{"benchmark_line":"gamebench2","economics_chart":{"eligible_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-05","GB2-06","GB2-07","GB2-08"],"enabled":true},"game_order":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-05","GB2-06","GB2-07","GB2-08"],"games":[{"alias":"GB2-01","name":"Go","slug":"go"},{"alias":"GB2-02","name":"Chess","slug":"chess"},{"alias":"GB2-03","name":"Shogi","slug":"shogi"},{"alias":"GB2-04","name":"Xiangqi","slug":"xiangqi"},{"alias":"GB2-05","name":"Hex","slug":"hex"},{"alias":"GB2-06","name":"International Draughts","slug":"international-draughts"},{"alias":"GB2-07","name":"Game of the Amazons","slug":"game-of-the-amazons"},{"alias":"GB2-08","name":"Tumbleweed","slug":"tumbleweed"}],"generated_at":"2026-07-27T14:02:29Z","heatmap_track_id":"full_freedom/intensive","models":[{"codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":11},"evidence_basis":"Standard list-price estimate","max":1.91725,"mean":1.58262125,"median":1.5854,"min":1.05322,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":11},"run_count":8,"token_priced_attempt_count":11,"total":12.66097},"medium":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.6981,"mean":0.5046499999999999,"median":0.511355,"min":0.33027,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":8},"run_count":8,"token_priced_attempt_count":8,"total":4.0371999999999995}},"codegen_cost_usd":{"admitted_cell_count":15,"cell_count":16,"cost_basis_counts":{"local_list_price_estimate":19},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":1.91725,"mean":1.043635625,"median":0.8756600000000001,"min":0.33027,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":19},"run_count":16,"token_priced_attempt_count":19,"total":16.698169999999998},"codegen_latency_ms":{"attempt_count":19,"max_ms":409229,"mean_ms":200864.125,"min_ms":48099,"run_count":16},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":11,"max_ms":409229,"mean_ms":316399.125,"min_ms":206163,"run_count":8},"medium":{"attempt_count":8,"max_ms":135206,"mean_ms":85329.125,"min_ms":48099,"run_count":8}},"codegen_output_tokens":{"attempt_count":19,"output_max":35932,"output_mean":17962.875,"output_min":4319,"run_count":16},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":11,"output_max":35932,"output_mean":28345.125,"output_min":18778,"run_count":8},"medium":{"attempt_count":8,"output_max":11549,"output_mean":7580.625,"output_min":4319,"run_count":8}},"display_name":"Claude Fable 5","economics":{"highest":79.75047098280922,"medium":65.00100860904149},"first_seen_at":null,"generation_metadata":{"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"anthropic","provider_model":"claude-fable-5","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"anthropic","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-03"],"first_pass_admitted":7,"first_pass_rate":0.875,"model_code_failure_rate":0.125,"model_code_failures":1},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":5,"first_pass_rate":0.625,"infra_excluded_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04"],"infra_failures_excluded":4,"model_code_failure_rate":0.0,"model_code_failures":0,"repaired_admitted":3,"repaired_rate":0.375}},"id":"claude-fable-5","is_recent_addition":false,"last_measured_at":"2026-07-27T11:46:35Z","match_totals_all":{"draws":124,"losses":186,"wins":540},"match_totals_tracks":{"highest":{"draws":65,"losses":78,"wins":319},"medium":{"draws":59,"losses":108,"wins":221}},"model_slug":"claude-fable-5","overall":{"max":100.0,"mean":73.1109201148505,"min":49.32044382130511},"per_game":{"GB2-01":63.53247225350247,"GB2-02":71.95778371836957,"GB2-03":69.09378758500024,"GB2-04":100.0,"GB2-05":92.451262399467,"GB2-06":79.37424207225958,"GB2-07":61.59421983387494,"GB2-08":100.0},"per_game_match_totals_all":{"GB2-01":{"draws":0,"losses":42,"wins":70},"GB2-02":{"draws":54,"losses":12,"wins":50},"GB2-03":{"draws":20,"losses":4,"wins":18},"GB2-04":{"draws":33,"losses":16,"wins":63},"GB2-05":{"draws":0,"losses":32,"wins":86},"GB2-06":{"draws":16,"losses":24,"wins":66},"GB2-07":{"draws":0,"losses":40,"wins":78},"GB2-08":{"draws":1,"losses":16,"wins":109}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":0,"losses":22,"wins":34},"GB2-02":{"draws":26,"losses":3,"wins":29},"GB2-03":{"draws":20,"losses":4,"wins":18},"GB2-04":{"draws":9,"losses":1,"wins":46},"GB2-05":{"draws":0,"losses":8,"wins":56},"GB2-06":{"draws":9,"losses":11,"wins":38},"GB2-07":{"draws":0,"losses":25,"wins":37},"GB2-08":{"draws":1,"losses":4,"wins":61}},"medium":{"GB2-01":{"draws":0,"losses":20,"wins":36},"GB2-02":{"draws":28,"losses":9,"wins":21},"GB2-04":{"draws":24,"losses":15,"wins":17},"GB2-05":{"draws":0,"losses":24,"wins":30},"GB2-06":{"draws":7,"losses":13,"wins":28},"GB2-07":{"draws":0,"losses":15,"wins":41},"GB2-08":{"draws":0,"losses":12,"wins":48}}},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1623.2307722548098,"GB2-02":1659.3993318565135,"GB2-03":1640.156750580333,"GB2-04":1821.193278726695,"GB2-05":1895.2246300132751,"GB2-06":1703.812816431412,"GB2-07":1604.4884389644276,"GB2-08":1910.1404215986424},"medium":{"GB2-01":1661.6976408495564,"GB2-02":1624.075614202798,"GB2-04":1566.7841216373108,"GB2-05":1564.6835482433685,"GB2-06":1646.4648905020276,"GB2-07":1721.3733595723618,"GB2-08":1742.3401615411974}},"per_game_tracks":{"highest":{"GB2-01":63.53247225350247,"GB2-02":71.95778371836957,"GB2-03":69.09378758500024,"GB2-04":100.0,"GB2-05":92.451262399467,"GB2-06":79.37424207225958,"GB2-07":61.59421983387494,"GB2-08":100.0},"medium":{"GB2-01":68.52383229044648,"GB2-02":63.51723403185436,"GB2-04":49.32044382130511,"GB2-05":52.452932914118634,"GB2-06":71.02490499954271,"GB2-07":76.52631679447857,"GB2-08":73.64139541154456}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":83.35493107640038,"medium":62.86690915330064},"reasoning_agg":{"highest":{"max":100.0,"mean":83.35493107640038,"min":61.59421983387494},"medium":{"max":76.52631679447857,"mean":62.86690915330064,"min":49.32044382130511}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Setting not tested"},"score_diagnostics":{"ceiling_score":100.0,"reasoning_variance":20.488021923099737},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":100.0,"expected_score":75.16758220079805,"reliability_score":78.12654997984268,"uncertainty_avg":21.87345002015733,"uncertainty_penalty":-8.187348875602325},"medium":{"ceiling_score":76.52631679447857,"expected_score":80.46612615442218,"reliability_score":77.08695618692684,"uncertainty_avg":22.913043813073163,"uncertainty_penalty":17.599217001121545}}},{"codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":13,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":16},"evidence_basis":"Standard list-price estimate","failed_cell_count":3,"max":2.09943,"mean":1.379653125,"median":1.320515,"min":0.8875599999999999,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":16},"run_count":16,"token_priced_attempt_count":16,"total":22.07445},"medium":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":16},"evidence_basis":"Standard list-price estimate","failed_cell_count":2,"max":0.551725,"mean":0.4461796875,"median":0.45788,"min":0.33828,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":16},"run_count":16,"token_priced_attempt_count":16,"total":7.1388750000000005},"none":{"admitted_cell_count":13,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":16},"evidence_basis":"Standard list-price estimate","failed_cell_count":3,"max":0.5221625,"mean":0.2856328125,"median":0.2536225,"min":0.2178175,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":16},"run_count":16,"token_priced_attempt_count":16,"total":4.570125}},"codegen_cost_usd":{"admitted_cell_count":40,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":48},"evidence_basis":"Standard list-price estimate","failed_cell_count":8,"max":2.09943,"mean":0.703821875,"median":0.48028875,"min":0.2178175,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":48},"run_count":48,"token_priced_attempt_count":48,"total":33.78345},"codegen_latency_ms":{"attempt_count":48,"max_ms":999214,"mean_ms":286075.0416666667,"min_ms":51907,"run_count":48},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":16,"max_ms":999214,"mean_ms":596693.625,"min_ms":340056,"run_count":16},"medium":{"attempt_count":16,"max_ms":302283,"mean_ms":172049.4375,"min_ms":111251,"run_count":16},"none":{"attempt_count":16,"max_ms":344404,"mean_ms":89482.0625,"min_ms":51907,"run_count":16}},"codegen_output_tokens":{"attempt_count":48,"output_max":88360,"output_mean":25640.5,"output_min":5404,"run_count":48},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":16,"output_max":88360,"output_mean":52673.75,"output_min":31102,"run_count":16},"medium":{"attempt_count":16,"output_max":25625,"output_mean":15334.8125,"output_min":9676,"run_count":16},"none":{"attempt_count":16,"output_max":28699,"output_mean":8912.9375,"output_min":5404,"run_count":16}},"display_name":"Claude Opus 5","economics":{"all":71.49086773620432,"highest":80.62402329771348,"medium":71.89661076286261,"none":65.24897294969355},"first_seen_at":null,"generation_metadata":{"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"anthropic","provider_model":"claude-opus-5","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"anthropic","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":14,"evaluated_cells":16,"failed_game_aliases":["GB2-06"],"first_pass_admitted":14,"first_pass_rate":0.875,"model_code_failure_rate":0.125,"model_code_failures":2},"baseline":{"admitted_plugins":13,"evaluated_cells":16,"failed_game_aliases":["GB2-06","GB2-07","GB2-08"],"first_pass_admitted":13,"first_pass_rate":0.8125,"model_code_failure_rate":0.1875,"model_code_failures":3},"intensive":{"admitted_plugins":13,"evaluated_cells":16,"failed_game_aliases":["GB2-06","GB2-07"],"first_pass_admitted":13,"first_pass_rate":0.8125,"model_code_failure_rate":0.1875,"model_code_failures":3}},"id":"claude-opus-5","is_recent_addition":false,"last_measured_at":"2026-07-27T11:10:13Z","match_totals_all":{"draws":292,"losses":446,"wins":1154},"match_totals_tracks":{"highest":{"draws":40,"losses":100,"wins":380},"medium":{"draws":99,"losses":180,"wins":431},"none":{"draws":153,"losses":166,"wins":343}},"model_slug":"claude-opus-5","overall":{"max":99.01057790596053,"mean":67.23813069766389,"min":43.019463779962486},"per_game":{"GB2-01":64.26871280365481,"GB2-02":78.60604273503697,"GB2-03":99.01057790596053,"GB2-04":73.42468015070315,"GB2-05":86.16060543308876,"GB2-07":99.7174091533898,"GB2-08":63.18013490216033},"per_game_all":{"GB2-01":65.05239791476579,"GB2-02":67.58343528974406,"GB2-03":80.27331458381356,"GB2-04":54.83237519481196,"GB2-05":82.70892317431822,"GB2-07":89.76542105429057,"GB2-08":60.22020694168611},"per_game_match_totals_all":{"GB2-01":{"draws":51,"losses":78,"wins":149},"GB2-02":{"draws":113,"losses":45,"wins":120},"GB2-03":{"draws":15,"losses":49,"wins":178},"GB2-04":{"draws":102,"losses":64,"wins":118},"GB2-05":{"draws":0,"losses":69,"wins":237},"GB2-06":{"draws":11,"losses":7,"wins":36},"GB2-07":{"draws":0,"losses":43,"wins":155},"GB2-08":{"draws":0,"losses":91,"wins":161}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":0,"losses":30,"wins":50},"GB2-02":{"draws":19,"losses":14,"wins":47},"GB2-03":{"draws":1,"losses":6,"wins":73},"GB2-04":{"draws":20,"losses":11,"wins":49},"GB2-05":{"draws":0,"losses":12,"wins":68},"GB2-07":{"draws":0,"losses":1,"wins":39},"GB2-08":{"draws":0,"losses":26,"wins":54}},"medium":{"GB2-01":{"draws":7,"losses":34,"wins":57},"GB2-02":{"draws":45,"losses":17,"wins":36},"GB2-03":{"draws":2,"losses":13,"wins":65},"GB2-04":{"draws":45,"losses":24,"wins":31},"GB2-05":{"draws":0,"losses":28,"wins":84},"GB2-07":{"draws":0,"losses":24,"wins":82},"GB2-08":{"draws":0,"losses":40,"wins":76}},"none":{"GB2-01":{"draws":44,"losses":14,"wins":42},"GB2-02":{"draws":49,"losses":14,"wins":37},"GB2-03":{"draws":12,"losses":30,"wins":40},"GB2-04":{"draws":37,"losses":29,"wins":38},"GB2-05":{"draws":0,"losses":29,"wins":85},"GB2-06":{"draws":11,"losses":7,"wins":36},"GB2-07":{"draws":0,"losses":18,"wins":34},"GB2-08":{"draws":0,"losses":25,"wins":31}}},"per_game_raw_elo_all":{"GB2-01":1640.3156545748313,"GB2-02":1647.3696898244914,"GB2-03":1707.4368083699712,"GB2-04":1599.3013627184152,"GB2-05":1820.0416394407528,"GB2-07":1827.0164238457385,"GB2-08":1660.332515897182},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1638.392961019582,"GB2-02":1697.616249764408,"GB2-03":1818.3922130275887,"GB2-04":1697.2745450187056,"GB2-05":1855.4153070757852,"GB2-07":1908.3795775583417,"GB2-08":1686.0665086802464},"medium":{"GB2-01":1619.2961858016197,"GB2-02":1630.3875789807648,"GB2-03":1776.563151472152,"GB2-04":1538.2157242898907,"GB2-05":1790.4131145129454,"GB2-07":1831.0772363583328,"GB2-08":1730.1736010828918},"none":{"GB2-01":1663.2578169032925,"GB2-02":1614.1052407283012,"GB2-03":1527.3550606101735,"GB2-04":1562.4138188466493,"GB2-05":1814.2964967335272,"GB2-06":1772.6067863963965,"GB2-07":1741.5924576205412,"GB2-08":1564.7574379284083}},"per_game_tracks":{"highest":{"GB2-01":64.26871280365481,"GB2-02":78.60604273503697,"GB2-03":99.01057790596053,"GB2-04":73.42468015070315,"GB2-05":86.16060543308876,"GB2-07":99.7174091533898,"GB2-08":63.18013490216033},"medium":{"GB2-01":62.55535735493004,"GB2-02":63.94985004999732,"GB2-03":91.93118700577347,"GB2-04":43.019463779962486,"GB2-05":79.52963881852078,"GB2-07":90.66753720750904,"GB2-08":71.62324112334503},"none":{"GB2-01":68.33312358571251,"GB2-02":60.19441308419789,"GB2-03":49.87817883970666,"GB2-04":48.05298165377025,"GB2-05":82.43652527134509,"GB2-06":88.32799956129024,"GB2-07":78.91131680197287,"GB2-08":45.85724479955294}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":73.52435752053414,"medium":69.53611634620681,"none":58.6539182262507},"reasoning_agg":{"highest":{"max":99.01057790596053,"mean":73.52435752053414,"min":63.18013490216033},"medium":{"max":91.93118700577347,"mean":69.53611634620681,"min":43.019463779962486},"none":{"max":82.43652527134509,"mean":58.6539182262507,"min":48.05298165377025}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Thinking disabled"},"score_diagnostics":{"ceiling_score":99.01057790596053,"expected_score":83.99695421853835,"reasoning_variance":14.870439294283436,"reliability_score":71.27172473708345,"uncertainty_avg":28.72827526291655,"uncertainty_penalty":16.758823520874458},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":99.01057790596053,"expected_score":78.01944956236885,"reliability_score":65.66311905569697,"uncertainty_avg":34.33688094430304,"uncertainty_penalty":4.49509204183471},"medium":{"ceiling_score":91.93118700577347,"expected_score":89.32284678735634,"reliability_score":73.89927275289551,"uncertainty_avg":26.10072724710449,"uncertainty_penalty":19.78673044114953},"none":{"ceiling_score":82.43652527134509,"expected_score":86.56749551765365,"reliability_score":74.51243632153512,"uncertainty_avg":25.487563678464873,"uncertainty_penalty":27.91357729140295}}},{"codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"evidence_basis":"Standard list-price estimate","max":3.2933475,"mean":2.642580625,"median":2.681945,"min":1.562975,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":9},"run_count":8,"token_priced_attempt_count":9,"total":21.140644999999996},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"evidence_basis":"Standard list-price estimate","max":0.712055,"mean":0.49864374999999994,"median":0.5065824999999999,"min":0.29423750000000004,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":9},"run_count":8,"token_priced_attempt_count":9,"total":3.989149999999999},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":10},"evidence_basis":"Standard list-price estimate","max":0.1598575,"mean":0.093565,"median":0.07461,"min":0.06826499999999999,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":10},"run_count":8,"token_priced_attempt_count":10,"total":0.7485199999999999}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":28},"evidence_basis":"Standard list-price estimate","max":3.2933475,"mean":1.078263125,"median":0.5065824999999999,"min":0.06826499999999999,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":28},"run_count":24,"token_priced_attempt_count":28,"total":25.878315},"codegen_latency_ms":{"attempt_count":28,"max_ms":1461887,"mean_ms":367273.6666666667,"min_ms":21601,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":9,"max_ms":1461887,"mean_ms":911419.875,"min_ms":461183,"run_count":8},"medium":{"attempt_count":9,"max_ms":292880,"mean_ms":161490.125,"min_ms":88006,"run_count":8},"none":{"attempt_count":10,"max_ms":50293,"mean_ms":28911.0,"min_ms":21601,"run_count":8}},"codegen_output_tokens":{"attempt_count":28,"output_max":218271,"output_mean":69498.70833333333,"output_min":3346,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":9,"output_max":218271,"output_mean":172117.75,"output_min":103016,"run_count":8},"medium":{"attempt_count":9,"output_max":45034,"output_mean":31797.75,"output_min":18396,"run_count":8},"none":{"attempt_count":10,"output_max":7647,"output_mean":4580.625,"output_min":3346,"run_count":8}},"display_name":"GPT-5.4","economics":{"all":57.62022282317851,"highest":71.82613215131099,"medium":48.349371100347874,"none":52.68516521787668},"first_seen_at":null,"generation_metadata":{"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-5.4","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openai","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"model_code_failure_rate":0.0,"model_code_failures":0,"repaired_admitted":1,"repaired_rate":0.125},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":6,"first_pass_rate":0.75,"model_code_failure_rate":0.0,"model_code_failures":0,"repaired_admitted":2,"repaired_rate":0.25},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"model_code_failure_rate":0.0,"model_code_failures":0,"repaired_admitted":1,"repaired_rate":0.125}},"id":"gpt-5.4","is_recent_addition":false,"last_measured_at":"2026-07-27T11:53:35Z","match_totals_all":{"draws":475,"losses":320,"wins":673},"match_totals_tracks":{"highest":{"draws":101,"losses":87,"wins":298},"medium":{"draws":179,"losses":129,"wins":170},"none":{"draws":195,"losses":104,"wins":205}},"model_slug":"gpt-5-4","overall":{"max":100.0,"mean":57.620222823178516,"min":25.753419845975525},"per_game":{"GB2-01":100.0,"GB2-02":57.20745689293141,"GB2-03":38.52438727472494,"GB2-04":60.360340816834494,"GB2-05":96.73066798261004,"GB2-06":88.95151331383552,"GB2-07":92.43903356479711,"GB2-08":40.39565736475438},"per_game_all":{"GB2-01":86.04462577220129,"GB2-02":38.167788227219575,"GB2-03":41.41677679531792,"GB2-04":45.00077463374007,"GB2-05":73.38696557875672,"GB2-06":82.82759041134558,"GB2-07":60.84076467540367,"GB2-08":33.27649649144329},"per_game_match_totals_all":{"GB2-01":{"draws":26,"losses":19,"wins":135},"GB2-02":{"draws":156,"losses":14,"wins":24},"GB2-03":{"draws":67,"losses":43,"wins":34},"GB2-04":{"draws":116,"losses":28,"wins":50},"GB2-05":{"draws":0,"losses":61,"wins":147},"GB2-06":{"draws":25,"losses":28,"wins":109},"GB2-07":{"draws":0,"losses":62,"wins":120},"GB2-08":{"draws":85,"losses":65,"wins":54}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":0,"losses":2,"wins":58},"GB2-02":{"draws":37,"losses":7,"wins":20},"GB2-03":{"draws":14,"losses":18,"wins":12},"GB2-04":{"draws":27,"losses":13,"wins":28},"GB2-05":{"draws":0,"losses":4,"wins":60},"GB2-06":{"draws":8,"losses":9,"wins":37},"GB2-07":{"draws":0,"losses":6,"wins":58},"GB2-08":{"draws":15,"losses":28,"wins":25}},"medium":{"GB2-01":{"draws":24,"losses":11,"wins":23},"GB2-02":{"draws":59,"losses":6,"wins":3},"GB2-03":{"draws":24,"losses":19,"wins":11},"GB2-04":{"draws":40,"losses":7,"wins":11},"GB2-05":{"draws":0,"losses":32,"wins":32},"GB2-06":{"draws":11,"losses":4,"wins":37},"GB2-07":{"draws":0,"losses":24,"wins":34},"GB2-08":{"draws":21,"losses":26,"wins":19}},"none":{"GB2-01":{"draws":2,"losses":6,"wins":54},"GB2-02":{"draws":60,"losses":1,"wins":1},"GB2-03":{"draws":29,"losses":6,"wins":11},"GB2-04":{"draws":49,"losses":8,"wins":11},"GB2-05":{"draws":0,"losses":25,"wins":55},"GB2-06":{"draws":6,"losses":15,"wins":35},"GB2-07":{"draws":0,"losses":32,"wins":28},"GB2-08":{"draws":49,"losses":11,"wins":10}}},"per_game_raw_elo_all":{"GB2-01":1794.9722113953997,"GB2-02":1515.3004001270583,"GB2-03":1472.9293143109987,"GB2-04":1541.5796924426852,"GB2-05":1733.8965396728042,"GB2-06":1731.5064901812912,"GB2-07":1599.2938652636046,"GB2-08":1478.7307096960449},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1902.50819139413,"GB2-02":1595.2075134501106,"GB2-03":1458.1644256131383,"GB2-04":1617.3769690127422,"GB2-05":1931.051509970191,"GB2-06":1777.2678447386463,"GB2-07":1839.8110785855636,"GB2-08":1524.6754320667146},"medium":{"GB2-01":1653.411765004077,"GB2-02":1462.112751652437,"GB2-03":1403.617820599916,"GB2-04":1513.1147492207922,"GB2-05":1525.8350202224913,"GB2-06":1788.705954908835,"GB2-07":1563.3796006203124,"GB2-08":1456.5400400197243},"none":{"GB2-01":1828.996677787992,"GB2-02":1488.5809352786268,"GB2-03":1557.0056967199416,"GB2-04":1494.2473590945217,"GB2-05":1744.8030888257304,"GB2-06":1628.545670896392,"GB2-07":1394.6909165849377,"GB2-08":1454.9766570016957}},"per_game_tracks":{"highest":{"GB2-01":100.0,"GB2-02":57.20745689293141,"GB2-03":38.52438727472494,"GB2-04":60.360340816834494,"GB2-05":96.73066798261004,"GB2-06":88.95151331383552,"GB2-07":92.43903356479711,"GB2-08":40.39565736475438},"medium":{"GB2-01":67.56620389662746,"GB2-02":25.753419845975525,"GB2-03":30.256036000566052,"GB2-04":38.809666551358085,"GB2-05":48.32886155421666,"GB2-06":90.34672640532096,"GB2-07":56.004212916192515,"GB2-08":29.72984163252576},"none":{"GB2-01":90.56767341997636,"GB2-02":31.542487942751787,"GB2-03":55.46990711066279,"GB2-04":35.83231653302763,"GB2-05":75.10136719944344,"GB2-06":69.18453151488029,"GB2-07":34.07904754522137,"GB2-08":29.70399047704974}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":71.82613215131099,"medium":48.349371100347874,"none":52.68516521787668},"reasoning_agg":{"highest":{"max":100.0,"mean":71.82613215131099,"min":38.52438727472494},"medium":{"max":90.34672640532096,"mean":48.349371100347874,"min":25.753419845975525},"none":{"max":90.56767341997636,"mean":52.68516521787668,"min":29.70399047704974}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"score_diagnostics":{"ceiling_score":100.0,"expected_score":56.929640788132986,"reasoning_variance":23.476761050963113,"reliability_score":79.94400385889935,"uncertainty_avg":20.055996141100657,"uncertainty_penalty":-0.6905820350455301},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":100.0,"expected_score":64.62077133024043,"reliability_score":79.69850244595662,"uncertainty_avg":20.301497554043387,"uncertainty_penalty":-7.205360821070556},"medium":{"ceiling_score":90.34672640532096,"expected_score":46.15848840712988,"reliability_score":79.41516866155675,"uncertainty_avg":20.584831338443248,"uncertainty_penalty":-2.1908826932179934},"none":{"ceiling_score":90.56767341997636,"expected_score":60.009662627028646,"reliability_score":80.71834046918467,"uncertainty_avg":19.281659530815336,"uncertainty_penalty":7.324497409151967}}},{"codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"evidence_basis":"Standard