:00Z", "losses": 4, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-707dd709e358a173", "rated_matches": 38, "raw_elo_rating": 1783.1611323348034, "reasoning": "high", "reasoning_bracket": "intensive", "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063", "reasoning_policy_version": "gb2_reasoning_brackets_v2", "reasoning_request_mode": "effort", "reasoning_setting": "high", "repair_status": "first_pass", "score": 77.69109785674755, "uncertainty": 36.31407690254356, "unilateral_faults": 0, "wins": 34 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 20, "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": 40, "raw_elo_rating": 1712.6788343858598, "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": 67.03234851831978, "uncertainty": 34.33688094430304, "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": "2026-07-17T22:36:00Z", "losses": 7, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-72b02fc86c46f3d7", "rated_matches": 60, "raw_elo_rating": 1847.4300953133004, "reasoning": "medium", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 89.61913049897616, "uncertainty": 20.268439966447993, "unilateral_faults": 0, "wins": 53 }, { "admitted_plugin_count": 1, "attempted_matches": 74, "capped_draws": 1, "coverage_status": "rated", "distinct_rated_opponents": 37, "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": 74, "raw_elo_rating": 1819.8426403190977, "reasoning": "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": 86.1290402353659, "uncertainty": 13.985026918962571, "unilateral_faults": 0, "wins": 61 }, { "admitted_plugin_count": 1, "attempted_matches": 40, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 20, "draws": 0, "generated_at": "2026-07-24T14:00:00Z", "losses": 7, "model": "x-ai/grok-4.5", "point_rating_method": "sequential_elo", "public_id": "E-b914d026c7631fcb", "rated_matches": 40, "raw_elo_rating": 1748.8021724726273, "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": 72.62054273750772, "uncertainty": 34.33688094430304, "unilateral_faults": 0, "wins": 33 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 24, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 24, "generated_at": "2026-07-02T16:51:45Z", "losses": 5, "model": "x-ai/grok-build-0.1", "point_rating_method": "sequential_elo", "public_id": "E-3e2fe948d2bcebb0", "rated_matches": 32, "raw_elo_rating": 1460.0573151384351, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 26.844526314718102, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 3 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 39, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 39, "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": 46, "raw_elo_rating": 1439.4563174105635, "reasoning": "highest", "reasoning_bracket": "highest", "reasoning_setting": "highest", "repair_status": "repaired", "score": 25.403373868757644, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 34, "capped_draws": 17, "coverage_status": "under_covered", "distinct_rated_opponents": 17, "draws": 17, "generated_at": "2026-07-03T19:35:00Z", "losses": 10, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-650d06103e7fa176", "rated_matches": 34, "raw_elo_rating": 1467.3593961658648, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 28.286432306166148, "uncertainty": 40.76542547285167, "unilateral_faults": 0, "wins": 7 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 21, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 21, "generated_at": "2026-07-02T06:10:40Z", "losses": 10, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-b5eb7da0f5021b69", "rated_matches": 32, "raw_elo_rating": 1394.7580906041408, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 16.7428920697459, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 66, "capped_draws": 47, "coverage_status": "rated", "distinct_rated_opponents": 33, "draws": 47, "generated_at": "2026-07-02T16:51:45Z", "losses": 17, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-cabbf604f15eb575", "rated_matches": 66, "raw_elo_rating": 1369.1623511787177, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 15.9953228436439, "uncertainty": 17.33472217815261, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 56, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 56, "generated_at": "2026-07-01T00:15:48Z", "losses": 6, "model": "xiaomi/mimo-v2.5", "point_rating_method": "sequential_elo", "public_id": "E-d51fce0298267f96", "rated_matches": 62, "raw_elo_rating": 1440.781930662483, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "none", "repair_status": "first_pass", "score": 26.83840258466534, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 