list-price estimate","max":12.915325,"mean":10.059243749999998,"median":10.0094025,"min":8.401555,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":8},"run_count":8,"token_priced_attempt_count":8,"total":80.47395},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":10},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.6689649999999999,"mean":0.46799875,"median":0.4352825,"min":0.366615,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":10},"run_count":9,"token_priced_attempt_count":10,"total":4.1199200000000005},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.147405,"mean":0.121464375,"median":0.124865,"min":0.09045,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":9},"run_count":9,"token_priced_attempt_count":9,"total":1.069485}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":27},"evidence_basis":"Standard list-price estimate","failed_cell_count":2,"max":12.915325,"mean":3.549568958333333,"median":0.4352825,"min":0.09045,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":27},"run_count":26,"token_priced_attempt_count":27,"total":85.66335499999998},"codegen_latency_ms":{"attempt_count":27,"max_ms":422464,"mean_ms":160017.42307692306,"min_ms":18406,"run_count":26},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":8,"max_ms":422464,"mean_ms":390133.625,"min_ms":351613,"run_count":8},"medium":{"attempt_count":10,"max_ms":132971,"mean_ms":90177.0,"min_ms":75382,"run_count":9},"none":{"attempt_count":9,"max_ms":34692,"mean_ms":25310.11111111111,"min_ms":18406,"run_count":9}},"codegen_output_tokens":{"attempt_count":27,"output_max":428840,"output_mean":108480.34615384616,"output_min":1810,"run_count":26},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":8,"output_max":428840,"output_mean":334016.875,"output_min":278832,"run_count":8},"medium":{"attempt_count":10,"output_max":20628,"output_mean":13803.555555555557,"output_min":9542,"run_count":9},"none":{"attempt_count":9,"output_max":3573,"output_mean":2680.222222222222,"output_min":1810,"run_count":9}},"display_name":"GPT-5.6 Sol","economics":{"all":56.055159811607766,"highest":65.25243558332284,"medium":57.84443319879201,"none":45.06861065270844},"first_seen_at":null,"generation_metadata":{"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-5.6-sol","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openai","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":9,"failed_game_aliases":["GB2-06"],"first_pass_admitted":7,"first_pass_rate":0.7777777777777778,"infra_excluded_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-05","GB2-06","GB2-07","GB2-08"],"infra_failures_excluded":8,"model_code_failure_rate":0.1111111111111111,"model_code_failures":1,"repaired_admitted":1,"repaired_rate":0.1111111111111111},"baseline":{"admitted_plugins":8,"evaluated_cells":9,"failed_game_aliases":["GB2-04"],"first_pass_admitted":8,"first_pass_rate":0.8888888888888888,"infra_excluded_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-05","GB2-06","GB2-07","GB2-08"],"infra_failures_excluded":8,"model_code_failure_rate":0.1111111111111111,"model_code_failures":1},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"infra_excluded_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-05","GB2-06","GB2-07","GB2-08"],"infra_failures_excluded":8,"model_code_failure_rate":0.0,"model_code_failures":0}},"id":"gpt-5.6-sol","is_recent_addition":false,"last_measured_at":"2026-07-27T11:59:44Z","match_totals_all":{"draws":291,"losses":430,"wins":697},"match_totals_tracks":{"highest":{"draws":58,"losses":137,"wins":293},"medium":{"draws":101,"losses":122,"wins":219},"none":{"draws":132,"losses":171,"wins":185}},"model_slug":"gpt-5-6-sol","overall":{"max":100.0,"mean":56.05515981160776,"min":16.21797777560009},"per_game":{"GB2-01":75.5601349974072,"GB2-02":100.0,"GB2-03":61.911144518391616,"GB2-04":66.45071005956129,"GB2-05":72.15544813911,"GB2-06":75.31957614668558,"GB2-07":54.40449302982698,"GB2-08":16.21797777560009},"per_game_all":{"GB2-01":63.54430407672731,"GB2-02":60.20608304016955,"GB2-03":56.26609258905366,"GB2-04":44.09929271392256,"GB2-05":63.205345768557684,"GB2-06":63.51757300778485,"GB2-07":58.16764894910002,"GB2-08":39.4349383475465},"per_game_match_totals_all":{"GB2-01":{"draws":15,"losses":60,"wins":99},"GB2-02":{"draws":78,"losses":21,"wins":71},"GB2-03":{"draws":39,"losses":38,"wins":65},"GB2-04":{"draws":121,"losses":10,"wins":33},"GB2-05":{"draws":0,"losses":66,"wins":134},"GB2-06":{"draws":16,"losses":83,"wins":93},"GB2-07":{"draws":0,"losses":84,"wins":112},"GB2-08":{"draws":22,"losses":68,"wins":90}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":0,"losses":16,"wins":42},"GB2-02":{"draws":11,"losses":4,"wins":43},"GB2-03":{"draws":3,"losses":13,"wins":28},"GB2-04":{"draws":26,"losses":2,"wins":26},"GB2-05":{"draws":0,"losses":21,"wins":55},"GB2-06":{"draws":6,"losses":21,"wins":29},"GB2-07":{"draws":0,"losses":28,"wins":50},"GB2-08":{"draws":12,"losses":32,"wins":20}},"medium":{"GB2-01":{"draws":0,"losses":25,"wins":29},"GB2-02":{"draws":25,"losses":11,"wins":22},"GB2-03":{"draws":12,"losses":9,"wins":23},"GB2-04":{"draws":50,"losses":4,"wins":4},"GB2-05":{"draws":0,"losses":20,"wins":40},"GB2-06":{"draws":9,"losses":13,"wins":30},"GB2-07":{"draws":0,"losses":25,"wins":33},"GB2-08":{"draws":5,"losses":15,"wins":38}},"none":{"GB2-01":{"draws":15,"losses":19,"wins":28},"GB2-02":{"draws":42,"losses":6,"wins":6},"GB2-03":{"draws":24,"losses":16,"wins":14},"GB2-04":{"draws":45,"losses":4,"wins":3},"GB2-05":{"draws":0,"losses":25,"wins":39},"GB2-06":{"draws":1,"losses":49,"wins":34},"GB2-07":{"draws":0,"losses":31,"wins":29},"GB2-08":{"draws":5,"losses":21,"wins":32}}},"per_game_raw_elo_all":{"GB2-01":1622.4762676614453,"GB2-02":1610.8385820839642,"GB2-03":1561.0949986496178,"GB2-04":1541.2448033067112,"GB2-05":1649.5702890080381,"GB2-06":1583.6384021976035,"GB2-07":1577.2955018919013,"GB2-08":1521.5745681224155},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1715.0185204641425,"GB2-02":1776.7560641910516,"GB2-03":1596.3466678596478,"GB2-04":1653.7320041970793,"GB2-05":1721.279849578368,"GB2-06":1674.4080128967423,"GB2-07":1544.0623728482103,"GB2-08":1370.0658232755432},"medium":{"GB2-01":1589.1789388885927,"GB2-02":1554.6276258057092,"GB2-03":1594.5085265402074,"GB2-04":1489.7668442731074,"GB2-05":1639.493660691125,"GB2-06":1667.5084391584408,"GB2-07":1613.924246727442,"GB2-08":1672.1128256209613},"none":{"GB2-01":1563.2313436316006,"GB2-02":1501.132056255132,"GB2-03":1492.4298015489974,"GB2-04":1480.2355614499472,"GB2-05":1587.9373567546218,"GB2-06":1408.9987545376268,"GB2-07":1573.8998861000514,"GB2-08":1522.545055470742}},"per_game_tracks":{"highest":{"GB2-01":75.5601349974072,"GB2-02":100.0,"GB2-03":61.911144518391616,"GB2-04":66.45071005956129,"GB2-05":72.15544813911,"GB2-06":75.31957614668558,"GB2-07":54.40449302982698,"GB2-08":16.21797777560009},"medium":{"GB2-01":58.990116931190066,"GB2-02":46.92274071038185,"GB2-03":61.60004691193783,"GB2-04":34.15864897798004,"GB2-05":61.71380324937027,"GB2-06":74.1340312841928,"GB2-07":62.60740530517968,"GB2-08":62.628672220103525},"none":{"GB2-01":56.082660301584646,"GB2-02":33.69550841012682,"GB2-03":45.28708633683153,"GB2-04":31.688519104226355,"GB2-05":55.746785917192774,"GB2-06":41.09911159247618,"GB2-07":57.49104851229338,"GB2-08":39.45816504693588}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":65.25243558332285,"medium":57.844433198792004,"none":45.06861065270844},"reasoning_agg":{"highest":{"max":100.0,"mean":65.25243558332285,"min":16.21797777560009},"medium":{"max":74.1340312841928,"mean":57.844433198792004,"min":34.15864897798004},"none":{"max":57.49104851229338,"mean":45.06861065270844,"min":31.688519104226355}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"score_diagnostics":{"ceiling_score":100.0,"expected_score":55.816670853627556,"reasoning_variance":20.183824930614406,"reliability_score":78.7278122996722,"uncertainty_avg":21.27218770032781,"uncertainty_penalty":-0.2384889579802021},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":100.0,"expected_score":57.1759494852536,"reliability_score":79.54710438736029,"uncertainty_avg":20.452895612639708,"uncertainty_penalty":-8.076486098069253},"medium":{"ceiling_score":74.1340312841928,"expected_score":61.47026412048231,"reliability_score":76.87098382515532,"uncertainty_avg":23.129016174844683,"uncertainty_penalty":3.6258309216903086},"none":{"ceiling_score":57.49104851229338,"expected_score":48.803798955146775,"reliability_score":79.76534868650096,"uncertainty_avg":20.234651313499047,"uncertainty_penalty":3.735188302438331}}},{"codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":20,"cell_count":8,"cost_basis_counts":{"provider_reported":37},"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.14454373333333334,"mean":0.08818255,"median":0.07401653333333333,"min":0.052337466666666665,"recorded_attempt_count":37,"run_count":24,"total":2.1163812},"medium":{"admitted_cell_count":23,"cell_count":8,"cost_basis_counts":{"provider_reported":39},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.12366493333333332,"mean":0.09185773333333332,"median":0.09170913333333332,"min":0.04980146666666666,"recorded_attempt_count":39,"run_count":24,"total":2.2045855999999997},"none":{"admitted_cell_count":16,"cell_count":8,"cost_basis_counts":{"provider_reported":28},"evidence_basis":"Provider-reported","max":0.116343,"mean":0.07787519999999999,"median":0.0843883,"min":0.041110400000000005,"recorded_attempt_count":28,"run_count":16,"total":1.2460032}},"codegen_cost_usd":{"admitted_cell_count":59,"cell_count":24,"cost_basis_counts":{"provider_reported":104},"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.14454373333333334,"mean":0.08597182777777779,"median":0.08538879999999999,"min":0.041110400000000005,"recorded_attempt_count":104,"run_count":64,"total":5.56697},"codegen_latency_ms":{"attempt_count":104,"max_ms":194096,"mean_ms":104338.484375,"min_ms":45373,"run_count":64},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":37,"max_ms":194096,"mean_ms":109560.20833333331,"min_ms":52667,"run_count":24},"medium":{"attempt_count":39,"max_ms":151974,"mean_ms":106852.375,"min_ms":48934,"run_count":24},"none":{"attempt_count":28,"max_ms":139814,"mean_ms":92735.0625,"min_ms":45373,"run_count":16}},"codegen_output_tokens":{"attempt_count":104,"output_max":26179,"output_mean":9948.484375,"output_min":3846,"run_count":64},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":37,"output_max":26179,"output_mean":10515.25,"output_min":4776,"run_count":24},"medium":{"attempt_count":39,"output_max":19479,"output_mean":10751.083333333334,"output_min":5204,"run_count":24},"none":{"attempt_count":28,"output_max":14459,"output_mean":7894.4375,"output_min":3846,"run_count":16}},"display_name":"Grok 4.5","economics":{"all":51.490906497033855,"highest":49.351185344484634,"medium":60.006958322299816,"none":45.1145758243171},"first_seen_at":null,"generation_metadata":{"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"x-ai","provider_model":"x-ai/grok-4.5","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":23,"evaluated_cells":24,"failed_game_aliases":["GB2-02"],"first_pass_admitted":10,"first_pass_rate":0.4166666666666667,"infra_excluded_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-05","GB2-06","GB2-07","GB2-08"],"infra_failures_excluded":8,"model_code_failure_rate":0.041666666666666664,"model_code_failures":1,"repaired_admitted":13,"repaired_rate":0.5416666666666666},"baseline":{"admitted_plugins":16,"evaluated_cells":16,"first_pass_admitted":5,"first_pass_rate":0.3125,"model_code_failure_rate":0.0,"model_code_failures":0,"repaired_admitted":11,"repaired_rate":0.6875},"intensive":{"admitted_plugins":20,"evaluated_cells":24,"failed_game_aliases":["GB2-02","GB2-03","GB2-05"],"first_pass_admitted":12,"first_pass_rate":0.5,"infra_excluded_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-05","GB2-06","GB2-07","GB2-08"],"infra_failures_excluded":8,"model_code_failure_rate":0.16666666666666666,"model_code_failures":4,"repaired_admitted":8,"repaired_rate":0.3333333333333333}},"id":"x-ai/grok-4.5","is_recent_addition":false,"last_measured_at":"2026-07-27T11:53:35Z","match_totals_all":{"draws":909,"losses":1143,"wins":1808},"match_totals_tracks":{"highest":{"draws":257,"losses":472,"wins":697},"medium":{"draws":344,"losses":416,"wins":742},"none":{"draws":308,"losses":255,"wins":369}},"model_slug":"x-ai-grok-4-5","overall":{"max":84.85770377828395,"mean":51.49090649703385,"min":19.6056169247618},"per_game":{"GB2-01":64.63299103911847,"GB2-02":38.93697130952252,"GB2-03":42.31105096947438,"GB2-04":22.814064655201765,"GB2-05":48.07016550643658,"GB2-06":55.39378555896641,"GB2-07":58.872648802864404,"GB2-08":63.7778049142926},"per_game_all":{"GB2-01":61.98430005063406,"GB2-02":35.005623044739295,"GB2-03":37.508010775026875,"GB2-04":28.77008871963272,"GB2-05":55.85947494438452,"GB2-06":55.05347104083837,"GB2-07":66.64008783797254,"GB2-08":71.10619556304243},"per_game_match_totals_all":{"GB2-01":{"draws":124,"losses":134,"wins":276},"GB2-02":{"draws":266,"losses":64,"wins":70},"GB2-03":{"draws":134,"losses":113,"wins":75},"GB2-04":{"draws":339,"losses":91,"wins":64},"GB2-05":{"draws":0,"losses":189,"wins":295},"GB2-06":{"draws":44,"losses":237,"wins":267},"GB2-07":{"draws":0,"losses":199,"wins":357},"GB2-08":{"draws":2,"losses":116,"wins":404}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":34,"losses":50,"wins":126},"GB2-02":{"draws":77,"losses":28,"wins":37},"GB2-03":{"draws":27,"losses":15,"wins":16},"GB2-04":{"draws":106,"losses":52,"wins":24},"GB2-05":{"draws":0,"losses":68,"wins":80},"GB2-06":{"draws":13,"losses":107,"wins":118},"GB2-07":{"draws":0,"losses":97,"wins":131},"GB2-08":{"draws":0,"losses":55,"wins":165}},"medium":{"GB2-01":{"draws":25,"losses":67,"wins":116},"GB2-02":{"draws":81,"losses":21,"wins":30},"GB2-03":{"draws":70,"losses":38,"wins":48},"GB2-04":{"draws":145,"losses":27,"wins":28},"GB2-05":{"draws":0,"losses":75,"wins":139},"GB2-06":{"draws":22,"losses":80,"wins":98},"GB2-07":{"draws":0,"losses":76,"wins":130},"GB2-08":{"draws":1,"losses":32,"wins":153}},"none":{"GB2-01":{"draws":65,"losses":17,"wins":34},"GB2-02":{"draws":108,"losses":15,"wins":3},"GB2-03":{"draws":37,"losses":60,"wins":11},"GB2-04":{"draws":88,"losses":12,"wins":12},"GB2-05":{"draws":0,"losses":46,"wins":76},"GB2-06":{"draws":9,"losses":50,"wins":51},"GB2-07":{"draws":0,"losses":26,"wins":96},"GB2-08":{"draws":1,"losses":29,"wins":86}}},"per_game_raw_elo_all":{"GB2-01":1617.7775568137342,"GB2-02":1516.9793197774197,"GB2-03":1458.738033763211,"GB2-04":1487.1389330038758,"GB2-05":1611.8429476233603,"GB2-06":1543.1923128756691,"GB2-07":1650.987123297795,"GB2-08":1734.7214275231552},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1645.7131029732216,"GB2-02":1536.6902606861279,"GB2-03":1498.0276047760062,"GB2-04":1453.637313690273,"GB2-05":1539.8264900054382,"GB2-06":1536.0930490675153,"GB2-07":1597.4696635584298,"GB2-08":1692.99759374344},"medium":{"GB2-01":1631.9565756398863,"GB2-02":1542.432769124338,"GB2-03":1525.3124264162536,"GB2-04":1504.0618821999399,"GB2-05":1699.4681950681797,"GB2-06":1565.809397581451,"GB2-07":1638.8693146453372,"GB2-08":1814.1521582571095},"none":{"GB2-01":1575.662991828095,"GB2-02":1471.8149295217936,"GB2-03":1352.8740700973729,"GB2-04":1503.7176031214149,"GB2-05":1596.2341577964626,"GB2-06":1527.6744919780417,"GB2-07":1716.6223916896186,"GB2-08":1697.0145305689155}},"per_game_tracks":{"highest":{"GB2-01":64.63299103911847,"GB2-02":38.93697130952252,"GB2-03":42.31105096947438,"GB2-04":22.814064655201765,"GB2-05":48.07016550643658,"GB2-06":55.39378555896641,"GB2-07":58.872648802864404,"GB2-08":63.7778049142926},"medium":{"GB2-01":65.32770242067362,"GB2-02":44.63145274557937,"GB2-03":50.60736443084445,"GB2-04":37.60021583373031,"GB2-05":69.34645655053502,"GB2-06":61.32306059649945,"GB2-07":66.36171022225238,"GB2-08":84.85770377828395},"none":{"GB2-01":55.99220669211011,"GB2-02":21.448445079116,"GB2-03":19.6056169247618,"GB2-04":25.895985669966077,"GB2-05":50.161802776181965,"GB2-06":48.44356696704924,"GB2-07":74.68590448880083,"GB2-08":64.68307799655075}},"provider_color":"#9CA3AF","provider_company":"xAI","provider_key":"x-ai","provider_text_color":"#0b1120","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":49.35118534448464,"medium":60.00695832229981,"none":45.1145758243171},"reasoning_agg":{"highest":{"max":64.63299103911847,"mean":49.35118534448464,"min":22.814064655201765},"medium":{"max":84.85770377828395,"mean":60.00695832229981,"min":37.60021583373031},"none":{"max":74.68590448880083,"mean":45.1145758243171,"min":19.6056169247618}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"score_diagnostics":{"ceiling_score":84.85770377828395,"expected_score":51.874036331128195,"reasoning_variance":14.892382497982709,"reliability_score":65.38259258395553,"uncertainty_avg":34.617407416044465,"uncertainty_penalty":0.38312983409434764},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":64.63299103911847,"expected_score":38.142486875551704,"reliability_score":58.797211835058995,"uncertainty_avg":41.202788164941005,"uncertainty_penalty":-11.208698468932937},"medium":{"ceiling_score":84.85770377828395,"expected_score":63.161727205152275,"reliability_score":81.7142245403631,"uncertainty_avg":18.285775459636895,"uncertainty_penalty":3.1547688828524656},"none":{"ceiling_score":74.68590448880083,"expected_score":54.317894912680615,"reliability_score":55.6363413764445,"uncertainty_avg":44.3636586235555,"uncertainty_penalty":9.203319088363514}}},{"codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":4.4173,"mean":2.7356843750000004,"median":2.536595,"min":2.045485,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":9},"run_count":8,"token_priced_attempt_count":9,"total":21.885474999999996},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"evidence_basis":"Standard list-price estimate","max":0.58673,"mean":0.442856875,"median":0.4176025,"min":0.34269,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":9},"run_count":8,"token_priced_attempt_count":9,"total":3.5428550000000003},"none":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.156555,"mean":0.1422525,"median":0.14850249999999998,"min":0.12078,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":8},"run_count":8,"token_priced_attempt_count":8,"total":1.13802}},"codegen_cost_usd":{"admitted_cell_count":22,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":26},"evidence_basis":"Standard list-price estimate","failed_cell_count":2,"max":4.4173,"mean":1.10693125,"median":0.4176025,"min":0.12078,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":26},"run_count":24,"token_priced_attempt_count":26,"total":26.566350000000007},"codegen_latency_ms":{"attempt_count":26,"max_ms":1288484,"mean_ms":282342.6666666667,"min_ms":29373,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":9,"max_ms":1288484,"mean_ms":693731.5,"min_ms":464667,"run_count":8},"medium":{"attempt_count":9,"max_ms":158785,"mean_ms":120076.75,"min_ms":87418,"run_count":8},"none":{"attempt_count":8,"max_ms":37405,"mean_ms":33219.75,"min_ms":29373,"run_count":8}},"codegen_output_tokens":{"attempt_count":26,"output_max":144760,"output_mean":35491.166666666664,"output_min":2821,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":9,"output_max":144760,"output_mean":89741.375,"output_min":66963,"run_count":8},"medium":{"attempt_count":9,"output_max":16870,"output_mean":13281.625,"output_min":10218,"run_count":8},"none":{"attempt_count":8,"output_max":3990,"output_mean":3450.5,"output_min":2821,"run_count":8}},"display_name":"GPT-5.5","economics":{"all":52.7881589315567,"highest":67.94710882260762,"medium":48.01639254386449,"none":41.835071106564946},"first_seen_at":null,"generation_metadata":{"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-5.5","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openai","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"model_code_failure_rate":0.0,"model_code_failures":0,"repaired_admitted":1,"repaired_rate":0.125},"baseline":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-06"],"first_pass_admitted":7,"first_pass_rate":0.875,"model_code_failure_rate":0.125,"model_code_failures":1},"intensive":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-02"],"first_pass_admitted":7,"first_pass_rate":0.875,"model_code_failure_rate":0.125,"model_code_failures":1}},"id":"gpt-5.5","is_recent_addition":false,"last_measured_at":"2026-07-27T11:52:58Z","match_totals_all":{"draws":469,"losses":328,"wins":494},"match_totals_tracks":{"highest":{"draws":95,"losses":94,"wins":240},"medium":{"draws":152,"losses":142,"wins":156},"none":{"draws":222,"losses":92,"wins":98}},"model_slug":"gpt-5-5","overall":{"max":88.73890042665397,"mean":51.398075670184305,"min":27.47820671040979},"per_game":{"GB2-01":77.1650058104334,"GB2-03":49.31150841617975,"GB2-04":30.738052083219,"GB2-05":83.56050300184323,"GB2-06":80.58681788029159,"GB2-07":88.73890042665397,"GB2-08":65.52897413963234},"per_game_all":{"GB2-01":60.565865381632214,"GB2-03":46.85899042428765,"GB2-04":31.383772220746085,"GB2-05":67.02842688940561,"GB2-07":65.55866549103602,"GB2-08":45.33323318223261},"per_game_match_totals_all":{"GB2-01":{"draws":107,"losses":24,"wins":51},"GB2-02":{"draws":92,"losses":14,"wins":14},"GB2-03":{"draws":58,"losses":31,"wins":32},"GB2-04":{"draws":126,"losses":38,"wins":26},"GB2-05":{"draws":0,"losses":61,"wins":125},"GB2-06":{"draws":7,"losses":52,"wins":63},"GB2-07":{"draws":0,"losses":62,"wins":122},"GB2-08":{"draws":79,"losses":46,"wins":61}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":19,"losses":12,"wins":29},"GB2-03":{"draws":20,"losses":10,"wins":9},"GB2-04":{"draws":40,"losses":13,"wins":11},"GB2-05":{"draws":0,"losses":15,"wins":53},"GB2-06":{"draws":7,"losses":20,"wins":37},"GB2-07":{"draws":0,"losses":8,"wins":58},"GB2-08":{"draws":9,"losses":16,"wins":43}},"medium":{"GB2-01":{"draws":38,"losses":3,"wins":15},"GB2-02":{"draws":30,"losses":12,"wins":14},"GB2-03":{"draws":19,"losses":13,"wins":8},"GB2-04":{"draws":40,"losses":13,"wins":9},"GB2-05":{"draws":0,"losses":21,"wins":37},"GB2-06":{"draws":0,"losses":32,"wins":26},"GB2-07":{"draws":0,"losses":26,"wins":32},"GB2-08":{"draws":25,"losses":22,"wins":15}},"none":{"GB2-01":{"draws":50,"losses":9,"wins":7},"GB2-02":{"draws":62,"losses":2,"wins":0},"GB2-03":{"draws":19,"losses":8,"wins":15},"GB2-04":{"draws":46,"losses":12,"wins":6},"GB2-05":{"draws":0,"losses":25,"wins":35},"GB2-07":{"draws":0,"losses":28,"wins":32},"GB2-08":{"draws":45,"losses":8,"wins":3}}},"per_game_raw_elo_all":{"GB2-01":1598.4080306811875,"GB2-03":1510.0196765558574,"GB2-04":1473.6358700806504,"GB2-05":1683.254113341083,"GB2-07":1635.1586960567265,"GB2-08":1558.9038996436439},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1726.5259512130235,"GB2-03":1525.5179367164974,"GB2-04":1470.1339268004403,"GB2-05":1819.332270454036,"GB2-06":1710.4157199319804,"GB2-07":1810.7420076245985,"GB2-08":1686.9133200163933},"medium":{"GB2-01":1578.7755636434526,"GB2-02":1534.4980840240307,"GB2-03":1471.7215759387857,"GB2-04":1454.5510147312568,"GB2-05":1652.109166288075,"GB2-06":1448.0809451241314,"GB2-07":1637.762905975935,"GB2-08":1541.4688058948389},"none":{"GB2-01":1489.9225771870858,"GB2-02":1501.313222137573,"GB2-03":1532.8195170122888,"GB2-04":1496.2226687102534,"GB2-05":1578.3209032811378,"GB2-07":1456.9711745696457,"GB2-08":1448.3295730196996}},"per_game_tracks":{"highest":{"GB2-01":77.1650058104334,"GB2-03":49.31150841617975,"GB2-04":30.738052083219,"GB2-05":83.56050300184323,"GB2-06":80.58681788029159,"GB2-07":88.73890042665397,"GB2-08":65.52897413963234},"medium":{"GB2-01":57.76408091303755,"GB2-02":41.89639389555927,"GB2-03":40.338045883793995,"GB2-04":27.47820671040979,"GB2-05":63.117863543585464,"GB2-06":45.16477138641322,"GB2-07":65.72170653066799,"GB2-08":42.65007148744865},"none":{"GB2-01":46.76850942142567,"GB2-02":34.77155592483919,"GB2-03":50.9274169728892,"GB2-04":35.93505786860947,"GB2-05":54.40691412278813,"GB2-07":42.21538951578612,"GB2-08":27.82065391961682}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":65.71628362373028,"medium":48.01639254386449,"none":40.461550842958125},"reasoning_agg":{"highest":{"max":88.73890042665397,"mean":65.71628362373028,"min":30.738052083219},"medium":{"max":65.72170653066799,"mean":48.01639254386449,"min":27.47820671040979},"none":{"max":54.40691412278813,"mean":40.461550842958125,"min":27.82065391961682}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"score_diagnostics":{"ceiling_score":88.73890042665397,"expected_score":50.5953412399256,"reasoning_variance":25.25473278077215,"reliability_score":78.15729089430486,"uncertainty_avg":21.842709105695132,"uncertainty_penalty":-0.8027344302587025},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":88.73890042665397,"expected_score":59.58947462697119,"reliability_score":79.66704409660176,"uncertainty_avg":20.332955903398247,"uncertainty_penalty":-6.126808996759088},"medium":{"ceiling_score":65.72170653066799,"expected_score":43.902358295974125,"reliability_score":77.2735449010268,"uncertainty_avg":22.726455098973204,"uncertainty_penalty":-4.114034247890366},"none":{"ceiling_score":54.40691412278813,"expected_score":45.639831590935486,"reliability_score":78.65968004002693,"uncertainty_avg":21.34031995997308,"uncertainty_penalty":5.178280747977361}}},{"codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":33},"evidence_basis":"Provider-reported","failed_cell_count":8,"max":0.341716425,"mean":0.30867194062500003,"median":0.31836633750000004,"min":0.2745495,"recorded_attempt_count":33,"run_count":16,"total":4.9387510500000005},"medium":{"admitted_cell_count":16,"cell_count":8,"cost_basis_counts":{"provider_reported":29},"evidence_basis":"Provider-reported","max":0.25698975,"mean":0.172479834375,"median":0.166217925,"min":0.10864875,"recorded_attempt_count":29,"run_count":16,"total":2.75967735},"none":{"admitted_cell_count":16,"cell_count":8,"cost_basis_counts":{"provider_reported":20},"evidence_basis":"Provider-reported","max":0.058529250000000005,"mean":0.03888066562499999,"median":0.038104875,"min":0.029012250000000003,"recorded_attempt_count":20,"run_count":16,"total":0.62209065}},"codegen_cost_usd":{"admitted_cell_count":40,"cell_count":24,"cost_basis_counts":{"provider_reported":82},"evidence_basis":"Provider-reported","failed_cell_count":8,"max":0.341716425,"mean":0.17334414687500002,"median":0.166217925,"min":0.029012250000000003,"recorded_attempt_count":82,"run_count":48,"total":8.320519050000001},"codegen_latency_ms":{"attempt_count":82,"max_ms":190231,"mean_ms":91741.70833333331,"min_ms":16474,"run_count":48},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":33,"max_ms":190231,"mean_ms":162520.375,"min_ms":111427,"run_count":16},"medium":{"attempt_count":29,"max_ms":131703,"mean_ms":90173.1875,"min_ms":44747,"run_count":16},"none":{"attempt_count":20,"max_ms":46243,"mean_ms":22531.5625,"min_ms":16474,"run_count":16}},"codegen_output_tokens":{"attempt_count":82,"output_max":45822,"output_mean":20391.416666666668,"output_min":1873,"run_count":48},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":33,"output_max":45822,"output_mean":37854.8125,"output_min":25990,"run_count":16},"medium":{"attempt_count":29,"output_max":31826,"output_mean":20126.3125,"output_min":8874,"run_count":16},"none":{"attempt_count":20,"output_max":6181,"output_mean":3193.125,"output_min":1873,"run_count":16}},"display_name":"Gemini 3.6 Flash","economics":{"all":49.59246012203158,"highest":58.01919372508709,"medium":49.29082044256338,"none":38.61863644188435},"first_seen_at":null,"generation_metadata":{"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"google","provider_model":"google/gemini-3.6-flash","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":16,"evaluated_cells":16,"first_pass_admitted":4,"first_pass_rate":0.25,"model_code_failure_rate":0.0,"model_code_failures":0,"repaired_admitted":12,"repaired_rate":0.75},"baseline":{"admitted_plugins":16,"evaluated_cells":16,"first_pass_admitted":12,"first_pass_rate":0.75,"model_code_failure_rate":0.0,"model_code_failures":0,"repaired_admitted":4,"repaired_rate":0.25},"intensive":{"admitted_plugins":8,"evaluated_cells":16,"failed_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-05","GB2-07"],"model_code_failure_rate":0.5,"model_code_failures":8,"repaired_admitted":8,"repaired_rate":0.5}},"id":"google/gemini-3.6-flash","is_recent_addition":false,"last_measured_at":"2026-07-27T11:26:38Z","match_totals_all":{"draws":757,"losses":528,"wins":737},"match_totals_tracks":{"highest":{"draws":106,"losses":59,"wins":173},"medium":{"draws":379,"losses":261,"wins":384},"none":{"draws":272,"losses":208,"wins":180}},"model_slug":"google-gemini-3-6-flash","overall":{"max":89.93824120320421,"mean":46.884401886076766,"min":22.174040290361702},"per_game":{"GB2-01":37.79869365428509,"GB2-03":35.88422783559002,"GB2-04":68.61993149054801,"GB2-05":80.36582674270291,"GB2-06":89.93824120320421,"GB2-08":35.50824142419229},"per_game_all":{"GB2-01":44.313549416764396,"GB2-03":47.93832656744279,"GB2-04":44.34714981794978,"GB2-05":66.3240181576506,"GB2-06":67.33332479983487,"GB2-08":27.29839197254708},"per_game_match_totals_all":{"GB2-01":{"draws":90,"losses":68,"wins":84},"GB2-02":{"draws":200,"losses":8,"wins":0},"GB2-03":{"draws":92,"losses":62,"wins":72},"GB2-04":{"draws":164,"losses":32,"wins":54},"GB2-05":{"draws":0,"losses":96,"wins":182},"GB2-06":{"draws":27,"losses":90,"wins":175},"GB2-07":{"draws":0,"losses":93,"wins":131},"GB2-08":{"draws":184,"losses":79,"wins":39}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":27,"losses":11,"wins":4},"GB2-03":{"draws":23,"losses":11,"wins":6},"GB2-04":{"draws":15,"losses":5,"wins":26},"GB2-05":{"draws":0,"losses":2,"wins":40},"GB2-06":{"draws":3,"losses":7,"wins":74},"GB2-08":{"draws":38,"losses":23,"wins":23}},"medium":{"GB2-01":{"draws":33,"losses":26,"wins":61},"GB2-02":{"draws":123,"losses":5,"wins":0},"GB2-03":{"draws":37,"losses":30,"wins":37},"GB2-04":{"draws":83,"losses":18,"wins":23},"GB2-05":{"draws":0,"losses":54,"wins":92},"GB2-06":{"draws":14,"losses":36,"wins":78},"GB2-07":{"draws":0,"losses":56,"wins":80},"GB2-08":{"draws":89,"losses":36,"wins":13}},"none":{"GB2-01":{"draws":30,"losses":31,"wins":19},"GB2-02":{"draws":77,"losses":3,"wins":0},"GB2-03":{"draws":32,"losses":21,"wins":29},"GB2-04":{"draws":66,"losses":9,"wins":5},"GB2-05":{"draws":0,"losses":40,"wins":50},"GB2-06":{"draws":10,"losses":47,"wins":23},"GB2-07":{"draws":0,"losses":37,"wins":51},"GB2-08":{"draws":57,"losses":20,"wins":3}}},"per_game_raw_elo_all":{"GB2-01":1480.3630766578492,"GB2-03":1513.8847011659147,"GB2-04":1545.9073636209866,"GB2-05":1682.4559750097105,"GB2-06":1619.420011954566,"GB2-08":1449.087463028275},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1432.9266307142595,"GB2-03":1445.4058897559369,"GB2-04":1669.0314085778646,"GB2-05":1805.431754344661,"GB2-06":1791.7075385947505,"GB2-08":1506.0213602790977},"medium":{"GB2-01":1581.1012071463724,"GB2-02":1476.427219156717,"GB2-03":1559.3371306272613,"GB2-04":1488.8990253241063,"GB2-05":1705.2214007370453,"GB2-06":1704.3788148815706,"GB2-07":1470.4484547993857,"GB2-08":1406.7116684800299},"none":{"GB2-01":1427.0613921129166,"GB2-02":1479.3227937021456,"GB2-03":1536.9110831145465,"GB2-04":1479.7916569609888,"GB2-05":1536.7147699474256,"GB2-06":1362.173682387377,"GB2-07":1594.7046977870536,"GB2-08":1434.5293603256966}},"per_game_tracks":{"highest":{"GB2-01":37.79869365428509,"GB2-03":35.88422783559002,"GB2-04":68.61993149054801,"GB2-05":80.36582674270291,"GB2-06":89.93824120320421,"GB2-08":35.50824142419229},"medium":{"GB2-01":58.295072217340596,"GB2-02":28.820870760406777,"GB2-03":56.435256830019185,"GB2-04":34.32049946583581,"GB2-05":70.1276647758533,"GB2-06":79.77925593934339,"GB2-07":44.37390326134637,"GB2-08":22.174040290361702},"none":{"GB2-01":36.84688237866748,"GB2-02":26.445146755820854,"GB2-03":51.49549503671918,"GB2-04":30.101018497465517,"GB2-05":48.4785629543956,"GB2-06":32.28247725695701,"GB2-07":59.08661445196189,"GB2-08":24.212894203087245}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#f5f9ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":52.74374877378255,"medium":49.29082044256339,"none":38.61863644188435},"reasoning_agg":{"highest":{"max":89.93824120320421,"mean":52.74374877378255,"min":35.50824142419229},"medium":{"max":79.77925593934339,"mean":49.29082044256339,"min":22.174040290361702},"none":{"max":59.08661445196189,"mean":38.61863644188435,"min":24.212894203087245}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Minimal"},"score_diagnostics":{"ceiling_score":89.93824120320421,"expected_score":47.82509262859754,"reasoning_variance":14.125112331898201,"reliability_score":71.78971066670776,"uncertainty_avg":28.210289333292238,"uncertainty_penalty":0.940690742520772},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":89.93824120320421,"expected_score":49.552572314437334,"reliability_score":67.73692128511578,"uncertainty_avg":32.26307871488422,"uncertainty_penalty":-3.1911764593452148},"medium":{"ceiling_score":79.77925593934339,"expected_score":47.38106227260945,"reliability_score":81.51350133062215,"uncertainty_avg":18.486498669377855,"uncertainty_penalty":-1.909758169953939},"none":{"ceiling_score":59.08661445196189,"expected_score":40.69269180556524,"reliability_score":66.69866793298664,"uncertainty_avg":33.30133206701336,"uncertainty_penalty":2.074055363680891}}},{"codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":11},"evidence_basis":"Standard list-price estimate","max":12.13752,"mean":8.1660015625,"median":8.18098,"min":4.7142525,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":11},"run_count":8,"token_priced_attempt_count":11,"total":65.3280125},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":11},"evidence_basis":"Standard list-price estimate","max":0.24673750000000003,"mean":0.16744,"median":0.158095,"min":0.108735,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":11},"run_count":8,"token_priced_attempt_count":11,"total":1.3395199999999998},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":10},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.1192425,"mean":0.0683559375,"median":0.06152125,"min":0.0542775,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":10},"run_count":9,"token_priced_attempt_count":10,"total":0.6063375}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":32},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":12.13752,"mean":2.8005991666666663,"median":0.158095,"min":0.0542775,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":32},"run_count":25,"token_priced_attempt_count":32,"total":67.27386999999999},"codegen_latency_ms":{"attempt_count":32,"max_ms":309143,"mean_ms":97936.92,"min_ms":13711,"run_count":25},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":11,"max_ms":309143,"mean_ms":245541.25,"min_ms":194014,"run_count":8},"medium":{"attempt_count":11,"max_ms":70195,"mean_ms":41737.375,"min_ms":27719,"run_count":8},"none":{"attempt_count":10,"max_ms":27196,"mean_ms":16688.222222222223,"min_ms":13711,"run_count":9}},"codegen_output_tokens":{"attempt_count":32,"output_max":806490,"output_mean":177703.68,"output_min":2382,"run_count":25},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":11,"output_max":806490,"output_mean":542498.625,"output_min":312998,"run_count":8},"medium":{"attempt_count":11,"output_max":13756,"output_mean":9389.25,"output_min":6044,"run_count":8},"none":{"attempt_count":10,"output_max":5458,"output_mean":3054.3333333333335,"output_min":2382,"run_count":9}},"display_name":"GPT-5.6 Terra","economics":{"all":46.318092710323576,"highest":54.627943464276825,"medium":41.999868759254326,"none":42.326465907439584},"first_seen_at":null,"generation_metadata":{"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-5.6-terra","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openai","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":5,"first_pass_rate":0.625,"infra_excluded_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-05","GB2-06","GB2-07","GB2-08"],"infra_failures_excluded":8,"model_code_failure_rate":0.0,"model_code_failures":0,"repaired_admitted":3,"repaired_rate":0.375},"baseline":{"admitted_plugins":8,"evaluated_cells":9,"failed_game_aliases":["GB2-03"],"first_pass_admitted":7,"first_pass_rate":0.7777777777777778,"infra_excluded_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-05","GB2-06","GB2-07","GB2-08"],"infra_failures_excluded":8,"model_code_failure_rate":0.1111111111111111,"model_code_failures":1,"repaired_admitted":1,"repaired_rate":0.1111111111111111},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":5,"first_pass_rate":0.625,"infra_excluded_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-05","GB2-06","GB2-07","GB2-08"],"infra_failures_excluded":8,"model_code_failure_rate":0.0,"model_code_failures":0,"repaired_admitted":3,"repaired_rate":0.375}},"id":"gpt-5.6-terra","is_recent_addition":false,"last_measured_at":"2026-07-27T11:59:44Z","match_totals_all":{"draws":502,"losses":437,"wins":487},"match_totals_tracks":{"highest":{"draws":96,"losses":167,"wins":229},"medium":{"draws":185,"losses":121,"wins":132},"none":{"draws":221,"losses":149,"wins":126}},"model_slug":"gpt-5-6-terra","overall":{"max":72.98349769903467,"mean":46.31809271032358,"min":28.668609009228703},"per_game":{"GB2-01":43.84767304178936,"GB2-02":45.346922229587115,"GB2-03":53.585646325873974,"GB2-04":48.305404528632984,"GB2-05":59.31522058212656,"GB2-06":70.76130982029495,"GB2-07":72.98349769903467,"GB2-08":42.877873486874975},"per_game_all":{"GB2-01":49.19025380385048,"GB2-02":34.77304281179649,"GB2-03":49.000711988603406,"GB2-04":42.804069255988345,"GB2-05":55.30169697742114,"GB2-06":51.829064855041146,"GB2-07":52.343050018262055,"GB2-08":35.302851971625564},"per_game_match_totals_all":{"GB2-01":{"draws":50,"losses":65,"wins":55},"GB2-02":{"draws":144,"losses":15,"wins":15},"GB2-03":{"draws":58,"losses":39,"wins":37},"GB2-04":{"draws":145,"losses":18,"wins":31},"GB2-05":{"draws":0,"losses":76,"wins":110},"GB2-06":{"draws":10,"losses":86,"wins":100},"GB2-07":{"draws":0,"losses":84,"wins":96},"GB2-08":{"draws":95,"losses":54,"wins":43}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":12,"losses":23,"wins":19},"GB2-02":{"draws":37,"losses":10,"wins":13},"GB2-03":{"draws":11,"losses":13,"wins":18},"GB2-04":{"draws":27,"losses":12,"wins":19},"GB2-05":{"draws":0,"losses":25,"wins":43},"GB2-06":{"draws":0,"losses":29,"wins":49},"GB2-07":{"draws":0,"losses":24,"wins":42},"GB2-08":{"draws":9,"losses":31,"wins":26}},"medium":{"GB2-01":{"draws":20,"losses":18,"wins":18},"GB2-02":{"draws":50,"losses":2,"wins":0},"GB2-03":{"draws":24,"losses":8,"wins":6},"GB2-04":{"draws":49,"losses":5,"wins":8},"GB2-05":{"draws":0,"losses":28,"wins":32},"GB2-06":{"draws":9,"losses":19,"wins":28},"GB2-07":{"draws":0,"losses":27,"wins":27},"GB2-08":{"draws":33,"losses":14,"wins":13}},"none":{"GB2-01":{"draws":18,"losses":24,"wins":18},"GB2-02":{"draws":57,"losses":3,"wins":2},"GB2-03":{"draws":23,"losses":18,"wins":13},"GB2-04":{"draws":69,"losses":1,"wins":4},"GB2-05":{"draws":0,"losses":23,"wins":35},"GB2-06":{"draws":1,"losses":38,"wins":23},"GB2-07":{"draws":0,"losses":33,"wins":27},"GB2-08":{"draws":53,"losses":9,"wins":4}}},"per_game_raw_elo_all":{"GB2-01":1512.4291130716704,"GB2-02":1503.8902978003487,"GB2-03":1520.0982479469042,"GB2-04":1530.6438614972292,"GB2-05":1585.0787624234738,"GB2-06":1495.2841309888133,"GB2-07":1534.6188883111452,"GB2-08":1493.2966627453418},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1472.4808055170065,"GB2-02":1547.1720098303158,"GB2-03":1548.5258455371809,"GB2-04":1560.7829388596697,"GB2-05":1616.3524860198763,"GB2-06":1632.355051545612,"GB2-07":1690.141060653709,"GB2-08":1541.4118035776828},"medium":{"GB2-01":1500.156493815032,"GB2-02":1487.2623907567247,"GB2-03":1504.641480334261,"GB2-04":1510.4667796354577,"GB2-05":1554.884848939414,"GB2-06":1496.011348653353,"GB2-07":1416.8015449056545,"GB2-08":1488.7884995268803},"none":{"GB2-01":1564.6500398829733,"GB2-02":1477.2364928140053,"GB2-03":1507.1274179692712,"GB2-04":1520.6818659965604,"GB2-05":1583.9989523111312,"GB2-06":1357.4859927674747,"GB2-07":1496.914059374072,"GB2-08":1449.6896851314627}},"per_game_tracks":{"highest":{"GB2-01":43.84767304178936,"GB2-02":45.346922229587115,"GB2-03":53.585646325873974,"GB2-04":48.305404528632984,"GB2-05":59.31522058212656,"GB2-06":70.76130982029495,"GB2-07":72.98349769903467,"GB2-08":42.877873486874975},"medium":{"GB2-01":47.5626764936281,"GB2-02":30.140455882095676,"GB2-03":45.64189418693135,"GB2-04":38.61690227136209,"GB2-05":51.6075528075571,"GB2-06":51.455302113536305,"GB2-07":36.612092900151,"GB2-08":34.36207341877303},"none":{"GB2-01":56.16041187613398,"GB2-02":28.8317503237067,"GB2-03":47.77459545300492,"GB2-04":41.48990096796995,"GB2-05":54.98231754257976,"GB2-06":33.27058263129217,"GB2-07":47.433559455600474,"GB2-08":28.668609009228703}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":54.627943464276825,"medium":41.99986875925433,"none":42.326465907439584},"reasoning_agg":{"highest":{"max":72.98349769903467,"mean":54.627943464276825,"min":42.877873486874975},"medium":{"max":51.6075528075571,"mean":41.99986875925433,"min":30.140455882095676},"none":{"max":56.16041187613398,"mean":42.326465907439584,"min":28.668609009228703}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"score_diagnostics":{"ceiling_score":72.98349769903467,"expected_score":41.94652975431147,"reasoning_variance":12.628074705022492,"reliability_score":78.89972079796037,"uncertainty_avg":21.100279202039626,"uncertainty_penalty":-4.371562956012113},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":72.98349769903467,"expected_score":42.30793305995119,"reliability_score":79.82513339812782,"uncertainty_avg":20.174866601872186,"uncertainty_penalty":-12.320010404325636},"medium":{"ceiling_score":51.6075528075571,"expected_score":38.31566704418934,"reliability_score":76.29393255031452,"uncertainty_avg":23.70606744968548,"uncertainty_penalty":-3.6842017150649937},"none":{"ceiling_score":56.16041187613398,"expected_score":45.21598915879387,"reliability_score":80.58009644543878,"uncertainty_avg":19.419903554561216,"uncertainty_penalty":2.8895232513542837}}},{"codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"evidence_basis":"Standard list-price estimate","max":0.73533,"mean":0.5886581249999999,"median":0.58241,"min":0.410635,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":8},"run_count":8,"token_priced_attempt_count":8,"total":4.709265},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"evidence_basis":"Standard list-price estimate","max":0.244315,"mean":0.178065,"median":0.1968175,"min":0.10277,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":8},"run_count":8,"token_priced_attempt_count":8,"total":1.42452},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"evidence_basis":"Standard list-price estimate","max":0.144235,"mean":0.12174125,"median":0.121475,"min":0.09594,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":8},"run_count":8,"token_priced_attempt_count":8,"total":0.97393}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":24},"evidence_basis":"Standard list-price estimate","max":0.73533,"mean":0.29615479166666664,"median":0.1968175,"min":0.09594,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":16,"boardgame-list-prices-2026-07-25":8},"run_count":24,"token_priced_attempt_count":24,"total":7.107715000000001},"codegen_latency_ms":{"attempt_count":24,"max_ms":319301,"mean_ms":98881.45833333331,"min_ms":22230,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":8,"max_ms":319301,"mean_ms":209645.0,"min_ms":137590,"run_count":8},"medium":{"attempt_count":8,"max_ms":81353,"mean_ms":54764.0,"min_ms":30922,"run_count":8},"none":{"attempt_count":8,"max_ms":40585,"mean_ms":32235.375,"min_ms":22230,"run_count":8}},"codegen_output_tokens":{"attempt_count":24,"output_max":27669,"output_mean":9998.125,"output_min":2138,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":8,"output_max":27669,"output_mean":21703.125,"output_min":14720,"run_count":8},"medium":{"attempt_count":8,"output_max":8008,"output_mean":5259.0,"output_min":2375,"run_count":8},"none":{"attempt_count":8,"output_max":4031,"output_mean":3032.25,"output_min":2138,"run_count":8}},"display_name":"Claude Opus 4.5","economics":{"none":46.10653397009744},"first_seen_at":null,"generation_metadata":{"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"anthropic","provider_model":"claude-opus-4-5","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"anthropic","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"model_code_failure_rate":0.0,"model_code_failures":0}},"id":"claude-opus-4-5","is_recent_addition":false,"last_measured_at":"2026-07-27T11:59:44Z","match_totals_all":{"draws":163,"losses":141,"wins":164},"match_totals_tracks":{"none":{"draws":163,"losses":141,"wins":164}},"model_slug":"claude-opus-4-5","overall":{"max":57.75514722037097,"mean":46.10653397009744,"min":35.54624651592337},"per_game_match_totals_all":{"GB2-01":{"draws":38,"losses":8,"wins":10},"GB2-02":{"draws":50,"losses":5,"wins":3},"GB2-03":{"draws":35,"losses":9,"wins":8},"GB2-04":{"draws":33,"losses":11,"wins":8},"GB2-05":{"draws":0,"losses":24,"wins":38},"GB2-06":{"draws":1,"losses":34,"wins":23},"GB2-07":{"draws":0,"losses":31,"wins":29},"GB2-08":{"draws":6,"losses":19,"wins":45}},"per_game_match_totals_tracks":{"none":{"GB2-01":{"draws":38,"losses":8,"wins":10},"GB2-02":{"draws":50,"losses":5,"wins":3},"GB2-03":{"draws":35,"losses":9,"wins":8},"GB2-04":{"draws":33,"losses":11,"wins":8},"GB2-05":{"draws":0,"losses":24,"wins":38},"GB2-06":{"draws":1,"losses":34,"wins":23},"GB2-07":{"draws":0,"losses":31,"wins":29},"GB2-08":{"draws":6,"losses":19,"wins":45}}},"per_game_raw_elo_tracks":{"none":{"GB2-01":1445.0343615965558,"GB2-02":1507.016974397993,"GB2-03":1543.043331713756,"GB2-04":1529.4343084381378,"GB2-05":1523.974286932912,"GB2-06":1455.789381704686,"GB2-07":1484.101949958685,"GB2-08":1636.0494722351684}},"per_game_tracks":{"none":{"GB2-01":40.41017310675189,"GB2-02":35.54624651592337,"GB2-03":53.68257145959784,"GB2-04":41.48915163819359,"GB2-05":48.01327090561448,"GB2-06":46.195935526761325,"GB2-07":45.759775387566016,"GB2-08":57.75514722037097}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"none":46.10653397009744},"reasoning_agg":{"none":{"max":57.75514722037097,"mean":46.10653397009744,"min":35.54624651592337}},"reasoning_labels":{"highest":"Extended