32, "capped_draws": 27, "coverage_status": "under_covered", "distinct_rated_opponents": 16, "draws": 27, "generated_at": "2026-07-02T16:51:45Z", "losses": 3, "model": "xiaomi/mimo-v2.5-pro", "point_rating_method": "sequential_elo", "public_id": "E-bd1bb7ac29877b8f", "rated_matches": 32, "raw_elo_rating": 1453.3775637489682, "reasoning": "enabled", "reasoning_bracket": "balanced", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "toggle", "reasoning_setting": "enabled", "repair_status": "repaired", "score": 25.811184711276827, "uncertainty": 43.288827977848925, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 32, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 32, "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": 46, "raw_elo_rating": 1455.3488403943122, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 27.861909258061228, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 4 }, { "admitted_plugin_count": 1, "attempted_matches": 48, "capped_draws": 43, "coverage_status": "rated", "distinct_rated_opponents": 24, "draws": 43, "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": 48, "raw_elo_rating": 1455.156829952007, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "first_pass", "score": 28.01832850418103, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 1 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 39, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 39, "generated_at": "2026-07-11T14:00:45Z", "losses": 5, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-6a361d88d8c1fb48", "rated_matches": 46, "raw_elo_rating": 1466.4937248820224, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "first_pass", "score": 29.58599629891401, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 64, "capped_draws": 0, "coverage_status": "rated", "distinct_rated_opponents": 32, "draws": 0, "generated_at": "2026-07-11T14:00:45Z", "losses": 23, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-907d60010bf80864", "rated_matches": 64, "raw_elo_rating": 1695.4682380124432, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 66.3586426587361, "uncertainty": 18.26736729460423, "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": "2026-07-02T16:51:45Z", "losses": 17, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-97efd9455394f6d7", "rated_matches": 48, "raw_elo_rating": 1608.38355668495, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 51.72213756239715, "uncertainty": 27.67857142857143, "unilateral_faults": 0, "wins": 31 }, { "admitted_plugin_count": 1, "attempted_matches": 72, "capped_draws": 58, "coverage_status": "rated", "distinct_rated_opponents": 36, "draws": 58, "generated_at": "2026-07-02T06:10:40Z", "losses": 14, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-9e8f3e43bfd2810e", "rated_matches": 72, "raw_elo_rating": 1400.4491945908924, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 21.152657009799032, "uncertainty": 14.770573598065289, "unilateral_faults": 0, "wins": 0 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 3, "coverage_status": "rated", "distinct_rated_opponents": 23, "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": 46, "raw_elo_rating": 1540.7683006503114, "reasoning": "none", "reasoning_bracket": "baseline", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "none", "repair_status": "repaired", "score": 41.076095966448115, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 26 }, { "admitted_plugin_count": 1, "attempted_matches": 62, "capped_draws": 30, "coverage_status": "rated", "distinct_rated_opponents": 31, "draws": 30, "generated_at": "2026-07-02T16:51:45Z", "losses": 30, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-bc28f817090c9f60", "rated_matches": 62, "raw_elo_rating": 1307.1251840172183, "reasoning": "xhigh", "reasoning_bracket": "intensive", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "xhigh", "repair_status": "repaired", "score": 6.162022756076456, "uncertainty": 19.244078834871203, "unilateral_faults": 0, "wins": 2 }, { "admitted_plugin_count": 1, "attempted_matches": 46, "capped_draws": 40, "coverage_status": "rated", "distinct_rated_opponents": 23, "draws": 40, "generated_at": "2026-07-11T17:22:09Z", "losses": 5, "model": "z-ai/glm-5.2", "point_rating_method": "sequential_elo", "public_id": "E-da1e9a6be31e371f", "rated_matches": 46, "raw_elo_rating": 1451.1771451962684, "reasoning": "medium", "reasoning_bracket": "medium", "reasoning_policy_version": "legacy_reasoning_presets_v1", "reasoning_request_mode": "effort", "reasoning_setting": "medium", "repair_status": "repaired", "score": 27.216557963728263, "uncertainty": 29.182495748947275, "unilateral_faults": 0, "wins": 1 } ] } } }