thinking (legacy shared budget)","medium":"Extended thinking (legacy shared budget)","none":"Thinking field omitted"},"score_diagnostics":{"ceiling_score":57.75514722037097},"score_diagnostics_by_reasoning":{"none":{"ceiling_score":57.75514722037097,"expected_score":56.05359570835138,"reliability_score":78.73403818827788,"uncertainty_avg":21.26596181172212,"uncertainty_penalty":9.947061738253943}}},{"codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":1.38945,"mean":0.93123625,"median":0.95991,"min":0.36561,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":9},"run_count":8,"token_priced_attempt_count":9,"total":7.44989},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"evidence_basis":"Standard list-price estimate","max":0.34174499999999997,"mean":0.217940625,"median":0.19638,"min":0.14813,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":8},"run_count":8,"token_priced_attempt_count":8,"total":1.743525},"none":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.190125,"mean":0.15785312499999998,"median":0.15388000000000002,"min":0.131495,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":8},"run_count":8,"token_priced_attempt_count":8,"total":1.262825}},"codegen_cost_usd":{"admitted_cell_count":22,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":25},"evidence_basis":"Standard list-price estimate","failed_cell_count":2,"max":1.38945,"mean":0.43567666666666666,"median":0.203055,"min":0.131495,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":25},"run_count":24,"token_priced_attempt_count":25,"total":10.456239999999998},"codegen_latency_ms":{"attempt_count":25,"max_ms":604929,"mean_ms":175315.375,"min_ms":28646,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":9,"max_ms":604929,"mean_ms":421376.5,"min_ms":132563,"run_count":8},"medium":{"attempt_count":8,"max_ms":137577,"mean_ms":68957.5,"min_ms":35597,"run_count":8},"none":{"attempt_count":8,"max_ms":48121,"mean_ms":35612.125,"min_ms":28646,"run_count":8}},"codegen_output_tokens":{"attempt_count":25,"output_max":52366,"output_mean":14843.708333333334,"output_min":2908,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":9,"output_max":52366,"output_mean":34524.125,"output_min":11990,"run_count":8},"medium":{"attempt_count":8,"output_max":11318,"output_mean":6205.25,"output_min":3583,"run_count":8},"none":{"attempt_count":8,"output_max":5116,"output_mean":3801.75,"output_min":2908,"run_count":8}},"display_name":"Claude Opus 4.8","economics":{"all":52.638189748032225,"highest":65.68815507185845,"medium":45.15308829494263,"none":46.142255589163746},"first_seen_at":null,"generation_metadata":{"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"anthropic","provider_model":"claude-opus-4-8","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"anthropic","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"model_code_failure_rate":0.0,"model_code_failures":0},"baseline":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-03"],"first_pass_admitted":7,"first_pass_rate":0.875,"model_code_failure_rate":0.125,"model_code_failures":1},"intensive":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-03"],"first_pass_admitted":6,"first_pass_rate":0.75,"infra_excluded_game_aliases":["GB2-01","GB2-02","GB2-04","GB2-06","GB2-07","GB2-08"],"infra_failures_excluded":6,"model_code_failure_rate":0.125,"model_code_failures":1,"repaired_admitted":1,"repaired_rate":0.125}},"id":"claude-opus-4-8","is_recent_addition":false,"last_measured_at":"2026-07-27T11:54:26Z","match_totals_all":{"draws":315,"losses":374,"wins":553},"match_totals_tracks":{"highest":{"draws":59,"losses":123,"wins":240},"medium":{"draws":161,"losses":117,"wins":142},"none":{"draws":95,"losses":134,"wins":171}},"model_slug":"claude-opus-4-8","overall":{"max":76.32595670280091,"mean":45.99009483614247,"min":26.60687800872694},"per_game":{"GB2-01":59.955367539088286,"GB2-02":90.13059941166075,"GB2-04":52.71452593995635,"GB2-05":49.82574174672981,"GB2-06":78.99935188287517,"GB2-07":63.275737183469275,"GB2-08":64.91576179922941},"per_game_all":{"GB2-01":54.18927342925114,"GB2-02":48.24884151166042,"GB2-04":37.859928989256694,"GB2-05":44.66660296924741,"GB2-06":68.93869507391993,"GB2-07":63.446706002683236,"GB2-08":51.11728026020674},"per_game_match_totals_all":{"GB2-01":{"draws":29,"losses":59,"wins":76},"GB2-02":{"draws":103,"losses":13,"wins":40},"GB2-03":{"draws":23,"losses":10,"wins":7},"GB2-04":{"draws":104,"losses":23,"wins":33},"GB2-05":{"draws":0,"losses":91,"wins":89},"GB2-06":{"draws":7,"losses":66,"wins":101},"GB2-07":{"draws":0,"losses":64,"wins":108},"GB2-08":{"draws":49,"losses":48,"wins":99}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":6,"losses":19,"wins":33},"GB2-02":{"draws":20,"losses":3,"wins":35},"GB2-04":{"draws":30,"losses":10,"wins":26},"GB2-05":{"draws":0,"losses":35,"wins":29},"GB2-06":{"draws":3,"losses":16,"wins":37},"GB2-07":{"draws":0,"losses":20,"wins":34},"GB2-08":{"draws":0,"losses":20,"wins":46}},"medium":{"GB2-01":{"draws":9,"losses":23,"wins":20},"GB2-02":{"draws":39,"losses":3,"wins":2},"GB2-03":{"draws":23,"losses":10,"wins":7},"GB2-04":{"draws":40,"losses":6,"wins":4},"GB2-05":{"draws":0,"losses":28,"wins":32},"GB2-06":{"draws":1,"losses":21,"wins":36},"GB2-07":{"draws":0,"losses":19,"wins":37},"GB2-08":{"draws":49,"losses":7,"wins":4}},"none":{"GB2-01":{"draws":14,"losses":17,"wins":23},"GB2-02":{"draws":44,"losses":7,"wins":3},"GB2-04":{"draws":34,"losses":7,"wins":3},"GB2-05":{"draws":0,"losses":28,"wins":28},"GB2-06":{"draws":3,"losses":29,"wins":28},"GB2-07":{"draws":0,"losses":25,"wins":37},"GB2-08":{"draws":0,"losses":21,"wins":49}}},"per_game_raw_elo_all":{"GB2-01":1551.8962596518377,"GB2-02":1563.3151402346211,"GB2-04":1511.107363942454,"GB2-05":1496.8309373480809,"GB2-06":1625.8171705609222,"GB2-07":1620.7106897926697,"GB2-08":1594.9147584769362},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1594.7574022863707,"GB2-02":1735.4526025988669,"GB2-04":1579.7087489959974,"GB2-05":1538.3667950040874,"GB2-06":1701.9160659633524,"GB2-07":1620.9004693099198,"GB2-08":1683.6684140637717},"medium":{"GB2-01":1483.905475102522,"GB2-02":1477.1586139699823,"GB2-03":1461.662536911419,"GB2-04":1471.7037725606615,"GB2-05":1525.7692733725237,"GB2-06":1681.0254506469776,"GB2-07":1655.5878327465305,"GB2-08":1451.714886192373},"none":{"GB2-01":1577.025901566621,"GB2-02":1477.334204135014,"GB2-04":1481.9095702707032,"GB2-05":1426.356743667632,"GB2-06":1494.5099950724373,"GB2-07":1585.6437673215585,"GB2-08":1649.3609751746642}},"per_game_tracks":{"highest":{"GB2-01":59.955367539088286,"GB2-02":90.13059941166075,"GB2-04":52.71452593995635,"GB2-05":49.82574174672981,"GB2-06":78.99935188287517,"GB2-07":63.275737183469275,"GB2-08":64.91576179922941},"medium":{"GB2-01":45.19928208402567,"GB2-02":26.60687800872694,"GB2-03":38.63559627801959,"GB2-04":29.776397542600765,"GB2-05":48.12979094866205,"GB2-06":76.32595670280091,"GB2-07":67.93204374088673,"GB2-08":28.618761053818325},"none":{"GB2-01":57.41317066463946,"GB2-02":28.009047114593564,"GB2-04":31.08886348521295,"GB2-05":36.044276212350354,"GB2-06":51.49077663608371,"GB2-07":59.132337083693706,"GB2-08":59.81731792757247}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":48.189873463775356,"medium":45.15308829494262,"none":44.62732274970943},"reasoning_agg":{"highest":{"max":49.82574174672981,"mean":48.189873463775356,"min":49.82574174672981},"medium":{"max":76.32595670280091,"mean":45.15308829494262,"min":26.60687800872694},"none":{"max":59.81731792757247,"mean":44.62732274970943,"min":28.009047114593564}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Thinking field omitted"},"score_diagnostics":{"ceiling_score":76.32595670280091,"expected_score":50.88904008947794,"reasoning_variance":3.562550714065928,"reliability_score":77.91362110759461,"uncertainty_avg":22.086378892405396,"uncertainty_penalty":4.898945253335469},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":49.82574174672981,"expected_score":58.26966671427658,"reliability_score":79.74681046695575,"uncertainty_avg":20.253189533044246,"uncertainty_penalty":10.079793250501226},"medium":{"ceiling_score":76.32595670280091,"expected_score":40.214417902501275,"reliability_score":74.91566004417486,"uncertainty_avg":25.084339955825147,"uncertainty_penalty":-4.938670392441345},"none":{"ceiling_score":59.81731792757247,"expected_score":50.66152841939475,"reliability_score":77.75660124187064,"uncertainty_avg":22.243398758129352,"uncertainty_penalty":6.034205669685321}}},{"codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":18,"cell_count":8,"cost_basis_counts":{"provider_reported":48},"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.9392418,"mean":0.7382814249999998,"median":0.7264120999999999,"min":0.4980382,"recorded_attempt_count":48,"run_count":23,"total":16.779512399999998},"medium":{"admitted_cell_count":15,"cell_count":8,"cost_basis_counts":{"provider_reported":32},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.3926418,"mean":0.31750829999999997,"median":0.32150055,"min":0.2298153,"recorded_attempt_count":32,"run_count":16,"total":5.0801327999999994},"none":{"admitted_cell_count":16,"cell_count":8,"cost_basis_counts":{"provider_reported":17},"evidence_basis":"Provider-reported","max":0.0820533,"mean":0.0699502125,"median":0.06609614999999999,"min":0.0587988,"recorded_attempt_count":17,"run_count":16,"total":1.1192034}},"codegen_cost_usd":{"admitted_cell_count":49,"cell_count":24,"cost_basis_counts":{"provider_reported":97},"evidence_basis":"Provider-reported","failed_cell_count":6,"max":0.9392418,"mean":0.3752466458333333,"median":0.32150055,"min":0.0587988,"recorded_attempt_count":97,"run_count":55,"total":22.9788486},"codegen_latency_ms":{"attempt_count":97,"max_ms":2434665,"mean_ms":734905.7636363637,"min_ms":64944,"run_count":55},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":48,"max_ms":2434665,"mean_ms":1301919.2608695652,"min_ms":865404,"run_count":23},"medium":{"attempt_count":32,"max_ms":962148,"mean_ms":564713.375,"min_ms":119309,"run_count":16},"none":{"attempt_count":17,"max_ms":115016,"mean_ms":90016.25,"min_ms":64944,"run_count":16}},"codegen_output_tokens":{"attempt_count":97,"output_max":81171,"output_mean":25811.70909090909,"output_min":2237,"run_count":55},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":48,"output_max":81171,"output_mean":46501.95652173913,"output_min":28508,"run_count":23},"medium":{"attempt_count":32,"output_max":30004,"output_mean":18825.75,"output_min":4345,"run_count":16},"none":{"attempt_count":17,"output_max":4534,"output_mean":3055.4375,"output_min":2237,"run_count":16}},"display_name":"Kimi K3","economics":{"all":44.39802806565967,"highest":45.32628662666308,"medium":41.38173410851089,"none":48.725624144182824},"first_seen_at":null,"generation_metadata":{"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"moonshotai","provider_model":"moonshotai/kimi-k3","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":15,"evaluated_cells":16,"failed_game_aliases":["GB2-05"],"first_pass_admitted":1,"first_pass_rate":0.0625,"model_code_failure_rate":0.0625,"model_code_failures":1,"repaired_admitted":14,"repaired_rate":0.875},"baseline":{"admitted_plugins":16,"evaluated_cells":16,"first_pass_admitted":15,"first_pass_rate":0.9375,"model_code_failure_rate":0.0,"model_code_failures":0,"repaired_admitted":1,"repaired_rate":0.0625},"intensive":{"admitted_plugins":18,"evaluated_cells":23,"failed_game_aliases":["GB2-03","GB2-05","GB2-06"],"infra_excluded_game_aliases":["GB2-02","GB2-08"],"infra_failures_excluded":3,"model_code_failure_rate":0.21739130434782608,"model_code_failures":5,"repaired_admitted":18,"repaired_rate":0.782608695652174}},"id":"moonshotai/kimi-k3","is_recent_addition":false,"last_measured_at":"2026-07-27T11:59:44Z","match_totals_all":{"draws":1047,"losses":851,"wins":1176},"match_totals_tracks":{"highest":{"draws":412,"losses":407,"wins":528},"medium":{"draws":349,"losses":201,"wins":245},"none":{"draws":286,"losses":243,"wins":403}},"model_slug":"moonshotai-kimi-k3","overall":{"max":67.21194886050958,"mean":45.987768375465144,"min":20.580987520067197},"per_game":{"GB2-01":52.36937197174774,"GB2-02":27.637499866574228,"GB2-04":46.192829786225445,"GB2-05":45.85469736568789,"GB2-06":69.03024505442248,"GB2-07":53.439927382671186,"GB2-08":22.759434959312564},"per_game_all":{"GB2-01":51.71420802889096,"GB2-02":24.772395629381506,"GB2-04":36.55887505532089,"GB2-05":46.71203957601696,"GB2-06":67.2065077574016,"GB2-07":48.86456601485452,"GB2-08":34.957604397751304},"per_game_match_totals_all":{"GB2-01":{"draws":181,"losses":119,"wins":162},"GB2-02":{"draws":371,"losses":50,"wins":29},"GB2-03":{"draws":48,"losses":52,"wins":88},"GB2-04":{"draws":221,"losses":88,"wins":122},"GB2-05":{"draws":0,"losses":131,"wins":178},"GB2-06":{"draws":31,"losses":100,"wins":217},"GB2-07":{"draws":0,"losses":217,"wins":267},"GB2-08":{"draws":195,"losses":94,"wins":113}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":51,"losses":85,"wins":108},"GB2-02":{"draws":169,"losses":29,"wins":20},"GB2-04":{"draws":77,"losses":41,"wins":80},"GB2-05":{"draws":0,"losses":71,"wins":80},"GB2-06":{"draws":12,"losses":35,"wins":81},"GB2-07":{"draws":0,"losses":109,"wins":149},"GB2-08":{"draws":103,"losses":37,"wins":10}},"medium":{"GB2-01":{"draws":65,"losses":15,"wins":22},"GB2-02":{"draws":94,"losses":9,"wins":3},"GB2-03":{"draws":20,"losses":29,"wins":33},"GB2-04":{"draws":78,"losses":29,"wins":20},"GB2-05":{"draws":0,"losses":20,"wins":18},"GB2-06":{"draws":11,"losses":27,"wins":66},"GB2-07":{"draws":0,"losses":44,"wins":64},"GB2-08":{"draws":81,"losses":28,"wins":19}},"none":{"GB2-01":{"draws":65,"losses":19,"wins":32},"GB2-02":{"draws":108,"losses":12,"wins":6},"GB2-03":{"draws":28,"losses":23,"wins":55},"GB2-04":{"draws":66,"losses":18,"wins":22},"GB2-05":{"draws":0,"losses":40,"wins":80},"GB2-06":{"draws":8,"losses":38,"wins":70},"GB2-07":{"draws":0,"losses":64,"wins":54},"GB2-08":{"draws":11,"losses":29,"wins":84}}},"per_game_raw_elo_all":{"GB2-01":1543.8561386919175,"GB2-02":1488.9964454266121,"GB2-04":1520.414008557702,"GB2-05":1555.092423122475,"GB2-06":1627.845550483602,"GB2-07":1533.9562972715742,"GB2-08":1509.5426220490406},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1546.5261237980658,"GB2-02":1487.5571190487,"GB2-04":1567.101366482504,"GB2-05":1521.802394121089,"GB2-06":1644.4298779060618,"GB2-07":1552.2221681288854,"GB2-08":1428.1658766468497},"medium":{"GB2-01":1521.6303368356873,"GB2-02":1488.0188021214274,"GB2-03":1530.631146017652,"GB2-04":1473.5659425899894,"GB2-05":1515.0366203285198,"GB2-06":1628.3092646305533,"GB2-07":1573.87579650109,"GB2-08":1472.7476833365188},"none":{"GB2-01":1563.4119554419992,"GB2-02":1491.4134151097094,"GB2-03":1583.1305040657564,"GB2-04":1520.5747166006124,"GB2-05":1628.4382549178163,"GB2-06":1610.797508914191,"GB2-07":1475.770927184747,"GB2-08":1627.714306163753}},"per_game_tracks":{"highest":{"GB2-01":52.36937197174774,"GB2-02":27.637499866574228,"GB2-04":46.192829786225445,"GB2-05":45.85469736568789,"GB2-06":69.03024505442248,"GB2-07":53.439927382671186,"GB2-08":22.759434959312564},"medium":{"GB2-01":48.37070779104473,"GB2-02":20.580987520067197,"GB2-03":47.41563774645095,"GB2-04":26.244434593609682,"GB2-05":35.24533485626138,"GB2-06":67.21194886050958,"GB2-07":55.562434490225975,"GB2-08":30.422387009917625},"none":{"GB2-01":54.4025443238804,"GB2-02":26.098699501503095,"GB2-03":58.36864528288711,"GB2-04":37.23936078612753,"GB2-05":59.03608650610162,"GB2-06":65.37732935727273,"GB2-07":37.591336171666406,"GB2-08":51.69099122402372}},"provider_color":"#7C3AED","provider_company":"Moonshot","provider_key":"moonshotai","provider_text_color":"#faf5ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":47.65567044796971,"medium":41.58201053424288,"none":48.72562414418283},"reasoning_agg":{"highest":{"max":53.439927382671186,"mean":47.65567044796971,"min":46.192829786225445},"medium":{"max":67.21194886050958,"mean":41.58201053424288,"min":20.580987520067197},"none":{"max":65.37732935727273,"mean":48.72562414418283,"min":26.098699501503095}},"reasoning_labels":{"highest":"Max","medium":"High","none":"Low"},"score_diagnostics":{"ceiling_score":67.21194886050958,"expected_score":45.5048706038373,"reasoning_variance":7.143613609939948,"reliability_score":57.20878818120642,"uncertainty_avg":42.79121181879358,"uncertainty_penalty":-0.4828977716278473},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":53.439927382671186,"expected_score":35.105868984382646,"reliability_score":61.71989076530139,"uncertainty_avg":38.28010923469861,"uncertainty_penalty":-12.549801463587066},"medium":{"ceiling_score":67.21194886050958,"expected_score":41.664637461189194,"reliability_score":51.94423285887227,"uncertainty_avg":48.05576714112773,"uncertainty_penalty":0.08262692694631113},"none":{"ceiling_score":65.37732935727273,"expected_score":63.825115193010156,"reliability_score":57.207672985531204,"uncertainty_avg":42.792327014468796,"uncertainty_penalty":15.099491048827325}}},{"codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":18},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.6921525,"mean":0.4890770625000001,"median":0.483741,"min":0.401826,"recorded_attempt_count":18,"run_count":8,"total":3.912616499999999},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":19},"evidence_basis":"Provider-reported","max":0.5145615,"mean":0.34875300000000004,"median":0.335163,"min":0.254883,"recorded_attempt_count":19,"run_count":8,"total":2.790024}},"codegen_cost_usd":{"admitted_cell_count":14,"cell_count":16,"cost_basis_counts":{"provider_reported":37},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.6921525,"mean":0.41891503125,"median":0.4031475,"min":0.254883,"recorded_attempt_count":37,"run_count":16,"total":6.702640499999999},"codegen_latency_ms":{"attempt_count":37,"max_ms":391025,"mean_ms":206292.5625,"min_ms":126419,"run_count":16},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":18,"max_ms":391025,"mean_ms":243664.625,"min_ms":198838,"run_count":8},"medium":{"attempt_count":19,"max_ms":243355,"mean_ms":168920.5,"min_ms":126419,"run_count":8}},"codegen_output_tokens":{"attempt_count":37,"output_max":74213,"output_mean":43169.4375,"output_min":25565,"run_count":16},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":18,"output_max":74213,"output_mean":51048.625,"output_min":41983,"run_count":8},"medium":{"attempt_count":19,"output_max":52941,"output_mean":35290.25,"output_min":25565,"run_count":8}},"display_name":"Gemini 3.5 Flash","economics":{"highest":41.30954240884414,"medium":52.00774565635941},"first_seen_at":null,"generation_metadata":{"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"google","provider_model":"google/gemini-3.5-flash","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"model_code_failure_rate":0.0,"model_code_failures":0,"repaired_admitted":8,"repaired_rate":1.0},"intensive":{"admitted_plugins":6,"evaluated_cells":8,"failed_game_aliases":["GB2-01","GB2-02"],"model_code_failure_rate":0.25,"model_code_failures":2,"repaired_admitted":6,"repaired_rate":0.75}},"id":"google/gemini-3.5-flash","is_recent_addition":false,"last_measured_at":"2026-07-27T11:53:34Z","match_totals_all":{"draws":272,"losses":242,"wins":302},"match_totals_tracks":{"highest":{"draws":113,"losses":130,"wins":121},"medium":{"draws":159,"losses":112,"wins":181}},"model_slug":"google-gemini-3-5-flash","overall":{"max":89.02948337376621,"mean":45.22530327465701,"min":18.44050863736999},"per_game":{"GB2-03":44.933996869115965,"GB2-04":18.677722595601647,"GB2-05":44.054822590859004,"GB2-06":66.37931618441283,"GB2-07":55.37088757570538,"GB2-08":18.44050863736999},"per_game_match_totals_all":{"GB2-01":{"draws":0,"losses":9,"wins":47},"GB2-02":{"draws":45,"losses":2,"wins":7},"GB2-03":{"draws":49,"losses":15,"wins":30},"GB2-04":{"draws":48,"losses":36,"wins":24},"GB2-05":{"draws":0,"losses":69,"wins":67},"GB2-06":{"draws":19,"losses":28,"wins":65},"GB2-07":{"draws":0,"losses":60,"wins":62},"GB2-08":{"draws":111,"losses":23,"wins":0}},"per_game_match_totals_tracks":{"highest":{"GB2-03":{"draws":35,"losses":2,"wins":7},"GB2-04":{"draws":16,"losses":28,"wins":12},"GB2-05":{"draws":0,"losses":29,"wins":33},"GB2-06":{"draws":8,"losses":19,"wins":35},"GB2-07":{"draws":0,"losses":34,"wins":34},"GB2-08":{"draws":54,"losses":18,"wins":0}},"medium":{"GB2-01":{"draws":0,"losses":9,"wins":47},"GB2-02":{"draws":45,"losses":2,"wins":7},"GB2-03":{"draws":14,"losses":13,"wins":23},"GB2-04":{"draws":32,"losses":8,"wins":12},"GB2-05":{"draws":0,"losses":40,"wins":34},"GB2-06":{"draws":11,"losses":9,"wins":30},"GB2-07":{"draws":0,"losses":26,"wins":28},"GB2-08":{"draws":57,"losses":5,"wins":0}}},"per_game_raw_elo_tracks":{"highest":{"GB2-03":1520.7807241906676,"GB2-04":1434.7932372194414,"GB2-05":1512.4648061510393,"GB2-06":1625.9638890170804,"GB2-07":1574.402889663777,"GB2-08":1400.630372981852},"medium":{"GB2-01":1819.728353888386,"GB2-02":1499.278211372801,"GB2-03":1586.8467498305283,"GB2-04":1535.795958549268,"GB2-05":1469.3980693923404,"GB2-06":1732.4144195081535,"GB2-07":1476.3023229705768,"GB2-08":1402.0511352404135}},"per_game_tracks":{"highest":{"GB2-03":44.933996869115965,"GB2-04":18.677722595601647,"GB2-05":44.054822590859004,"GB2-06":66.37931618441283,"GB2-07":55.37088757570538,"GB2-08":18.44050863736999},"medium":{"GB2-01":89.02948337376621,"GB2-02":33.25253493848372,"GB2-03":60.91553236200583,"GB2-04":42.75642364948741,"GB2-05":41.99685872000467,"GB2-06":82.67382914279403,"GB2-07":44.38532142418434,"GB2-08":21.05198164014908}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#f5f9ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":38.442860892954606,"medium":52.007745656359404},"reasoning_agg":{"highest":{"max":66.37931618441283,"mean":38.442860892954606,"min":18.44050863736999},"medium":{"max":89.02948337376621,"mean":52.007745656359404,"min":21.05198164014908}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Setting not tested"},"score_diagnostics":{"ceiling_score":89.02948337376621,"reasoning_variance":13.564884763404798},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":66.37931618441283,"expected_score":30.29670764261455,"reliability_score":52.841117875870545,"uncertainty_avg":47.158882124129455,"uncertainty_penalty":-8.146153250340056},"medium":{"ceiling_score":89.02948337376621,"expected_score":55.12711703863174,"reliability_score":77.43700169039002,"uncertainty_avg":22.562998309609988,"uncertainty_penalty":3.119371382272334}}},{"codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":15},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.121855,"mean":0.09110296875,"median":0.09280125,"min":0.0343775,"recorded_attempt_count":15,"run_count":8,"total":0.7288237499999999},"none":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.03912625,"mean":0.022799843750000003,"median":0.0216425,"min":0.015285,"recorded_attempt_count":9,"run_count":8,"total":0.18239875}},"codegen_cost_usd":{"admitted_cell_count":14,"cell_count":16,"cost_basis_counts":{"provider_reported":24},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.121855,"mean":0.05695140625,"median":0.036751875,"min":0.015285,"recorded_attempt_count":24,"run_count":16,"total":0.9112225},"codegen_latency_ms":{"attempt_count":24,"max_ms":500731,"mean_ms":212687.25,"min_ms":38716,"run_count":16},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":15,"max_ms":500731,"mean_ms":358367.875,"min_ms":131800,"run_count":8},"none":{"attempt_count":9,"max_ms":115558,"mean_ms":67006.625,"min_ms":38716,"run_count":8}},"codegen_output_tokens":{"attempt_count":24,"output_max":27099,"output_mean":11144.8125,"output_min":1575,"run_count":16},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":15,"output_max":27099,"output_mean":19189.625,"output_min":6698,"run_count":8},"none":{"attempt_count":9,"output_max":5506,"output_mean":3100.0,"output_min":1575,"run_count":8}},"display_name":"Qwen3.7 Max","economics":{"medium":41.598580199122026,"none":45.267658771883625},"first_seen_at":null,"generation_metadata":{"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"qwen","provider_model":"qwen/qwen3.7-max","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-03"],"first_pass_admitted":1,"first_pass_rate":0.125,"model_code_failure_rate":0.125,"model_code_failures":1,"repaired_admitted":6,"repaired_rate":0.75},"baseline":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-04"],"first_pass_admitted":7,"first_pass_rate":0.875,"model_code_failure_rate":0.125,"model_code_failures":1}},"id":"qwen/qwen3.7-max","is_recent_addition":false,"last_measured_at":"2026-07-27T11:59:32Z","match_totals_all":{"draws":305,"losses":272,"wins":271},"match_totals_tracks":{"medium":{"draws":156,"losses":136,"wins":140},"none":{"draws":149,"losses":136,"wins":131}},"model_slug":"qwen-qwen3-7-max","overall":{"max":78.20945134532496,"mean":42.007132433322745,"min":28.574021625817622},"per_game_match_totals_all":{"GB2-01":{"draws":41,"losses":43,"wins":44},"GB2-02":{"draws":99,"losses":3,"wins":6},"GB2-03":{"draws":39,"losses":7,"wins":4},"GB2-04":{"draws":33,"losses":9,"wins":8},"GB2-05":{"draws":0,"losses":66,"wins":56},"GB2-06":{"draws":9,"losses":63,"wins":52},"GB2-07":{"draws":0,"losses":44,"wins":88},"GB2-08":{"draws":84,"losses":37,"wins":13}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":24,"losses":25,"wins":15},"GB2-02":{"draws":53,"losses":2,"wins":3},"GB2-04":{"draws":33,"losses":9,"wins":8},"GB2-05":{"draws":0,"losses":32,"wins":28},"GB2-06":{"draws":9,"losses":31,"wins":32},"GB2-07":{"draws":0,"losses":22,"wins":46},"GB2-08":{"draws":37,"losses":15,"wins":8}},"none":{"GB2-01":{"draws":17,"losses":18,"wins":29},"GB2-02":{"draws":46,"losses":1,"wins":3},"GB2-03":{"draws":39,"losses":7,"wins":4},"GB2-05":{"draws":0,"losses":34,"wins":28},"GB2-06":{"draws":0,"losses":32,"wins":20},"GB2-07":{"draws":0,"losses":22,"wins":42},"GB2-08":{"draws":47,"losses":22,"wins":5}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1413.8795717766495,"GB2-02":1498.8227626605349,"GB2-04":1505.9919152699777,"GB2-05":1530.497151230373,"GB2-06":1516.5320737959407,"GB2-07":1667.5150915775343,"GB2-08":1481.8014648809944},"none":{"GB2-01":1582.8274794165334,"GB2-02":1502.5488228935112,"GB2-03":1441.1397761187798,"GB2-05":1521.2856555640442,"GB2-06":1354.7769806450185,"GB2-07":1730.8896425336536,"GB2-08":1456.5863157614344}},"per_game_tracks":{"medium":{"GB2-01":34.19470044445362,"GB2-02":28.574021625817622,"GB2-04":32.12887382515068,"GB2-05":46.176411006143624,"GB2-06":52.48135378529035,"GB2-07":67.56797718896486,"GB2-08":30.066723518033452},"none":{"GB2-01":58.72679193774028,"GB2-02":33.53817330743257,"GB2-03":36.25524629697736,"GB2-05":47.692122535876926,"GB2-06":32.299677169988506,"GB2-07":78.20945134532496,"GB2-08":30.15214880984472}},"provider_color":"#FF6A00","provider_company":"Alibaba","provider_key":"qwen","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":40.23282435529362,"none":43.78144051135187},"reasoning_agg":{"medium":{"max":67.56797718896486,"mean":40.23282435529362,"min":28.574021625817622},"none":{"max":78.20945134532496,"mean":43.78144051135187,"min":30.15214880984472}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"score_diagnostics":{"ceiling_score":78.20945134532496,"reasoning_variance":3.5486161560582445},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":67.56797718896486,"expected_score":43.386879265034004,"reliability_score":54.63298336691592,"uncertainty_avg":45.36701663308408,"uncertainty_penalty":3.154054909740381},"none":{"ceiling_score":78.20945134532496,"expected_score":45.47042648414227,"reliability_score":78.96826703997317,"uncertainty_avg":21.031732960026822,"uncertainty_penalty":1.6889859727904053}}},{"codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":10},"evidence_basis":"Standard list-price estimate","max":0.454645,"mean":0.28201406249999994,"median":0.2695775,"min":0.17401125,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":10},"run_count":8,"token_priced_attempt_count":10,"total":2.2561125},"medium":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.21477375,"mean":0.17756265624999998,"median":0.17285124999999998,"min":0.1418975,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":9},"run_count":8,"token_priced_attempt_count":9,"total":1.42050125}},"codegen_cost_usd":{"admitted_cell_count":15,"cell_count":16,"cost_basis_counts":{"local_standard_estimate":19},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.454645,"mean":0.22978835937499997,"median":0.1997375,"min":0.1418975,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":19},"run_count":16,"token_priced_attempt_count":19,"total":3.67661375},"codegen_latency_ms":{"attempt_count":19,"max_ms":452838,"mean_ms":201000.75,"min_ms":115295,"run_count":16},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":10,"max_ms":452838,"mean_ms":260996.125,"min_ms":140461,"run_count":8},"medium":{"attempt_count":9,"max_ms":181508,"mean_ms":141005.375,"min_ms":115295,"run_count":8}},"codegen_output_tokens":{"attempt_count":19,"output_max":43637,"output_mean":21815.875,"output_min":13286,"run_count":16},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":10,"output_max":43637,"output_mean":26965.5,"output_min":16148,"run_count":8},"medium":{"attempt_count":9,"output_max":19618,"output_mean":16666.25,"output_min":13286,"run_count":8}},"display_name":"GPT 5","economics":{"highest":42.010776110623965,"medium":42.75066336563581},"first_seen_at":null,"generation_metadata":{"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-5","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openai","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-02"],"first_pass_admitted":6,"first_pass_rate":0.75,"model_code_failure_rate":0.125,"model_code_failures":1,"repaired_admitted":1,"repaired_rate":0.125},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":6,"first_pass_rate":0.75,"model_code_failure_rate":0.0,"model_code_failures":0,"repaired_admitted":2,"repaired_rate":0.25}},"id":"gpt-5","is_recent_addition":false,"last_measured_at":"2026-07-27T11:53:48Z","match_totals_all":{"draws":302,"losses":307,"wins":314},"match_totals_tracks":{"highest":{"draws":166,"losses":172,"wins":183},"medium":{"draws":136,"losses":135,"wins":131}},"model_slug":"gpt-5","overall":{"max":62.019294143192774,"mean":41.678929340000025,"min":24.622792993226426},"per_game":{"GB2-01":44.818716626603695,"GB2-02":27.927667006728253,"GB2-03":39.83067183067213,"GB2-04":28.918714793887677,"GB2-05":55.71385221064524,"GB2-06":62.019294143192774,"GB2-07":52.23449928003549,"GB2-08":24.622792993226426},"per_game_match_totals_all":{"GB2-01":{"draws":24,"losses":54,"wins":42},"GB2-02":{"draws":50,"losses":10,"wins":4},"GB2-03":{"draws":43,"losses":28,"wins":16},"GB2-04":{"draws":82,"losses":14,"wins":18},"GB2-05":{"draws":0,"losses":61,"wins":71},"GB2-06":{"draws":12,"losses":51,"wins":61},"GB2-07":{"draws":0,"losses":63,"wins":85},"GB2-08":{"draws":91,"losses":26,"wins":17}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":9,"losses":29,"wins":28},"GB2-02":{"draws":50,"losses":10,"wins":4},"GB2-03":{"draws":17,"losses":17,"wins":11},"GB2-04":{"draws":43,"losses":7,"wins":4},"GB2-05":{"draws":0,"losses":30,"wins":44},"GB2-06":{"draws":5,"losses":26,"wins":39},"GB2-07":{"draws":0,"losses":38,"wins":44},"GB2-08":{"draws":42,"losses":15,"wins":9}},"medium":{"GB2-01":{"draws":15,"losses":25,"wins":14},"GB2-03":{"draws":26,"losses":11,"wins":5},"GB2-04":{"draws":39,"losses":7,"wins":14},"GB2-05":{"draws":0,"losses":31,"wins":27},"GB2-06":{"draws":7,"losses":25,"wins":22},"GB2-07":{"draws":0,"losses":25,"wins":41},"GB2-08":{"draws":49,"losses":11,"wins":8}}},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1495.193047600924,"GB2-02":1493.573287927545,"GB2-03":1488.8943604301728,"GB2-04":1487.0161248670333,"GB2-05":1602.9531724861602,"GB2-06":1589.6396414098424,"GB2-07":1544.5012678250691,"GB2-08":1445.205504297169},"medium":{"GB2-01":1359.6393456579792,"GB2-03":1435.8623185574695,"GB2-04":1548.729486332967,"GB2-05":1567.8741951513823,"GB2-06":1498.859087874097,"GB2-07":1571.1643984055847,"GB2-08":1439.8208523917242}},"per_game_tracks":{"highest":{"GB2-01":44.818716626603695,"GB2-02":27.927667006728253,"GB2-03":39.83067183067213,"GB2-04":28.918714793887677,"GB2-05":55.71385221064524,"GB2-06":62.019294143192774,"GB2-07":52.23449928003549,"GB2-08":24.622792993226426},"medium":{"GB2-01":29.205660998009655,"GB2-03":34.51782318989246,"GB2-04":46.07577553411435,"GB2-05":53.05626716087649,"GB2-06":51.70853629281069,"GB2-07":57.44029280728862,"GB2-08":27.25028757645839}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":42.010776110623965,"medium":41.347082569376084},"reasoning_agg":{"highest":{"max":62.019294143192774,"mean":42.010776110623965,"min":24.622792993226426},"medium":{"max":57.44029280728862,"mean":41.347082569376084,"min":27.25028757645839}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Setting not tested"},"score_diagnostics":{"ceiling_score":62.019294143192774,"reasoning_variance":0.6636935412478806},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":62.019294143192774,"expected_score":30.003177840884856,"reliability_score":55.774016295762614,"uncertainty_avg":44.225983704237386,"uncertainty_penalty":-12.007598269739109},"medium":{"ceiling_score":57.44029280728862,"expected_score":41.64887945197632,"reliability_score":77.82431402330744,"uncertainty_avg":22.175685976692556,"uncertainty_penalty":0.30179688260023596}}},{"codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":10,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":10},"evidence_basis":"Standard list-price estimate","max":0.4567,"mean":0.3660333333333334,"median":0.355077,"min":0.234622,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":2,"boardgame-list-prices-2026-07-25":8},"run_count":10,"token_priced_attempt_count":10,"total":3.5443079999999996},"medium":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.132112,"mean":0.0780535,"median":0.06797,"min":0.05673,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":9},"run_count":8,"token_priced_attempt_count":9,"total":0.624428}},"codegen_cost_usd":{"admitted_cell_count":17,"cell_count":16,"cost_basis_counts":{"local_list_price_estimate":19},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.4567,"mean":0.2220434166666667,"median":0.183367,"min":0.05673,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":2,"boardgame-list-prices-2026-07-25":17},"run_count":18,"token_priced_attempt_count":19,"total":4.168736000000001},"codegen_latency_ms":{"attempt_count":19,"max_ms":417022,"mean_ms":186639.61111111112,"min_ms":23645,"run_count":18},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":10,"max_ms":417022,"mean_ms":302024.2,"min_ms":185272,"run_count":10},"medium":{"attempt_count":9,"max_ms":95118,"mean_ms":42408.875,"min_ms":23645,"run_count":8}},"codegen_output_tokens":{"attempt_count":19,"output_max":43177,"output_mean":20523.777777777777,"output_min":3136,"run_count":18},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":10,"output_max":43177,"output_mean":32906.3,"output_min":21120,"run_count":10},"medium":{"attempt_count":9,"output_max":10845,"output_mean":5045.625,"output_min":3136,"run_count":8}},"display_name":"Claude Sonnet 5","economics":{"all":42.035393624300625,"highest":44.83513320324787,"medium":39.484554802264036,"none":41.45827687268098},"first_seen_at":null,"generation_metadata":{"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"anthropic","provider_model":"claude-sonnet-5","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"anthropic","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-03"],"first_pass_admitted":6,"first_pass_rate":0.75,"model_code_failure_rate":0.125,"model_code_failures":1,"repaired_admitted":1,"repaired_rate":0.125},"intensive":{"admitted_plugins":10,"evaluated_cells":10,"first_pass_admitted":10,"first_pass_rate":1.0,"infra_excluded_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-05","GB2-06","GB2-07","GB2-08"],"infra_failures_excluded":18,"model_code_failure_rate":0.0,"model_code_failures":0}},"id":"claude-sonnet-5","is_recent_addition":false,"last_measured_at":"2026-07-27T11:52:58Z","match_totals_all":{"draws":463,"losses":449,"wins":452},"match_totals_tracks":{"highest":{"draws":194,"losses":217,"wins":209},"medium":{"draws":137,"losses":134,"wins":145},"none":{"draws":132,"losses":98,"wins":98}},"model_slug":"claude-sonnet-5","overall":{"max":58.84535558133786,"mean":41.49387209065529,"min":26.09668923633087},"per_game":{"GB2-01":58.84535558133786,"GB2-02":40.24032728154734,"GB2-03":41.66259225389678,"GB2-04":43.23945167121127,"GB2-05":51.609766414462925,"GB2-06":54.55378800839192,"GB2-07":36.6633342427911,"GB2-08":31.86645017234374},"per_game_all":{"GB2-01":51.68440504844049,"GB2-02":32.45331398702496,"GB2-04":38.090113557211005,"GB2-05":45.26880274246346,"GB2-06":52.12574088675353,"GB2-07":46.05228749523304,"GB2-08":28.573091652977855},"per_game_match_totals_all":{"GB2-01":{"draws":33,"losses":54,"wins":93},"GB2-02":{"draws":124,"losses":16,"wins":8},"GB2-03":{"draws":59,"losses":59,"wins":44},"GB2-04":{"draws":104,"losses":16,"wins":22},"GB2-05":{"draws":0,"losses":92,"wins":92},"GB2-06":{"draws":14,"losses":86,"wins":90},"GB2-07":{"draws":0,"losses":89,"wins":87},"GB2-08":{"draws":129,"losses":37,"wins":16}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":14,"losses":19,"wins":43},"GB2-02":{"draws":39,"losses":10,"wins":7},"GB2-03":{"draws":46,"losses":44,"wins":34},"GB2-04":{"draws":43,"losses":8,"wins":11},"GB2-05":{"draws":0,"losses":38,"wins":38},"GB2-06":{"draws":10,"losses":33,"wins":39},"GB2-07":{"draws":0,"losses":39,"wins":27},"GB2-08":{"draws":42,"losses":26,"wins":10}},"medium":{"GB2-01":{"draws":7,"losses":26,"wins":27},"GB2-02":{"draws":50,"losses":3,"wins":1},"GB2-04":{"draws":32,"losses":7,"wins":7},"GB2-05":{"draws":0,"losses":27,"wins":35},"GB2-06":{"draws":3,"losses":32,"wins":33},"GB2-07":{"draws":0,"losses":30,"wins":36},"GB2-08":{"draws":45,"losses":9,"wins":6}},"none":{"GB2-01":{"draws":12,"losses":9,"wins":23},"GB2-02":{"draws":35,"losses":3,"wins":0},"GB2-03":{"draws":13,"losses":15,"wins":10},"GB2-04":{"draws":29,"losses":1,"wins":4},"GB2-05":{"draws":0,"losses":27,"wins":19},"GB2-06":{"draws":1,"losses":21,"wins":18},"GB2-07":{"draws":0,"losses":20,"wins":24},"GB2-08":{"draws":42,"losses":2,"wins":0}}},"per_game_raw_elo_all":{"GB2-01":1531.0825744827919,"GB2-02":1498.9869959976656,"GB2-04":1516.2115935940358,"GB2-05":1502.0443611819685,"GB2-06":1499.5517492917786,"GB2-07":1487.5809327994348,"GB2-08":1452.1542498097053},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1579.7115495088487,"GB2-02":1527.5674418666176,"GB2-03":1478.826703359781,"GB2-04":1533.6717755962163,"GB2-05":1549.2728597100909,"GB2-06":1510.098396671887,"GB2-07":1412.1255644657329,"GB2-08":1466.4677843586585},"medium":{"GB2-01":1450.988870016457,"GB2-02":1489.9472910874329,"GB2-04":1487.5701896988592,"GB2-05":1520.9036581003338,"GB2-06":1480.3349355924784,"GB2-07":1486.9450008445583,"GB2-08":1443.826362619811},"none":{"GB2-01":1562.54730392307,"GB2-02":1479.446255038946,"GB2-03":1485.0924616716402,"GB2-04":1527.3928154870323,"GB2-05":1435.9565657354813,"GB2-06":1508.2219156109704,"GB2-07":1563.6722330880127,"GB2-08":1446.1686024506469}},"per_game_tracks":{"highest":{"GB2-01":58.84535558133786,"GB2-02":40.24032728154734,"GB2-03":41.66259225389678,"GB2-04":43.23945167121127,"GB2-05":51.609766414462925,"GB2-06":54.55378800839192,"GB2-07":36.6633342427911,"GB2-08":31.86645017234374},"medium":{"GB2-01":41.41203641046077,"GB2-02":31.022925443196662,"GB2-04":32.47196362002854,"GB2-05":47.646494167430816,"GB2-06":50.00396058789727,"GB2-07":46.43780435774322,"GB2-08":27.396699029090957},"none":{"GB2-01":54.79582315352283,"GB2-02":26.09668923633087,"GB2-03":42.333305859069256,"GB2-04":38.55892538039321,"GB2-05":36.55014764549661,"GB2-06":51.81947406397143,"GB2-07":55.05572388516481,"GB2-08":26.45612575749886}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":44.835133203247864,"medium":38.18820619603701,"none":41.45827687268098},"reasoning_agg":{"highest":{"max":58.84535558133786,"mean":44.835133203247864,"min":31.86645017234374},"medium":{"max":50.00396058789727,"mean":38.18820619603701,"min":27.396699029090957},"none":{"max":55.05572388516481,"mean":41.45827687268098,"min":26.09668923633087}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Thinking disabled"},"score_diagnostics":{"ceiling_score":58.84535558133786,"expected_score":36.99995231088667,"reasoning_variance":6.646927007210856,"reliability_score":76.73717682524949,"uncertainty_avg":23.26282317475051,"uncertainty_penalty":-4.493919779768618},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":58.84535558133786,"expected_score":29.048797178487607,"reliability_score":82.17648806938169,"uncertainty_avg":17.823511930618313,"uncertainty_penalty":-15.786336024760256},"medium":{"ceiling_score":50.00396058789727,"expected_score":35.320548127794424,"reliability_score":79.08413007370345,"uncertainty_avg":20.915869926296555,"uncertainty_penalty":-2.8676580682425836},"none":{"ceiling_score":55.05572388516481,"expected_score":46.49066858892597,"reliability_score":66.34128078485399,"uncertainty_avg":33.65871921514601,"uncertainty_penalty":5.032391716244987}}},{"codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":4,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"evidence_basis":"Standard list-price estimate","failed_cell_count":4,"max":0.055222,"mean":0.046879,"median":0.046959,"min":0.039474,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":8},"run_count":8,"token_priced_attempt_count":8,"total":0.375032},"medium":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"evidence_basis":"Standard list-price estimate","failed_cell_count":2,"max":0.072978,"mean":0.048872,"median":0.046325000000000005,"min":0.03731,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":8},"run_count":8,"token_priced_attempt_count":8,"total":0.390976},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":13},"evidence_basis":"Standard list-price estimate","max":0.136952,"mean":0.07424775,"median":0.070604,"min":0.041758,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":13},"run_count":8,"token_priced_attempt_count":13,"total":0.593982}},"codegen_cost_usd":{"admitted_cell_count":18,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":29},"evidence_basis":"Standard list-price estimate","failed_cell_count":6,"max":0.136952,"mean":0.056666249999999994,"median":0.050531999999999994,"min":0.03731,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":13,"boardgame-list-prices-2026-07-25":16},"run_count":24,"token_priced_attempt_count":29,"total":1.3599900000000005},"codegen_latency_ms":{"attempt_count":29,"max_ms":130647,"mean_ms":59683.958333333336,"min_ms":17534,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":8,"max_ms":39668,"mean_ms":28324.375,"min_ms":19788,"run_count":8},"medium":{"attempt_count":8,"max_ms":79649,"mean_ms":42263.5,"min_ms":17534,"run_count":8},"none":{"attempt_count":13,"max_ms":130647,"mean_ms":108464.0,"min_ms":46796,"run_count":8}},"codegen_output_tokens":{"attempt_count":29,"output_max":12043,"output_mean":4816.25,"output_min":2653,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":8,"output_max":5073,"output_mean":3923.0,"output_min":3125,"run_count":8},"medium":{"attempt_count":8,"output_max":6616,"output_mean":4172.125,"output_min":2653,"run_count":8},"none":{"attempt_count":13,"output_max":12043,"output_mean":6353.625,"output_min":3209,"run_count":8}},"display_name":"O3","economics":{"all":44.96086315313599,"highest":44.35747664972329,"medium":43.92209000400485,"none":36.721824761133135},"first_seen_at":null,"generation_metadata":{"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"o3","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openai","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":6,"evaluated_cells":8,"failed_game_aliases":["GB2-02","GB2-03"],"first_pass_admitted":6,"first_pass_rate":0.75,"model_code_failure_rate":0.25,"model_code_failures":2},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":4,"first_pass_rate":0.5,"model_code_failure_rate":0.0,"model_code_failures":0,"repaired_admitted":4,"repaired_rate":0.5},"intensive":{"admitted_plugins":4,"evaluated_cells":8,"failed_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04"],"first_pass_admitted":4,"first_pass_rate":0.5,"infra_excluded_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-05","GB2-06","GB2-07","GB2-08"],"infra_failures_excluded":24,"model_code_failure_rate":0.5,"model_code_failures":4}},"id":"o3","is_recent_addition":false,"last_measured_at":"2026-07-27T11:59:44Z","match_totals_all":{"draws":198,"losses":360,"wins":386},"match_totals_tracks":{"highest":{"draws":12,"losses":136,"wins":140},"medium":{"draws":99,"losses":132,"wins":135},"none":{"draws":87,"losses":92,"wins":111}},"model_slug":"o3","overall":{"max":83.5076304126712,"mean":40.65113726350103,"min":17.83316943117343},"per_game":{"GB2-05":42.19349702401932,"GB2-06":48.39619884773006,"GB2-07":35.574874573353014,"GB2-08":51.26533615379074},"per_game_all":{"GB2-05":42.01471627127139,"GB2-06":62.87263014562418,"GB2-07":41.731264700176816,"GB2-08":33.22484149547157},"per_game_match_totals_all":{"GB2-01":{"draws":14,"losses":36,"wins":42},"GB2-02":{"draws":30,"losses":1,"wins":1},"GB2-03":{"draws":19,"losses":11,"wins":2},"GB2-04":{"draws":59,"losses":15,"wins":8},"GB2-05":{"draws":0,"losses":85,"wins":99},"GB2-06":{"draws":21,"losses":55,"wins":88},"GB2-07":{"draws":0,"losses":94,"wins":86},"GB2-08":{"draws":55,"losses":63,"wins":60}},"per_game_match_totals_tracks":{"highest":{"GB2-05":{"draws":0,"losses":39,"wins":37},"GB2-06":{"draws":10,"losses":27,"wins":33},"GB2-07":{"draws":0,"losses":40,"wins":28},"GB2-08":{"draws":2,"losses":30,"wins":42}},"medium":{"GB2-01":{"draws":7,"losses":21,"wins":26},"GB2-04":{"draws":44,"losses":7,"wins":3},"GB2-05":{"draws":0,"losses":32,"wins":36},"GB2-06":{"draws":10,"losses":24,"wins":26},"GB2-07":{"draws":0,"losses":30,"wins":34},"GB2-08":{"draws":38,"losses":18,"wins":10}},"none":{"GB2-01":{"draws":7,"losses":15,"wins":16},"GB2-02":{"draws":30,"losses":1,"wins":1},"GB2-03":{"draws":19,"losses":11,"wins":2},"GB2-04":{"draws":15,"losses":8,"wins":5},"GB2-05":{"draws":0,"losses":14,"wins":26},"GB2-06":{"draws":1,"losses":4,"wins":29},"GB2-07":{"draws":0,"losses":24,"wins":24},"GB2-08":{"draws":15,"losses":15,"wins":8}}},"per_game_raw_elo_all":{"GB2-05":1510.2742448556048,"GB2-06":1590.2176340482372,"GB2-07":1473.8713198218484,"GB2-08":1517.6071625651118},"per_game_raw_elo_tracks":{"highest":{"GB2-05":1489.950348493604,"GB2-06":1486.847787377084,"GB2-07":1422.872779287951,"GB2-08":1611.591302525787},"medium":{"GB2-01":1521.3936825716696,"GB2-04":1460.2028298284708,"GB2-05":1497.821508842899,"GB2-06":1533.5565018760735,"GB2-07":1537.8619196179889,"GB2-08":1462.0021926743475},"none":{"GB2-01":1483.123014784552,"GB2-02":1479.8188659817515,"GB2-03":1457.5588113209724,"GB2-04":1468.27005544933,"GB2-05":1543.0508772303115,"GB2-06":1750.2486128915534,"GB2-07":1460.8792605596052,"GB2-08":1479.2279924952009}},"per_game_tracks":{"highest":{"GB2-05":42.19349702401932,"GB2-06":48.39619884773006,"GB2-07":35.574874573353014,"GB2-08":51.26533615379074},"medium":{"GB2-01":50.19447975472116,"GB2-04":27.89874606250913,"GB2-05":45.157076581963906,"GB2-06":56.714061176471255,"GB2-07":52.99215754691314,"GB2-08":30.576018901450553},"none":{"GB2-01":43.91604697226371,"GB2-02":24.852438966409498,"GB2-03":22.89145366159343,"GB2-04":25.45352145685857,"GB2-05":38.69357520783093,"GB2-06":83.5076304126712,"GB2-07":36.62676198026428,"GB2-08":17.83316943117343}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":44.35747664972328,"medium":40.87411037964668,"none":36.72182476113313},"reasoning_agg":{"highest":{"max":51.26533615379074,"mean":44.35747664972328,"min":35.574874573353014},"medium":{"max":56.714061176471255,"mean":40.87411037964668,"min":27.89874606250913},"none":{"max":83.5076304126712,"mean":36.72182476113313,"min":17.83316943117343}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"score_diagnostics":{"ceiling_score":83.5076304126712,"expected_score":45.59129337833259,"reasoning_variance":7.635651888590154,"reliability_score":60.548392551315594,"uncertainty_avg":39.451607448684406,"uncertainty_penalty":4.940156114831559},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":51.26533615379074,"expected_score":34.11260910171706,"reliability_score":61.052454455122714,"uncertainty_avg":38.947545544877286,"uncertainty_penalty":-10.24486754800622},"medium":{"ceiling_score":56.714061176471255,"expected_score":40.43577693690498,"reliability_score":80.05776192087703,"uncertainty_avg":19.942238079122973,"uncertainty_penalty":-0.43833344274170116},"none":{"ceiling_score":83.5076304126712,"expected_score":44.35904466736434,"reliability_score":44.11968116272169,"uncertainty_avg":55.88031883727831,"uncertainty_penalty":7.637219906231209}}},{"codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":19,"cell_count":8,"cost_basis_counts":{"provider_reported":57},"evidence_basis":"Provider-reported","failed_cell_count":8,"max":0.25293804044999996,"mean":0.19953128278325,"median":0.20662718916666667,"min":0.13279406625,"recorded_attempt_count":57,"run_count":27,"total":5.24138213703}},"codegen_cost_usd":{"admitted_cell_count":19,"cell_count":8,"cost_basis_counts":{"provider_reported":57},"evidence_basis":"Provider-reported","failed_cell_count":8,"max":0.25293804044999996,"mean":0.19953128278325,"median":0.20662718916666667,"min":0.13279406625,"recorded_attempt_count":57,"run_count":27,"total":5.24138213703},"codegen_latency_ms":{"attempt_count":57,"max_ms":3869582,"mean_ms":1358902.4074074074,"min_ms":364048,"run_count":27},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":57,"max_ms":3869582,"mean_ms":1358902.4074074074,"min_ms":364048,"run_count":27}},"codegen_output_tokens":{"attempt_count":57,"output_max":109372,"output_mean":63750.148148148146,"output_min":27968,"run_count":27},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":57,"output_max":109372,"output_mean":63750.148148148146,"output_min":27968,"run_count":27}},"display_name":"GLM-5.2","economics":{"all":42.82355883512063,"highest":44.87374152511646,"medium":43.93076557633315,"none":39.66616940391225},"first_seen_at":null,"generation_metadata":{"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"z-ai","provider_model":"z-ai/glm-5.2","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"intensive":{"admitted_plugins":19,"evaluated_cells":27,"failed_game_aliases":["GB2-01","GB2-03","GB2-04","GB2-06"],"first_pass_admitted":1,"first_pass_rate":0.037037037037037035,"infra_excluded_game_aliases":["GB2-03","GB2-06"],"infra_failures_excluded":2,"model_code_failure_rate":0.2962962962962963,"model_code_failures":8,"repaired_admitted":18,"repaired_rate":0.6666666666666666}},"id":"z-ai/glm-5.2","is_recent_addition":false,"last_measured_at":"2026-07-27T11:37:08Z","match_totals_all":{"draws":1001,"losses":1004,"wins":996},"match_totals_tracks":{"highest":{"draws":428,"losses":392,"wins":377},"medium":{"draws":245,"losses":192,"wins":227},"none":{"draws":328,"losses":420,"wins":392}},"model_slug":"z-ai-glm-5-2","overall":{"max":68.70041680687149,"mean":40.584909218159005,"min":24.41934796442663},"per_game":{"GB2-01":47.54578462463877,"GB2-02":30.05739733199343,"GB2-03":44.58016839641555,"GB2-04":31.882383562863147,"GB2-05":47.81950080868389,"GB2-06":68.3352570412757,"GB2-07":57.37331813393658,"GB2-08":31.39612230112461},"per_game_all":{"GB2-01":44.15349049981109,"GB2-02":26.989338118308595,"GB2-03":40.26406815057252,"GB2-04":33.06794511537238,"GB2-05":47.26588148239879,"GB2-06":60.01200483001918,"GB2-07":57.50245784268399,"GB2-08":33.33328464179842},"per_game_match_totals_all":{"GB2-01":{"draws":126,"losses":133,"wins":125},"GB2-02":{"draws":287,"losses":29,"wins":13},"GB2-03":{"draws":103,"losses":63,"wins":48},"GB2-04":{"draws":220,"losses":71,"wins":59},"GB2-05":{"draws":0,"losses":253,"wins":237},"GB2-06":{"draws":29,"losses":129,"wins":138},"GB2-07":{"draws":0,"losses":204,"wins":272},"GB2-08":{"draws":236,"losses":122,"wins":104}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":68,"losses":28,"wins":24},"GB2-02":{"draws":146,"losses":19,"wins":10},"GB2-03":{"draws":38,"losses":31,"wins":27},"GB2-04":{"draws":82,"losses":28,"wins":20},"GB2-05":{"draws":0,"losses":110,"wins":100},"GB2-06":{"draws":6,"losses":17,"wins":31},"GB2-07":{"draws":0,"losses":92,"wins":122},"GB2-08":{"draws":88,"losses":67,"wins":43}},"medium":{"GB2-01":{"draws":35,"losses":25,"wins":28},"GB2-02":{"draws":38,"losses":2,"wins":0},"GB2-03":{"draws":19,"losses":6,"wins":5},"GB2-04":{"draws":35,"losses":20,"wins":17},"GB2-05":{"draws":0,"losses":44,"wins":50},"GB2-06":{"draws":10,"losses":26,"wins":44},"GB2-07":{"draws":0,"losses":51,"wins":77},"GB2-08":{"draws":108,"losses":18,"wins":6}},"none":{"GB2-01":{"draws":23,"losses":80,"wins":73},"GB2-02":{"draws":103,"losses":8,"wins":3},"GB2-03":{"draws":46,"losses":26,"wins":16},"GB2-04":{"draws":103,"losses":23,"wins":22},"GB2-05":{"draws":0,"losses":99,"wins":87},"GB2-06":{"draws":13,"losses":86,"wins":63},"GB2-07":{"draws":0,"losses":61,"wins":73},"GB2-08":{"draws":40,"losses":37,"wins":55}}},"per_game_raw_elo_all":{"GB2-01":1477.7471922828279,"GB2-02":1478.624514371026,"GB2-03":1476.0649126481565,"GB2-04":1492.537678517562,"GB2-05":1521.7518894474572,"GB2-06":1566.4979218139588,"GB2-07":1578.4427776896543,"GB2-08":1486.9990976079453},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1498.2804328508075,"GB2-02":1483.9311490852626,"GB2-03":1491.4955399082585,"GB2-04":1476.49235088285,"GB2-05":1519.457026192892,"GB2-06":1623.151639774578,"GB2-07":1569.0514573847759,"GB2-08":1467.3701302724855},"medium":{"GB2-01":1455.6399619899837,"GB2-02":1470.8448216282686,"GB2-03":1483.8175424040835,"GB2-04":1493.572395842094,"GB2-05":1586.7624035224435,"GB2-06":1634.4148964003216,"GB2-07":1615.0897353689143,"GB2-08":1457.0274966044346},"none":{"GB2-01":1479.3211820076922,"GB2-02":1481.097572399547,"GB2-03":1452.8816556321274,"GB2-04":1507.548288827742,"GB2-05":1459.0362386270358,"GB2-06":1441.9272292669764,"GB2-07":1551.187140315273,"GB2-08":1536.5996659469154}},"per_game_tracks":{"highest":{"GB2-01":47.54578462463877,"GB2-02":30.05739733199343,"GB2-03":44.58016839641555,"GB2-04":31.882383562863147,"GB2-05":47.81950080868389,"GB2-06":68.3352570412757,"GB2-07":57.37331813393658,"GB2-08":31.39612230112461},"medium":{"GB2-01":40.92380669690927,"GB2-02":24.41934796442663,"GB2-03":40.79896136680666,"GB2-04":32.17642355544414,"GB2-05":54.63527551118202,"GB2-06":68.70041680687149,"GB2-07":61.653545677315115,"GB2-08":28.138347031709902},"none":{"GB2-01":43.99088017788524,"GB2-02":26.491269058505726,"GB2-03":35.413074688495364,"GB2-04":35.14502822780986,"GB2-05":39.34286812733045,"GB2-06":43.00034064191036,"GB2-07":53.48050971680028,"GB2-08":40.46538459256074}},"provider_color":"#2563EB","provider_company":"Zhipu","provider_key":"z-ai","provider_text_color":"#f8fbff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":38.15779267423163,"medium":43.93076557633315,"none":39.66616940391225},"reasoning_agg":{"highest":{"max":57.37331813393658,"mean":38.15779267423163,"min":30.05739733199343},"medium":{"max":68.70041680687149,"mean":43.93076557633315,"min":24.41934796442663},"none":{"max":53.48050971680028,"mean":39.66616940391225,"min":26.491269058505726}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Reasoning disabled"},"score_diagnostics":{"ceiling_score":68.70041680687149,"expected_score":38.266415812691655,"reasoning_variance":5.772972902101522,"reliability_score":70.3781275453573,"uncertainty_avg":29.6218724546427,"uncertainty_penalty":-2.3184934054673505},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":57.37331813393658,"expected_score":29.752961434685794,"reliability_score":79.96124781069804,"uncertainty_avg":20.038752189301967,"uncertainty_penalty":-8.404831239545835},"medium":{"ceiling_score":68.70041680687149,"expected_score":41.31461134717893,"reliability_score":65.60050591175388,"uncertainty_avg":34.39949408824612,"uncertainty_penalty":-2.616154229154219},"none":{"ceiling_score":53.48050971680028,"expected_score":43.731674656210224,"reliability_score":65.57262891362001,"uncertainty_avg":34.42737108637999,"uncertainty_penalty":4.065505252297974}}},{"codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":16},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.10909930499999998,"mean":0.082847753875,"median":0.084146916,"min":0.03951746,"recorded_attempt_count":16,"run_count":8,"total":0.662782031},"none":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.029078938,"mean":0.015562441375,"median":0.0131167185,"min":0.005612805,"recorded_attempt_count":12,"run_count":8,"total":0.124499531}},"codegen_cost_usd":{"admitted_cell_count":13,"cell_count":16,"cost_basis_counts":{"provider_reported":28},"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.10909930499999998,"mean":0.049205097625000006,"median":0.034298199,"min":0.005612805,"recorded_attempt_count":28,"run_count":16,"total":0.7872815620000001},"codegen_latency_ms":{"attempt_count":28,"max_ms":1214284,"mean_ms":465438.125,"min_ms":42870,"run_count":16},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":16,"max_ms":1214284,"mean_ms":845698.625,"min_ms":162422,"run_count":8},"none":{"attempt_count":12,"max_ms":162843,"mean_ms":85177.625,"min_ms":42870,"run_count":8}},"codegen_output_tokens":{"attempt_count":28,"output_max":80681,"output_mean":29459.75,"output_min":2689,"run_count":16},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":16,"output_max":80681,"output_mean":54027.75,"output_min":8210,"run_count":8},"none":{"attempt_count":12,"output_max":7681,"output_mean":4891.75,"output_min":2689,"run_count":8}},"display_name":"DeepSeek V4 Pro","economics":{"highest":45.7754669580277,"none":39.69653399014509},"first_seen_at":null,"generation_metadata":{"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"deepseek","provider_model":"deepseek/deepseek-v4-pro","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"baseline":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-04"],"first_pass_admitted":4,"first_pass_rate":0.5,"model_code_failure_rate":0.125,"model_code_failures":1,"repaired_admitted":3,"repaired_rate":0.375},"intensive":{"admitted_plugins":6,"evaluated_cells":8,"failed_game_aliases":["GB2-02","GB2-03"],"first_pass_admitted":1,"first_pass_rate":0.125,"model_code_failure_rate":0.25,"model_code_failures":2,"repaired_admitted":5,"repaired_rate":0.625}},"id":"deepseek/deepseek-v4-pro","is_recent_addition":false,"last_measured_at":"2026-07-27T11:59:44Z","match_totals_all":{"draws":242,"losses":285,"wins":287},"match_totals_tracks":{"highest":{"draws":90,"losses":144,"wins":150},"none":{"draws":152,"losses":141,"wins":137}},"model_slug":"deepseek-deepseek-v4-pro","overall":{"max":76.49983872640665,"mean":40.49604885328687,"min":21.132140682151817},"per_game":{"GB2-01":45.46304512513314,"GB2-04":23.38150584800255,"GB2-05":76.49983872640665,"GB2-06":41.325050962101,"GB2-07":60.25603724598094,"GB2-08":27.727323840541924},"per_game_match_totals_all":{"GB2-01":{"draws":39,"losses":46,"wins":51},"GB2-02":{"draws":48,"losses":1,"wins":1},"GB2-03":{"draws":14,"losses":27,"wins":9},"GB2-04":{"draws":22,"losses":19,"wins":7},"GB2-05":{"draws":0,"losses":62,"wins":80},"GB2-06":{"draws":8,"losses":46,"wins":66},"GB2-07":{"draws":0,"losses":66,"wins":64},"GB2-08":{"draws":111,"losses":18,"wins":9}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":12,"losses":22,"wins":28},"GB2-04":{"draws":22,"losses":19,"wins":7},"GB2-05":{"draws":0,"losses":23,"wins":49},"GB2-06":{"draws":2,"losses":34,"wins":26},"GB2-07":{"draws":0,"losses":36,"wins":34},"GB2-08":{"draws":54,"losses":10,"wins":6}},"none":{"GB2-01":{"draws":27,"losses":24,"wins":23},"GB2-02":{"draws":48,"losses":1,"wins":1},"GB2-03":{"draws":14,"losses":27,"wins":9},"GB2-05":{"draws":0,"losses":39,"wins":31},"GB2-06":{"draws":6,"losses":12,"wins":40},"GB2-07":{"draws":0,"losses":30,"wins":30},"GB2-08":{"draws":57,"losses":8,"wins":3}}},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1481.3892527994904,"GB2-04":1440.733349521438,"GB2-05":1758.883007674556,"GB2-06":1417.6969290178033,"GB2-07":1591.3212202571904,"GB2-08":1442.2170907590032},"none":{"GB2-01":1494.5716412258355,"GB2-02":1502.3246516528714,"GB2-03":1351.7838803092702,"GB2-05":1407.767805319223,"GB2-06":1666.5668321788196,"GB2-07":1427.2591466449226,"GB2-08":1446.802549177008}},"per_game_tracks":{"highest":{"GB2-01":45.46304512513314,"GB2-04":23.38150584800255,"GB2-05":76.49983872640665,"GB2-06":41.325050962101,"GB2-07":60.25603724598094,"GB2-08":27.727323840541924},"none":{"GB2-01":47.71947792576954,"GB2-02":33.484607923588854,"GB2-03":21.132140682151817,"GB2-05":34.48204243070537,"GB2-06":74.39181497022835,"GB2-07":38.33378677910713,"GB2-08":28.33186721946456}},"provider_color":"#4C8BF5","provider_company":"DeepSeek","provider_key":"deepseek","provider_text_color":"#f6f9ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":42.598871978808184,"none":38.39322572776556},"reasoning_agg":{"highest":{"max":76.49983872640665,"mean":42.598871978808184,"min":23.38150584800255},"none":{"max":74.39181497022835,"mean":38.39322572776556,"min":21.132140682151817}},"reasoning_labels":{"highest":"XHigh","medium":"Setting not tested","none":"Reasoning disabled"},"score_diagnostics":{"ceiling_score":76.49983872640665,"reasoning_variance":4.205646251042623},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":76.49983872640665,"expected_score":31.347207825316314,"reliability_score":81.31408858070593,"uncertainty_avg":18.685911419294076,"uncertainty_penalty":-11.25166415349187},"none":{"ceiling_score":74.39181497022835,"expected_score":34.87987002043334,"reliability_score":79.97743710982846,"uncertainty_avg":20.022562890171535,"uncertainty_penalty":-3.5133557073322237}}},{"codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":10},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":4.987857,"mean":3.1645696249999995,"median":3.0710854999999997,"min":1.985613,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":10},"run_count":9,"token_priced_attempt_count":10,"total":28.806540999999996},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.046574,"mean":0.036155625,"median":0.035338,"min":0.025803,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":9},"run_count":9,"token_priced_attempt_count":9,"total":0.315048},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"evidence_basis":"Standard list-price estimate","max":0.038815,"mean":0.02196775,"median":0.0196975,"min":0.016152,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":9},"run_count":8,"token_priced_attempt_count":9,"total":0.17574199999999998}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":28},"evidence_basis":"Standard list-price estimate","failed_cell_count":2,"max":4.987857,"mean":1.074231,"median":0.038529,"min":0.016152,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":28},"run_count":26,"token_priced_attempt_count":28,"total":29.297331},"codegen_latency_ms":{"attempt_count":28,"max_ms":220389,"mean_ms":65068.84615384616,"min_ms":7259,"run_count":26},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":10,"max_ms":220389,"mean_ms":159594.88888888888,"min_ms":125171,"run_count":9},"medium":{"attempt_count":9,"max_ms":22604,"mean_ms":17903.777777777777,"min_ms":13783,"run_count":9},"none":{"attempt_count":9,"max_ms":28315,"mean_ms":11787.75,"min_ms":7259,"run_count":8}},"codegen_output_tokens":{"attempt_count":28,"output_max":830024,"output_mean":186407.65384615384,"output_min":1487,"run_count":26},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":10,"output_max":830024,"output_mean":531970.4444444445,"output_min":329738,"run_count":9},"medium":{"attempt_count":9,"output_max":6580,"output_mean":4552.555555555556,"output_min":2724,"run_count":9},"none":{"attempt_count":9,"output_max":4181,"output_mean":2236.5,"output_min":1487,"run_count":8}},"display_name":"GPT-5.6 Luna","economics":{"all":40.28980329852322,"highest":50.27379592979226,"medium":46.845076043069795,"none":23.750537922707622},"first_seen_at":null,"generation_metadata":{"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-5.6-luna","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openai","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":9,"failed_game_aliases":["GB2-06"],"first_pass_admitted":8,"first_pass_rate":0.8888888888888888,"infra_excluded_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-05","GB2-06","GB2-07","GB2-08"],"infra_failures_excluded":8,"model_code_failure_rate":0.1111111111111111,"model_code_failures":1},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"infra_excluded_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-05","GB2-06","GB2-07","GB2-08"],"infra_failures_excluded":8,"model_code_failure_rate":0.0,"model_code_failures":0,"repaired_admitted":1,"repaired_rate":0.125},"intensive":{"admitted_plugins":8,"evaluated_cells":9,"failed_game_aliases":["GB2-03"],"first_pass_admitted":7,"first_pass_rate":0.7777777777777778,"infra_excluded_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-05","GB2-06","GB2-07","GB2-08"],"infra_failures_excluded":8,"model_code_failure_rate":0.1111111111111111,"model_code_failures":1,"repaired_admitted":1,"repaired_rate":0.1111111111111111}},"id":"gpt-5.6-luna","is_recent_addition":false,"last_measured_at":"2026-07-27T11:59:32Z","match_totals_all":{"draws":521,"losses":485,"wins":375},"match_totals_tracks":{"highest":{"draws":132,"losses":154,"wins":184},"medium":{"draws":204,"losses":125,"wins":129},"none":{"draws":185,"losses":206,"wins":62}},"model_slug":"gpt-5-6-luna","overall":{"max":75.31262484978316,"mean":40.289803298523225,"min":0.0},"per_game":{"GB2-01":66.16530892077893,"GB2-02":28.573734971782702,"GB2-03":30.519421112195783,"GB2-04":39.376003042374144,"GB2-05":54.39513803855472,"GB2-06":75.31262484978316,"GB2-07":64.05449486122448,"GB2-08":43.793641641644086},"per_game_all":{"GB2-01":53.47978533160171,"GB2-02":30.24855958317042,"GB2-03":38.76390392907411,"GB2-04":38.01476409552081,"GB2-05":35.68351480235322,"GB2-06":49.77298795027648,"GB2-07":42.42112593476045,"GB2-08":33.93378476142859},"per_game_match_totals_all":{"GB2-01":{"draws":24,"losses":72,"wins":79},"GB2-02":{"draws":172,"losses":6,"wins":0},"GB2-03":{"draws":68,"losses":37,"wins":27},"GB2-04":{"draws":134,"losses":27,"wins":21},"GB2-05":{"draws":0,"losses":113,"wins":65},"GB2-06":{"draws":19,"losses":84,"wins":65},"GB2-07":{"draws":0,"losses":105,"wins":79},"GB2-08":{"draws":104,"losses":41,"wins":39}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":0,"losses":18,"wins":36},"GB2-02":{"draws":64,"losses":6,"wins":0},"GB2-03":{"draws":17,"losses":20,"wins":9},"GB2-04":{"draws":33,"losses":15,"wins":12},"GB2-05":{"draws":0,"losses":31,"wins":35},"GB2-06":{"draws":13,"losses":15,"wins":28},"GB2-07":{"draws":0,"losses":21,"wins":33},"GB2-08":{"draws":5,"losses":28,"wins":31}},"medium":{"GB2-01":{"draws":8,"losses":23,"wins":31},"GB2-02":{"draws":50,"losses":0,"wins":0},"GB2-03":{"draws":32,"losses":4,"wins":4},"GB2-04":{"draws":59,"losses":1,"wins":2},"GB2-05":{"draws":0,"losses":29,"wins":25},"GB2-06":{"draws":6,"losses":24,"wins":28},"GB2-07":{"draws":0,"losses":38,"wins":32},"GB2-08":{"draws":49,"losses":6,"wins":7}},"none":{"GB2-01":{"draws":16,"losses":31,"wins":12},"GB2-02":{"draws":58,"losses":0,"wins":0},"GB2-03":{"draws":19,"losses":13,"wins":14},"GB2-04":{"draws":42,"losses":11,"wins":7},"GB2-05":{"draws":0,"losses":53,"wins":5},"GB2-06":{"draws":0,"losses":45,"wins":9},"GB2-07":{"draws":0,"losses":46,"wins":14},"GB2-08":{"draws":50,"losses":7,"wins":1}}},"per_game_raw_elo_all":{"GB2-01":1544.7668712552984,"GB2-02":1484.6232574138073,"GB2-03":1459.6716459373663,"GB2-04":1507.9903982457588,"GB2-05":1421.9816241639335,"GB2-06":1483.4515812289947,"GB2-07":1458.2052503372408,"GB2-08":1485.5040116956513},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1644.4759251533983,"GB2-02":1473.232701299803,"GB2-03":1409.5840570079213,"GB2-04":1515.0969212350349,"GB2-05":1575.875340508706,"GB2-06":1674.3560486853933,"GB2-07":1626.8615300978795,"GB2-08":1548.0692879399865},"medium":{"GB2-01":1631.9779985185817,"GB2-02":1491.9181454193697,"GB2-03":1487.0489962766576,"GB2-04":1512.834046928935,"GB2-05":1566.3786416398286,"GB2-06":1591.7478127385095,"GB2-07":1502.494574211802,"GB2-08":1466.5807611762505},"none":{"GB2-01":1357.846690093915,"GB2-02":1488.7189255222488,"GB2-03":1482.3818845275205,"GB2-04":1496.0402265733064,"GB2-05":1123.6908903432654,"GB2-06":1184.250882263081,"GB2-07":1245.2596467020408,"GB2-08":1441.8619859707171}},"per_game_tracks":{"highest":{"GB2-01":66.16530892077893,"GB2-02":28.573734971782702,"GB2-03":30.519421112195783,"GB2-04":39.376003042374144,"GB2-05":54.39513803855472,"GB2-06":75.31262484978316,"GB2-07":64.05449486122448,"GB2-08":43.793641641644086},"medium":{"GB2-01":65.00304603642252,"GB2-02":30.997988769059855,"GB2-03":42.932146636436144,"GB2-04":39.08847356683884,"GB2-05":52.65540636850494,"GB2-06":64.38321088344401,"GB2-07":48.65165422462213,"GB2-08":31.048681859229955},"none":{"GB2-01":29.271001037603703,"GB2-02":31.173955008668692,"GB2-03":42.8401440385904,"GB2-04":35.57981567734945,"GB2-05":0.0,"GB2-06":9.62312811760228,"GB2-07":14.557228718434729,"GB2-08":26.959030783411738}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":50.27379592979224,"medium":46.8450760430698,"none":23.750537922707625},"reasoning_agg":{"highest":{"max":75.31262484978316,"mean":50.27379592979224,"min":28.573734971782702},"medium":{"max":65.00304603642252,"mean":46.8450760430698,"min":30.997988769059855},"none":{"max":42.8401440385904,"mean":23.750537922707625,"min":0.0}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"score_diagnostics":{"ceiling_score":75.31262484978316,"expected_score":33.92373046471665,"reasoning_variance":26.523258007084618,"reliability_score":78.01592518430479,"uncertainty_avg":21.9840748156952,"uncertainty_penalty":-6.366072833806577},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":75.31262484978316,"expected_score":36.570273876790836,"reliability_score":78.69266269453183,"uncertainty_avg":21.307337305468174,"uncertainty_penalty":-13.703522053001407},"medium":{"ceiling_score":65.00304603642252,"expected_score":45.29493067239586,"reliability_score":77.63291921290676,"uncertainty_avg":22.367080787093244,"uncertainty_penalty":-1.5501453706739454},"none":{"ceiling_score":42.8401440385904,"expected_score":19.90598684496326,"reliability_score":77.72219364547581,"uncertainty_avg":22.277806354524195,"uncertainty_penalty":-3.8445510777443666}}},{"codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":12,"cell_count":7,"cost_basis_counts":{"local_standard_estimate":15},"evidence_basis":"Standard list-price estimate","max":1.5164726249999998,"mean":1.0182428035714286,"median":0.9670455,"min":0.8356068750000001,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":15},"run_count":12,"token_priced_attempt_count":15,"total":12.214044},"medium":{"admitted_cell_count":23,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":26},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.29749325000000004,"mean":0.24155631250000004,"median":0.24021375,"min":0.17873725,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":26},"run_count":24,"token_priced_attempt_count":26,"total":5.7973515},"none":{"admitted_cell_count":24,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":29},"evidence_basis":"Standard list-price estimate","max":0.021615250000000003,"mean":0.017288937500000004,"median":0.01830825,"min":0.01259225,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":29},"run_count":24,"token_priced_attempt_count":29,"total":0.4149345}},"codegen_cost_usd":{"admitted_cell_count":59,"cell_count":23,"cost_basis_counts":{"local_standard_estimate":70},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":1.5164726249999998,"mean":0.3999331141304348,"median":0.2331955,"min":0.01259225,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":70},"run_count":60,"token_priced_attempt_count":70,"total":18.42633},"codegen_latency_ms":{"attempt_count":70,"max_ms":2003150,"mean_ms":252256.05,"min_ms":9399,"run_count":60},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":15,"max_ms":2003150,"mean_ms":889166.0,"min_ms":660984,"run_count":12},"medium":{"attempt_count":26,"max_ms":308347,"mean_ms":170741.83333333334,"min_ms":75782,"run_count":24},"none":{"attempt_count":29,"max_ms":30363,"mean_ms":15315.291666666666,"min_ms":9399,"run_count":24}},"codegen_output_tokens":{"attempt_count":70,"output_max":440805,"output_mean":65843.35,"output_min":1473,"run_count":60},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":15,"output_max":440805,"output_mean":219612.66666666663,"output_min":114521,"run_count":12},"medium":{"attempt_count":26,"output_max":83384,"output_mean":52370.75,"output_min":25033,"run_count":24},"none":{"attempt_count":29,"output_max":4573,"output_mean":2431.2916666666665,"output_min":1473,"run_count":24}},"display_name":"GPT-5.4 Mini","economics":{"all":39.163981892134416,"highest":45.21060583342231,"medium":41.86048177907101,"none":33.588635387923325},"first_seen_at":null,"generation_metadata":{"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-5.4-mini","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openai","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":23,"evaluated_cells":24,"failed_game_aliases":["GB2-06"],"first_pass_admitted":22,"first_pass_rate":0.9166666666666666,"model_code_failure_rate":0.041666666666666664,"model_code_failures":1,"repaired_admitted":1,"repaired_rate":0.041666666666666664},"baseline":{"admitted_plugins":24,"evaluated_cells":24,"first_pass_admitted":19,"first_pass_rate":0.7916666666666666,"model_code_failure_rate":0.0,"model_code_failures":0,"repaired_admitted":5,"repaired_rate":0.20833333333333337},"intensive":{"admitted_plugins":12,"evaluated_cells":12,"first_pass_admitted":10,"first_pass_rate":0.8333333333333334,"infra_excluded_game_aliases":["GB2-01","GB2-03","GB2-04"],"infra_failures_excluded":6,"model_code_failure_rate":0.0,"model_code_failures":0,"repaired_admitted":2,"repaired_rate":0.16666666666666666}},"id":"gpt-5.4-mini","is_recent_addition":false,"last_measured_at":"2026-07-27T11:59:44Z","match_totals_all":{"draws":1278,"losses":1200,"wins":1031},"match_totals_tracks":{"highest":{"draws":205,"losses":271,"wins":286},"medium":{"draws":485,"losses":433,"wins":397},"none":{"draws":588,"losses":496,"wins":348}},"model_slug":"gpt-5-4-mini","overall":{"max":66.30476749736133,"mean":39.78288745492075,"min":21.382657975617843},"per_game":{"GB2-01":52.12198654872786,"GB2-02":29.44411630713003,"GB2-04":31.60740336660926,"GB2-05":44.753682456063075,"GB2-06":57.264851725461014,"GB2-07":66.30476749736133,"GB2-08":34.97743293260359},"per_game_all":{"GB2-01":43.88193776666151,"GB2-02":30.9828297818831,"GB2-04":36.46147205396677,"GB2-05":37.17584290707089,"GB2-06":51.33413967791534,"GB2-07":44.440556781899204,"GB2-08":29.871094275544095},"per_game_match_totals_all":{"GB2-01":{"draws":101,"losses":193,"wins":154},"GB2-02":{"draws":411,"losses":21,"wins":10},"GB2-03":{"draws":170,"losses":50,"wins":62},"GB2-04":{"draws":281,"losses":53,"wins":76},"GB2-05":{"draws":0,"losses":275,"wins":229},"GB2-06":{"draws":21,"losses":199,"wins":204},"GB2-07":{"draws":0,"losses":279,"wins":218},"GB2-08":{"draws":294,"losses":130,"wins":78}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":4,"losses":19,"wins":35},"GB2-02":{"draws":105,"losses":8,"wins":3},"GB2-04":{"draws":36,"losses":12,"wins":8},"GB2-05":{"draws":0,"losses":77,"wins":67},"GB2-06":{"draws":8,"losses":55,"wins":55},"GB2-07":{"draws":0,"losses":50,"wins":76},"GB2-08":{"draws":52,"losses":50,"wins":42}},"medium":{"GB2-01":{"draws":32,"losses":88,"wins":74},"GB2-02":{"draws":144,"losses":9,"wins":3},"GB2-03":{"draws":77,"losses":28,"wins":31},"GB2-04":{"draws":116,"losses":18,"wins":40},"GB2-05":{"draws":0,"losses":95,"wins":77},"GB2-06":{"draws":5,"losses":50,"wins":65},"GB2-07":{"draws":0,"losses":104,"wins":85},"GB2-08":{"draws":111,"losses":41,"wins":22}},"none":{"GB2-01":{"draws":65,"losses":86,"wins":45},"GB2-02":{"draws":162,"losses":4,"wins":4},"GB2-03":{"draws":93,"losses":22,"wins":31},"GB2-04":{"draws":129,"losses":23,"wins":28},"GB2-05":{"draws":0,"losses":103,"wins":85},"GB2-06":{"draws":8,"losses":94,"wins":84},"GB2-07":{"draws":0,"losses":125,"wins":57},"GB2-08":{"draws":131,"losses":39,"wins":14}}},"per_game_raw_elo_all":{"GB2-01":1469.0957356448826,"GB2-02":1489.1499723576524,"GB2-04":1501.527400689659,"GB2-05":1432.7356802766533,"GB2-06":1493.3400893996752,"GB2-07":1473.1582792903373,"GB2-08":1458.5715326248337},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1534.387956889026,"GB2-02":1481.5020057636186,"GB2-04":1477.865432695363,"GB2-05":1493.3191497437817,"GB2-06":1538.1474467950384,"GB2-07":1640.1550052348434,"GB2-08":1488.5751193579963},"medium":{"GB2-01":1467.8106521935588,"GB2-02":1487.0053737211565,"GB2-03":1514.5537109582262,"GB2-04":1549.3135275728098,"GB2-05":1427.4966669312125,"GB2-06":1539.3980095984984,"GB2-07":1482.0610924621042,"GB2-08":1445.4053682602037},"none":{"GB2-01":1405.0885978520625,"GB2-02":1498.942537588182,"GB2-03":1520.0022000607767,"GB2-04":1477.4032418008044,"GB2-05":1377.3912241549654,"GB2-06":1402.4748118054893,"GB2-07":1297.2587401740645,"GB2-08":1441.7341102563012}},"per_game_tracks":{"highest":{"GB2-01":52.12198654872786,"GB2-02":29.44411630713003,"GB2-04":31.60740336660926,"GB2-05":44.753682456063075,"GB2-06":57.264851725461014,"GB2-07":66.30476749736133,"GB2-08":34.97743293260359},"medium":{"GB2-01":43.801088415817844,"GB2-02":30.047425320937624,"GB2-03":48.172020366997366,"GB2-04":46.0004231200324,"GB2-05":36.25256072815697,"GB2-06":57.47045192344825,"GB2-07":45.63424487271845,"GB2-08":27.50563948445921},"none":{"GB2-01":35.72273833543881,"GB2-02":33.45694771758166,"GB2-03":49.45153806809078,"GB2-04":31.776589675258645,"GB2-05":30.52128553699262,"GB2-06":39.26711538483674,"GB2-07":21.382657975617843,"GB2-08":27.130210409569486}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":46.5489701837238,"medium":39.21105679311512,"none":33.58863538792332},"reasoning_agg":{"highest":{"max":66.30476749736133,"mean":46.5489701837238,"min":29.44411630713003},"medium":{"max":48.172020366997366,"mean":39.21105679311512,"min":27.50563948445921},"none":{"max":49.45153806809078,"mean":33.58863538792332,"min":21.382657975617843}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"score_diagnostics":{"ceiling_score":66.30476749736133,"expected_score":33.03132205815066,"reasoning_variance":12.960334795800485,"reliability_score":79.9413212102912,"uncertainty_avg":20.05867878970879,"uncertainty_penalty":-6.75156539677009},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":66.30476749736133,"expected_score":30.86734409951365,"reliability_score":80.73105764107522,"uncertainty_avg":19.26894235892477,"uncertainty_penalty":-15.681626084210151},"medium":{"ceiling_score":48.172020366997366,"expected_score":39.815320641417,"reliability_score":77.8285638014432,"uncertainty_avg":22.17143619855681,"uncertainty_penalty":0.6042638483018834},"none":{"ceiling_score":49.45153806809078,"expected_score":32.690293771050726,"reliability_score":79.20327397740002,"uncertainty_avg":20.796726022599977,"uncertainty_penalty":-0.8983416168725924}}},{"codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":17},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.2996388,"mean":0.13471628689999998,"median":0.1144847257,"min":0.0276132876,"recorded_attempt_count":17,"run_count":8,"total":1.0777302952},"none":{"admitted_cell_count":6,"cell_count":7,"cost_basis_counts":{"provider_reported":10},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.1311545862,"mean":0.02955606902857143,"median":0.0063034062,"min":0.0057139812,"recorded_attempt_count":10,"run_count":7,"total":0.2068924832}},"codegen_cost_usd":{"admitted_cell_count":12,"cell_count":15,"cost_basis_counts":{"provider_reported":27},"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.2996388,"mean":0.08564151856,"median":0.0495450162,"min":0.0057139812,"recorded_attempt_count":27,"run_count":15,"total":1.2846227784},"codegen_latency_ms":{"attempt_count":27,"max_ms":2144825,"mean_ms":717544.7333333333,"min_ms":43161,"run_count":15},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":17,"max_ms":2144825,"mean_ms":1159734.625,"min_ms":304276,"run_count":8},"none":{"attempt_count":10,"max_ms":886851,"mean_ms":212184.85714285713,"min_ms":43161,"run_count":7}},"codegen_output_tokens":{"attempt_count":27,"output_max":131072,"output_mean":42903.2,"output_min":2846,"run_count":15},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":17,"output_max":131072,"output_mean":71259.5,"output_min":16045,"run_count":8},"none":{"attempt_count":10,"output_max":42691,"output_mean":10496.0,"output_min":2846,"run_count":7}},"display_name":"MiMo-V2.5-Pro","economics":{"medium":42.765828700392,"none":40.96023532559226},"first_seen_at":null,"generation_metadata":{"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"xiaomi","provider_model":"xiaomi/mimo-v2.5-pro","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":6,"evaluated_cells":8,"failed_game_aliases":["GB2-02","GB2-03"],"model_code_failure_rate":0.25,"model_code_failures":2,"repaired_admitted":6,"repaired_rate":0.75},"baseline":{"admitted_plugins":6,"evaluated_cells":7,"failed_game_aliases":["GB2-04"],"first_pass_admitted":4,"first_pass_rate":0.5714285714285714,"model_code_failure_rate":0.14285714285714285,"model_code_failures":1,"repaired_admitted":2,"repaired_rate":0.2857142857142857}},"id":"xiaomi/mimo-v2.5-pro","is_recent_addition":false,"last_measured_at":"2026-07-27T11:52:51Z","match_totals_all":{"draws":192,"losses":296,"wins":260},"match_totals_tracks":{"medium":{"draws":84,"losses":154,"wins":136},"none":{"draws":108,"losses":142,"wins":124}},"model_slug":"xiaomi-mimo-v2-5-pro","overall":{"max":65.31899895038302,"mean":39.60492019451364,"min":25.71921399965224},"per_game_match_totals_all":{"GB2-01":{"draws":26,"losses":47,"wins":45},"GB2-02":{"draws":56,"losses":4,"wins":4},"GB2-03":{"draws":28,"losses":8,"wins":10},"GB2-04":{"draws":22,"losses":19,"wins":17},"GB2-05":{"draws":0,"losses":87,"wins":55},"GB2-06":{"draws":2,"losses":63,"wins":59},"GB2-07":{"draws":0,"losses":62,"wins":68},"GB2-08":{"draws":58,"losses":6,"wins":2}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":2,"losses":18,"wins":22},"GB2-04":{"draws":22,"losses":19,"wins":17},"GB2-05":{"draws":0,"losses":39,"wins":29},"GB2-06":{"draws":2,"losses":31,"wins":31},"GB2-07":{"draws":0,"losses":41,"wins":35},"GB2-08":{"draws":58,"losses":6,"wins":2}},"none":{"GB2-01":{"draws":24,"losses":29,"wins":23},"GB2-02":{"draws":56,"losses":4,"wins":4},"GB2-03":{"draws":28,"losses":8,"wins":10},"GB2-05":{"draws":0,"losses":48,"wins":26},"GB2-06":{"draws":0,"losses":32,"wins":28},"GB2-07":{"draws":0,"losses":21,"wins":33}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1612.48039153947,"GB2-04":1518.91404152128,"GB2-05":1409.8327711353907,"GB2-06":1560.571039169908,"GB2-07":1482.226825234452,"GB2-08":1450.4049907718822},"none":{"GB2-01":1431.6560101881555,"GB2-02":1479.9188889322822,"GB2-03":1457.46717560364,"GB2-05":1340.6671312177457,"GB2-06":1452.7547853739904,"GB2-07":1636.5407743062012}},"per_game_tracks":{"medium":{"GB2-01":61.09711900072354,"GB2-04":35.7846857638282,"GB2-05":32.31299675673494,"GB2-06":57.85138882139616,"GB2-07":43.82956786001692,"GB2-08":25.71921399965224},"none":{"GB2-01":39.63405689209577,"GB2-02":29.659411891774138,"GB2-03":38.62343543749571,"GB2-05":26.62036218416104,"GB2-06":45.905146597643856,"GB2-07":65.31899895038302}},"provider_color":"#FF6900","provider_company":"Xiaomi","provider_key":"xiaomi","provider_text_color":"#fff7f1","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":39.798087992112826,"none":39.41175239691446},"reasoning_agg":{"medium":{"max":61.09711900072354,"mean":39.798087992112826,"min":25.71921399965224},"none":{"max":65.31899895038302,"mean":39.41175239691446,"min":26.62036218416104}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"score_diagnostics":{"ceiling_score":65.31899895038302,"reasoning_variance":0.3863355951983678},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":61.09711900072354,"expected_score":46.854019366176914,"reliability_score":59.53784028341942,"uncertainty_avg":40.46215971658058,"uncertainty_penalty":7.055931374064087},"none":{"ceiling_score":65.31899895038302,"expected_score":39.559187836650345,"reliability_score":80.23273259914913,"uncertainty_avg":19.767267400850873,"uncertainty_penalty":0.14743543973588658}}},{"codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":11,"cell_count":8,"cost_basis_counts":{"provider_reported":22},"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.00596013,"mean":0.0023956312500000004,"median":0.00186283,"min":0.00105702,"recorded_attempt_count":22,"run_count":14,"total":0.03542156},"none":{"admitted_cell_count":12,"cell_count":8,"cost_basis_counts":{"provider_reported":23},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.00407402,"mean":0.00223773125,"median":0.00220356,"min":0.00093502,"recorded_attempt_count":23,"run_count":14,"total":0.03065926}},"codegen_cost_usd":{"admitted_cell_count":23,"cell_count":16,"cost_basis_counts":{"provider_reported":45},"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.00596013,"mean":0.0023166812500000004,"median":0.00193686,"min":0.00093502,"recorded_attempt_count":45,"run_count":28,"total":0.06608082},"codegen_latency_ms":{"attempt_count":45,"max_ms":490920,"mean_ms":93765.89285714286,"min_ms":17974,"run_count":28},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":22,"max_ms":490920,"mean_ms":102055.21428571428,"min_ms":17974,"run_count":14},"none":{"attempt_count":23,"max_ms":199208,"mean_ms":85476.57142857143,"min_ms":34688,"run_count":14}},"codegen_output_tokens":{"attempt_count":45,"output_max":42038,"output_mean":6248.107142857143,"output_min":1564,"run_count":28},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":22,"output_max":42038,"output_mean":7478.214285714285,"output_min":1564,"run_count":14},"none":{"attempt_count":23,"output_max":11735,"output_mean":5018.0,"output_min":1646,"run_count":14}},"display_name":"Laguna S 2.1","economics":{"medium":33.38244172951511,"none":41.37058141762966},"first_seen_at":null,"generation_metadata":{"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"other","provider_model":"poolside/laguna-s-2.1","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":11,"evaluated_cells":14,"failed_game_aliases":["GB2-01","GB2-07"],"first_pass_admitted":7,"first_pass_rate":0.5,"infra_excluded_game_aliases":["GB2-04","GB2-06"],"infra_failures_excluded":2,"model_code_failure_rate":0.21428571428571427,"model_code_failures":3,"repaired_admitted":4,"repaired_rate":0.2857142857142857},"baseline":{"admitted_plugins":12,"evaluated_cells":14,"failed_game_aliases":["GB2-02","GB2-04"],"first_pass_admitted":6,"first_pass_rate":0.42857142857142855,"infra_excluded_game_aliases":["GB2-04","GB2-06"],"infra_failures_excluded":2,"model_code_failure_rate":0.14285714285714285,"model_code_failures":2,"repaired_admitted":6,"repaired_rate":0.42857142857142855}},"id":"poolside/laguna-s-2.1","is_recent_addition":false,"last_measured_at":"2026-07-27T11:54:26Z","match_totals_all":{"draws":472,"losses":405,"wins":347},"match_totals_tracks":{"medium":{"draws":223,"losses":140,"wins":93},"none":{"draws":249,"losses":265,"wins":254}},"model_slug":"poolside-laguna-s-2-1","overall":{"max":58.36812405939523,"mean":37.787885842626956,"min":23.723344738770017},"per_game_match_totals_all":{"GB2-01":{"draws":36,"losses":70,"wins":68},"GB2-02":{"draws":139,"losses":3,"wins":2},"GB2-03":{"draws":80,"losses":65,"wins":49},"GB2-04":{"draws":28,"losses":11,"wins":3},"GB2-05":{"draws":0,"losses":100,"wins":114},"GB2-06":{"draws":4,"losses":58,"wins":40},"GB2-07":{"draws":0,"losses":67,"wins":67},"GB2-08":{"draws":185,"losses":31,"wins":4}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":7,"losses":17,"wins":16},"GB2-02":{"draws":79,"losses":1,"wins":0},"GB2-03":{"draws":35,"losses":34,"wins":23},"GB2-04":{"draws":28,"losses":11,"wins":3},"GB2-05":{"draws":0,"losses":44,"wins":38},"GB2-06":{"draws":2,"losses":25,"wins":13},"GB2-08":{"draws":72,"losses":8,"wins":0}},"none":{"GB2-01":{"draws":29,"losses":53,"wins":52},"GB2-02":{"draws":60,"losses":2,"wins":2},"GB2-03":{"draws":45,"losses":31,"wins":26},"GB2-05":{"draws":0,"losses":56,"wins":76},"GB2-06":{"draws":2,"losses":33,"wins":27},"GB2-07":{"draws":0,"losses":67,"wins":67},"GB2-08":{"draws":113,"losses":23,"wins":4}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1527.987432545009,"GB2-02":1487.3145592583064,"GB2-03":1467.727157847934,"GB2-04":1431.6560449045471,"GB2-05":1459.640319348581,"GB2-06":1337.3836752186996,"GB2-08":1448.2281414127099},"none":{"GB2-01":1578.9605026224492,"GB2-02":1477.653649416274,"GB2-03":1475.2414972738902,"GB2-05":1547.7029292841976,"GB2-06":1345.003199893997,"GB2-07":1541.7067569374103,"GB2-08":1416.3710347575352}},"per_game_tracks":{"medium":{"GB2-01":49.94278083109678,"GB2-02":28.354767224454108,"GB2-03":40.298818357212,"GB2-04":20.80501417240327,"GB2-05":38.9743540171584,"GB2-06":28.966296840321345,"GB2-08":26.335060663959837},"none":{"GB2-01":58.36812405939523,"GB2-02":29.11813628556075,"GB2-03":42.117108402114056,"GB2-05":51.0280823912595,"GB2-06":31.60074877484011,"GB2-07":53.638525271468005,"GB2-08":23.723344738770017}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":31.53123901147382,"none":44.04453267378009},"reasoning_agg":{"medium":{"max":40.298818357212,"mean":31.53123901147382,"min":26.335060663959837},"none":{"max":58.36812405939523,"mean":44.04453267378009,"min":23.723344738770017}},"reasoning_labels":{"highest":"Setting not tested","medium":"Enabled","none":"None"},"score_diagnostics":{"ceiling_score":58.36812405939523,"reasoning_variance":12.513293662306271},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":40.298818357212,"expected_score":21.01635053953813,"reliability_score":66.72878950597988,"uncertainty_avg":33.27121049402013,"uncertainty_penalty":-10.514888471935688},"none":{"ceiling_score":58.36812405939523,"expected_score":38.95642901414162,"reliability_score":81.4527903190254,"uncertainty_avg":18.5472096809746,"uncertainty_penalty":-5.08810365963847}}},{"display_name":"GPT 4.1","economics":{"none":37.36024586658149},"first_seen_at":null,"generation_metadata":{"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-4.1","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openai","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{},"id":"gpt-4.1","is_recent_addition":false,"last_measured_at":"2026-07-27T11:48:31Z","match_totals_all":{"draws":100,"losses":128,"wins":104},"match_totals_tracks":{"none":{"draws":100,"losses":128,"wins":104}},"model_slug":"gpt-4-1","overall":{"max":56.67090350467359,"mean":37.36024586658148,"min":22.47989431367969},"per_game_match_totals_all":{"GB2-01":{"draws":1,"losses":22,"wins":21},"GB2-02":{"draws":31,"losses":10,"wins":3},"GB2-03":{"draws":10,"losses":10,"wins":10},"GB2-04":{"draws":23,"losses":9,"wins":2},"GB2-05":{"draws":0,"losses":28,"wins":18},"GB2-06":{"draws":8,"losses":16,"wins":18},"GB2-07":{"draws":0,"losses":19,"wins":25},"GB2-08":{"draws":27,"losses":14,"wins":7}},"per_game_match_totals_tracks":{"none":{"GB2-01":{"draws":1,"losses":22,"wins":21},"GB2-02":{"draws":31,"losses":10,"wins":3},"GB2-03":{"draws":10,"losses":10,"wins":10},"GB2-04":{"draws":23,"losses":9,"wins":2},"GB2-05":{"draws":0,"losses":28,"wins":18},"GB2-06":{"draws":8,"losses":16,"wins":18},"GB2-07":{"draws":0,"losses":19,"wins":25},"GB2-08":{"draws":27,"losses":14,"wins":7}}},"per_game_raw_elo_tracks":{"none":{"GB2-01":1576.9979684590764,"GB2-02":1461.1826663180202,"GB2-03":1527.2252132901654,"GB2-04":1458.5374385455698,"GB2-05":1343.9306693331305,"GB2-06":1498.497941533217,"GB2-07":1507.216526715812,"GB2-08":1418.016037894468}},"per_game_tracks":{"none":{"GB2-01":56.67090350467359,"GB2-02":22.789449128010855,"GB2-03":48.1455251873211,"GB2-04":24.842595418716364,"GB2-05":25.5579502972611,"GB2-06":50.71534315686365,"GB2-07":47.68030592612551,"GB2-08":22.47989431367969}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"none":37.36024586658148},"reasoning_agg":{"none":{"max":56.67090350467359,"mean":37.36024586658148,"min":22.47989431367969}},"reasoning_labels":{"highest":"Setting not tested","medium":"Setting not tested","none":"None"},"score_diagnostics":{"ceiling_score":56.67090350467359},"score_diagnostics_by_reasoning":{"none":{"ceiling_score":56.67090350467359,"expected_score":37.52636182931014,"reliability_score":66.43309667749512,"uncertainty_avg":33.56690332250489,"uncertainty_penalty":0.1661159627286608}}},{"codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":16,"cell_count":8,"cost_basis_counts":{"provider_reported":34},"evidence_basis":"Provider-reported","max":0.04815395,"mean":0.0408814375,"median":0.040641,"min":0.0341807,"recorded_attempt_count":34,"run_count":16,"total":0.654103},"medium":{"admitted_cell_count":16,"cell_count":8,"cost_basis_counts":{"provider_reported":32},"evidence_basis":"Provider-reported","max":0.03261155,"mean":0.02559155625,"median":0.02516155,"min":0.017927,"recorded_attempt_count":32,"run_count":16,"total":0.4094649},"none":{"admitted_cell_count":15,"cell_count":8,"cost_basis_counts":{"provider_reported":23},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.0148808,"mean":0.0114004875,"median":0.01124825,"min":0.00845595,"recorded_attempt_count":23,"run_count":16,"total":0.1824078}},"codegen_cost_usd":{"admitted_cell_count":47,"cell_count":24,"cost_basis_counts":{"provider_reported":89},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.04815395,"mean":0.025957827083333333,"median":0.02516155,"min":0.00845595,"recorded_attempt_count":89,"run_count":48,"total":1.2459757000000002},"codegen_latency_ms":{"attempt_count":89,"max_ms":61871,"mean_ms":33706.5625,"min_ms":13028,"run_count":48},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":34,"max_ms":61871,"mean_ms":50306.25,"min_ms":38302,"run_count":16},"medium":{"attempt_count":32,"max_ms":47168,"mean_ms":32849.5625,"min_ms":19840,"run_count":16},"none":{"attempt_count":23,"max_ms":28160,"mean_ms":17963.875,"min_ms":13028,"run_count":16}},"codegen_output_tokens":{"attempt_count":89,"output_max":18224,"output_mean":8477.208333333334,"output_min":1476,"run_count":48},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":34,"output_max":18224,"output_mean":14154.25,"output_min":11410,"run_count":16},"medium":{"attempt_count":32,"output_max":11113,"output_mean":8141.625,"output_min":4066,"run_count":16},"none":{"attempt_count":23,"output_max":4635,"output_mean":3135.75,"output_min":1476,"run_count":16}},"display_name":"Gemini 3.5 Flash Lite","economics":{"all":37.80790412369296,"highest":37.08427156622473,"medium":34.578316108190634,"none":41.7611246966635},"first_seen_at":null,"generation_metadata":{"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"google","provider_model":"google/gemini-3.5-flash-lite","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":16,"evaluated_cells":16,"first_pass_admitted":1,"first_pass_rate":0.0625,"model_code_failure_rate":0.0,"model_code_failures":0,"repaired_admitted":15,"repaired_rate":0.9375},"baseline":{"admitted_plugins":15,"evaluated_cells":16,"failed_game_aliases":["GB2-03"],"first_pass_admitted":9,"first_pass_rate":0.5625,"model_code_failure_rate":0.0625,"model_code_failures":1,"repaired_admitted":6,"repaired_rate":0.375},"intensive":{"admitted_plugins":16,"evaluated_cells":16,"model_code_failure_rate":0.0,"model_code_failures":0,"repaired_admitted":16,"repaired_rate":1.0}},"id":"google/gemini-3.5-flash-lite","is_recent_addition":false,"last_measured_at":"2026-07-27T11:23:13Z","match_totals_all":{"draws":804,"losses":763,"wins":632},"match_totals_tracks":{"highest":{"draws":232,"losses":230,"wins":188},"medium":{"draws":344,"losses":331,"wins":255},"none":{"draws":228,"losses":202,"wins":189}},"model_slug":"google-gemini-3-5-flash-lite","overall":{"max":66.08096329718745,"mean":36.955267515931276,"min":13.059186845663167},"per_game":{"GB2-01":44.50093428611456,"GB2-02":28.8476633604157,"GB2-03":48.635693497339204,"GB2-04":25.31872041058993,"GB2-05":25.25796091549614,"GB2-06":53.91719217050105,"GB2-07":44.886064479879934,"GB2-08":25.309943409461283},"per_game_all":{"GB2-01":46.929524991906334,"GB2-02":28.878391530667443,"GB2-03":51.20867886256988,"GB2-04":33.146654436984306,"GB2-05":22.68559484907917,"GB2-06":52.62459862409718,"GB2-07":42.74887706020892,"GB2-08":24.240912634030384},"per_game_match_totals_all":{"GB2-01":{"draws":68,"losses":121,"wins":101},"GB2-02":{"draws":269,"losses":16,"wins":9},"GB2-03":{"draws":65,"losses":75,"wins":88},"GB2-04":{"draws":209,"losses":45,"wins":33},"GB2-05":{"draws":0,"losses":184,"wins":108},"GB2-06":{"draws":10,"losses":132,"wins":142},"GB2-07":{"draws":0,"losses":149,"wins":145},"GB2-08":{"draws":183,"losses":41,"wins":6}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":17,"losses":31,"wins":34},"GB2-02":{"draws":73,"losses":8,"wins":5},"GB2-03":{"draws":17,"losses":28,"wins":35},"GB2-04":{"draws":54,"losses":20,"wins":6},"GB2-05":{"draws":0,"losses":52,"wins":28},"GB2-06":{"draws":6,"losses":33,"wins":43},"GB2-07":{"draws":0,"losses":45,"wins":35},"GB2-08":{"draws":65,"losses":13,"wins":2}},"medium":{"GB2-01":{"draws":31,"losses":55,"wins":40},"GB2-02":{"draws":120,"losses":4,"wins":4},"GB2-03":{"draws":38,"losses":32,"wins":32},"GB2-04":{"draws":98,"losses":15,"wins":11},"GB2-05":{"draws":0,"losses":67,"wins":65},"GB2-06":{"draws":2,"losses":69,"wins":51},"GB2-07":{"draws":0,"losses":77,"wins":49},"GB2-08":{"draws":55,"losses":12,"wins":3}},"none":{"GB2-01":{"draws":20,"losses":35,"wins":27},"GB2-02":{"draws":76,"losses":4,"wins":0},"GB2-03":{"draws":10,"losses":15,"wins":21},"GB2-04":{"draws":57,"losses":10,"wins":16},"GB2-05":{"draws":0,"losses":65,"wins":15},"GB2-06":{"draws":2,"losses":30,"wins":48},"GB2-07":{"draws":0,"losses":27,"wins":61},"GB2-08":{"draws":63,"losses":16,"wins":1}}},"per_game_raw_elo_all":{"GB2-01":1500.132429246176,"GB2-02":1484.533473048512,"GB2-03":1532.246349116388,"GB2-04":1490.6877495852277,"GB2-05":1319.478559038085,"GB2-06":1510.1074215788285,"GB2-07":1467.266798925396,"GB2-08":1429.7108090836289},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1485.3137654013412,"GB2-02":1487.3155765144922,"GB2-03":1520.7487899584455,"GB2-04":1455.7847295731035,"GB2-05":1345.5426876668148,"GB2-06":1523.1683060416635,"GB2-07":1488.6688151212497,"GB2-08":1441.610914575508},"medium":{"GB2-01":1503.1584684942027,"GB2-02":1486.2711131042715,"GB2-03":1520.5623366481877,"GB2-04":1489.3127842819954,"GB2-05":1369.4775729004741,"GB2-06":1409.7666921541868,"GB2-07":1264.8881004574012,"GB2-08":1429.1142665897733},"none":{"GB2-01":1511.9250538429842,"GB2-02":1480.0137295267718,"GB2-03":1555.427920742531,"GB2-04":1526.9657349005845,"GB2-05":1243.4154165469658,"GB2-06":1597.3872665406357,"GB2-07":1648.2434811975372,"GB2-08":1418.4072460856055}},"per_game_tracks":{"highest":{"GB2-01":44.50093428611456,"GB2-02":28.8476633604157,"GB2-03":48.635693497339204,"GB2-04":25.31872041058993,"GB2-05":25.25796091549614,"GB2-06":53.91719217050105,"GB2-07":44.886064479879934,"GB2-08":25.309943409461283},"medium":{"GB2-01":48.3336953705786,"GB2-02":31.177266390249358,"GB2-03":49.78746785854181,"GB2-04":34.401973606580675,"GB2-05":29.739636786078208,"GB2-06":40.2094045434509,"GB2-07":17.279603403559378,"GB2-08":25.697480906486177},"none":{"GB2-01":47.95394531902585,"GB2-02":26.61024484133727,"GB2-03":55.20287523182865,"GB2-04":39.71926929378232,"GB2-05":13.059186845663167,"GB2-06":63.74719915833959,"GB2-07":66.08096329718745,"GB2-08":21.7153135861437}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#f5f9ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":37.08427156622473,"medium":34.578316108190634,"none":39.203214873378464},"reasoning_agg":{"highest":{"max":53.91719217050105,"mean":37.08427156622473,"min":25.25796091549614},"medium":{"max":49.78746785854181,"mean":34.578316108190634,"min":17.279603403559378},"none":{"max":66.08096329718745,"mean":39.203214873378464,"min":13.059186845663167}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Minimal"},"score_diagnostics":{"ceiling_score":66.08096329718745,"expected_score":31.872487717543148,"reasoning_variance":4.6248987651878295,"reliability_score":71.3517123533759,"uncertainty_avg":28.648287646624098,"uncertainty_penalty":-5.0827797983881275},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":53.91719217050105,"expected_score":21.6808004135097,"reliability_score":66.21496760265678,"uncertainty_avg":33.785032397343215,"uncertainty_penalty":-15.403471152715028},"medium":{"ceiling_score":49.78746785854181,"expected_score":25.92478364863436,"reliability_score":80.82845806266762,"uncertainty_avg":19.171541937332382,"uncertainty_penalty":-8.653532459556274},"none":{"ceiling_score":66.08096329718745,"expected_score":48.011879090485394,"reliability_score":67.01171139480331,"uncertainty_avg":32.988288605196686,"uncertainty_penalty":8.80866421710693}}},{"codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":17},"evidence_basis":"Provider-reported","max":0.07439860000000001,"mean":0.060660574999999994,"median":0.0565846,"min":0.0485456,"recorded_attempt_count":17,"run_count":8,"total":0.4852845999999999}},"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":17},"evidence_basis":"Provider-reported","max":0.07439860000000001,"mean":0.060660574999999994,"median":0.0565846,"min":0.0485456,"recorded_attempt_count":17,"run_count":8,"total":0.4852845999999999},"codegen_latency_ms":{"attempt_count":17,"max_ms":357442,"mean_ms":205939.25,"min_ms":129630,"run_count":8},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":17,"max_ms":357442,"mean_ms":205939.25,"min_ms":129630,"run_count":8}},"codegen_output_tokens":{"attempt_count":17,"output_max":29845,"output_mean":22432.25,"output_min":16334,"run_count":8},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":17,"output_max":29845,"output_mean":22432.25,"output_min":16334,"run_count":8}},"display_name":"Grok Build 0.1","economics":{"medium":36.60929744604539},"first_seen_at":null,"generation_metadata":{"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"x-ai","provider_model":"x-ai/grok-build-0.1","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"model_code_failure_rate":0.0,"model_code_failures":0,"repaired_admitted":8,"repaired_rate":1.0}},"id":"x-ai/grok-build-0.1","is_recent_addition":false,"last_measured_at":"2026-07-27T11:30:10Z","match_totals_all":{"draws":178,"losses":161,"wins":151},"match_totals_tracks":{"medium":{"draws":178,"losses":161,"wins":151}},"model_slug":"x-ai-grok-build-0-1","overall":{"max":53.83120272886001,"mean":36.60929744604539,"min":26.493587534338452},"per_game_match_totals_all":{"GB2-01":{"draws":15,"losses":24,"wins":33},"GB2-02":{"draws":52,"losses":2,"wins":2},"GB2-03":{"draws":22,"losses":15,"wins":13},"GB2-04":{"draws":39,"losses":5,"wins":4},"GB2-05":{"draws":0,"losses":28,"wins":38},"GB2-06":{"draws":0,"losses":39,"wins":31},"GB2-07":{"draws":0,"losses":41,"wins":27},"GB2-08":{"draws":50,"losses":7,"wins":3}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":15,"losses":24,"wins":33},"GB2-02":{"draws":52,"losses":2,"wins":2},"GB2-03":{"draws":22,"losses":15,"wins":13},"GB2-04":{"draws":39,"losses":5,"wins":4},"GB2-05":{"draws":0,"losses":28,"wins":38},"GB2-06":{"draws":0,"losses":39,"wins":31},"GB2-07":{"draws":0,"losses":41,"wins":27},"GB2-08":{"draws":50,"losses":7,"wins":3}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1527.5889880044401,"GB2-02":1496.2343584526793,"GB2-03":1484.771748750963,"GB2-04":1487.6598211813339,"GB2-05":1591.4510347559626,"GB2-06":1430.7493983829117,"GB2-07":1355.5092833564145,"GB2-08":1458.736541116889}},"per_game_tracks":{"medium":{"GB2-01":49.426447239287874,"GB2-02":27.632718734896454,"GB2-03":39.653453444576584,"GB2-04":28.1378078235891,"GB2-05":53.83120272886001,"GB2-06":40.89186947333852,"GB2-07":26.80729258947612,"GB2-08":26.493587534338452}},"provider_color":"#9CA3AF","provider_company":"xAI","provider_key":"x-ai","provider_text_color":"#0b1120","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":36.60929744604539},"reasoning_agg":{"medium":{"max":53.83120272886001,"mean":36.60929744604539,"min":26.493587534338452}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Setting not tested"},"score_diagnostics":{"ceiling_score":53.83120272886001},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":53.83120272886001,"expected_score":34.024852568323,"reliability_score":53.793828960072624,"uncertainty_avg":46.206171039927376,"uncertainty_penalty":-2.5844448777223903}}},{"codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":12,"cell_count":8,"cost_basis_counts":{"provider_reported":32},"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.04649778,"mean":0.039593841,"median":0.039509778,"min":0.030762138,"recorded_attempt_count":32,"run_count":16,"total":0.6335014560000001},"none":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"provider_reported":25},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.014209038,"mean":0.0093957345,"median":0.009312405,"min":0.004429524000000001,"recorded_attempt_count":25,"run_count":16,"total":0.150331752}},"codegen_cost_usd":{"admitted_cell_count":26,"cell_count":16,"cost_basis_counts":{"provider_reported":57},"evidence_basis":"Provider-reported","failed_cell_count":6,"max":0.04649778,"mean":0.024494787749999997,"median":0.022485588,"min":0.004429524000000001,"recorded_attempt_count":57,"run_count":32,"total":0.7838332079999999},"codegen_latency_ms":{"attempt_count":58,"max_ms":848935,"mean_ms":404316.75,"min_ms":47979,"run_count":32},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":33,"max_ms":848935,"mean_ms":690334.25,"min_ms":443841,"run_count":16},"none":{"attempt_count":25,"max_ms":266268,"mean_ms":118299.25,"min_ms":47979,"run_count":16}},"codegen_output_tokens":{"attempt_count":57,"output_max":40000,"output_mean":18334.0625,"output_min":2150,"run_count":32},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":32,"output_max":40000,"output_mean":31078.25,"output_min":16796,"run_count":16},"none":{"attempt_count":25,"output_max":13510,"output_mean":5589.875,"output_min":2150,"run_count":16}},"display_name":"LongCat 2.0","economics":{"medium":35.32612709802781,"none":37.3890207574689},"first_seen_at":null,"generation_metadata":{"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"other","provider_model":"meituan/longcat-2.0","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":12,"evaluated_cells":16,"failed_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-07"],"model_code_failure_rate":0.25,"model_code_failures":4,"repaired_admitted":12,"repaired_rate":0.75},"baseline":{"admitted_plugins":14,"evaluated_cells":16,"failed_game_aliases":["GB2-02","GB2-04"],"first_pass_admitted":8,"first_pass_rate":0.5,"model_code_failure_rate":0.125,"model_code_failures":2,"repaired_admitted":6,"repaired_rate":0.375}},"id":"meituan/longcat-2.0","is_recent_addition":false,"last_measured_at":"2026-07-27T11:54:00Z","match_totals_all":{"draws":433,"losses":536,"wins":409},"match_totals_tracks":{"medium":{"draws":126,"losses":198,"wins":162},"none":{"draws":307,"losses":338,"wins":247}},"model_slug":"meituan-longcat-2-0","overall":{"max":52.38713921457689,"mean":36.07115177214229,"min":19.697931844478177},"per_game_match_totals_all":{"GB2-01":{"draws":49,"losses":71,"wins":52},"GB2-02":{"draws":101,"losses":2,"wins":1},"GB2-03":{"draws":59,"losses":45,"wins":36},"GB2-04":{"draws":84,"losses":32,"wins":20},"GB2-05":{"draws":0,"losses":142,"wins":78},"GB2-06":{"draws":16,"losses":106,"wins":90},"GB2-07":{"draws":0,"losses":98,"wins":72},"GB2-08":{"draws":124,"losses":40,"wins":60}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":8,"losses":23,"wins":9},"GB2-02":{"draws":38,"losses":1,"wins":1},"GB2-03":{"draws":13,"losses":13,"wins":14},"GB2-04":{"draws":50,"losses":21,"wins":5},"GB2-05":{"draws":0,"losses":44,"wins":36},"GB2-06":{"draws":4,"losses":41,"wins":37},"GB2-07":{"draws":0,"losses":30,"wins":10},"GB2-08":{"draws":13,"losses":25,"wins":50}},"none":{"GB2-01":{"draws":41,"losses":48,"wins":43},"GB2-02":{"draws":63,"losses":1,"wins":0},"GB2-03":{"draws":46,"losses":32,"wins":22},"GB2-04":{"draws":34,"losses":11,"wins":15},"GB2-05":{"draws":0,"losses":98,"wins":42},"GB2-06":{"draws":12,"losses":65,"wins":53},"GB2-07":{"draws":0,"losses":68,"wins":62},"GB2-08":{"draws":111,"losses":15,"wins":10}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1351.2546228678034,"GB2-02":1489.1522376403848,"GB2-03":1487.6875843006812,"GB2-04":1429.2136617086594,"GB2-05":1443.5801068097953,"GB2-06":1495.4573766623844,"GB2-07":1340.532812293546,"GB2-08":1606.890781954458},"none":{"GB2-01":1480.535597443261,"GB2-02":1480.524029567731,"GB2-03":1437.3954080780577,"GB2-04":1569.103382231883,"GB2-05":1301.7070258578515,"GB2-06":1499.2368104393881,"GB2-07":1426.8494348714175,"GB2-08":1427.1095998713513}},"per_game_tracks":{"medium":{"GB2-01":27.010394711158984,"GB2-02":28.79387773495653,"GB2-03":43.04022494558611,"GB2-04":19.697931844478177,"GB2-05":36.968215320622434,"GB2-06":50.21027749681558,"GB2-07":25.53346036165865,"GB2-08":51.354634368946044},"none":{"GB2-01":45.54198211998018,"GB2-02":29.80400934470667,"GB2-03":35.61605485008677,"GB2-04":50.13435586825387,"GB2-05":21.811735212142757,"GB2-06":52.38713921457689,"GB2-07":38.538135675658424,"GB2-08":25.27875377434565}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":36.812648098747886,"none":35.32965544553668},"reasoning_agg":{"medium":{"max":51.354634368946044,"mean":36.812648098747886,"min":19.697931844478177},"none":{"max":52.38713921457689,"mean":35.32965544553668,"min":21.811735212142757}},"reasoning_labels":{"highest":"Setting not tested","medium":"Enabled","none":"None"},"score_diagnostics":{"ceiling_score":52.38713921457689,"reasoning_variance":1.4829926532112054},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":51.354634368946044,"expected_score":25.97858427777227,"reliability_score":65.9648407093373,"uncertainty_avg":34.03515929066271,"uncertainty_penalty":-10.834063820975615},"none":{"ceiling_score":52.38713921457689,"expected_score":39.18164439426249,"reliability_score":81.25905538475668,"uncertainty_avg":18.74094461524332,"uncertainty_penalty":3.851988948725811}}},{"codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":18},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.226689264,"mean":0.16037539425,"median":0.140728509,"min":0.10689655,"recorded_attempt_count":18,"run_count":8,"total":1.283003154}},"codegen_cost_usd":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":18},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.226689264,"mean":0.16037539425,"median":0.140728509,"min":0.10689655,"recorded_attempt_count":18,"run_count":8,"total":1.283003154},"codegen_latency_ms":{"attempt_count":18,"max_ms":1108247,"mean_ms":850298.125,"min_ms":548194,"run_count":8},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":18,"max_ms":1108247,"mean_ms":850298.125,"min_ms":548194,"run_count":8}},"codegen_output_tokens":{"attempt_count":18,"output_max":56063,"output_mean":38535.375,"output_min":23283,"run_count":8},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":18,"output_max":56063,"output_mean":38535.375,"output_min":23283,"run_count":8}},"display_name":"Kimi K2.7 Code","economics":{"medium":37.96744668867628},"first_seen_at":null,"generation_metadata":{"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"moonshotai","provider_model":"moonshotai/kimi-k2.7-code","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":6,"evaluated_cells":8,"failed_game_aliases":["GB2-03","GB2-06"],"model_code_failure_rate":0.25,"model_code_failures":2,"repaired_admitted":6,"repaired_rate":0.75}},"id":"moonshotai/kimi-k2.7-code","is_recent_addition":false,"last_measured_at":"2026-07-27T11:03:48Z","match_totals_all":{"draws":95,"losses":139,"wins":128},"match_totals_tracks":{"medium":{"draws":95,"losses":139,"wins":128}},"model_slug":"moonshotai-kimi-k2-7-code","overall":{"max":47.67871891237462,"mean":35.33269037618208,"min":24.01242101325399},"per_game_match_totals_all":{"GB2-01":{"draws":2,"losses":29,"wins":31},"GB2-02":{"draws":50,"losses":8,"wins":4},"GB2-04":{"draws":38,"losses":8,"wins":4},"GB2-05":{"draws":0,"losses":29,"wins":29},"GB2-07":{"draws":0,"losses":35,"wins":35},"GB2-08":{"draws":5,"losses":30,"wins":25}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":2,"losses":29,"wins":31},"GB2-02":{"draws":50,"losses":8,"wins":4},"GB2-04":{"draws":38,"losses":8,"wins":4},"GB2-05":{"draws":0,"losses":29,"wins":29},"GB2-07":{"draws":0,"losses":35,"wins":35},"GB2-08":{"draws":5,"losses":30,"wins":25}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1495.4492714651392,"GB2-02":1477.4089183486803,"GB2-04":1476.1836514200374,"GB2-05":1544.0837274481667,"GB2-07":1498.1567772201045,"GB2-08":1544.324469670316}},"per_game_tracks":{"medium":{"GB2-01":44.64799882230341,"GB2-02":24.01242101325399,"GB2-04":26.12081427726525,"GB2-05":47.67871891237462,"GB2-07":45.57473728904729,"GB2-08":39.76998981781314}},"provider_color":"#7C3AED","provider_company":"Moonshot","provider_key":"moonshotai","provider_text_color":"#faf5ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":35.33269037618208},"reasoning_agg":{"medium":{"max":47.67871891237462,"mean":35.33269037618208,"min":24.01242101325399}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Setting not tested"},"score_diagnostics":{"ceiling_score":47.67871891237462},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":47.67871891237462,"expected_score":38.86946061873976,"reliability_score":53.71900599211435,"uncertainty_avg":46.28099400788565,"uncertainty_penalty":3.5367702425576795}}},{"codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":15,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":25},"evidence_basis":"Standard list-price estimate","failed_cell_count":2,"max":0.38568888333333334,"mean":0.29249454166666666,"median":0.2834616125,"min":0.2238526,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":25},"run_count":17,"token_priced_attempt_count":25,"total":5.07700365},"medium":{"admitted_cell_count":25,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":49},"evidence_basis":"Standard list-price estimate","failed_cell_count":7,"max":0.036200562500000005,"mean":0.024352715625,"median":0.02520601875,"min":0.0165820625,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":49},"run_count":32,"token_priced_attempt_count":49,"total":0.7792869},"none":{"admitted_cell_count":25,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":56},"evidence_basis":"Standard list-price estimate","failed_cell_count":7,"max":0.013223525,"mean":0.0089983359375,"median":0.00845865,"min":0.0058062875,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":56},"run_count":32,"token_priced_attempt_count":56,"total":0.28794675000000003}},"codegen_cost_usd":{"admitted_cell_count":65,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":130},"evidence_basis":"Standard list-price estimate","failed_cell_count":16,"max":0.38568888333333334,"mean":0.10861519774305556,"median":0.02520601875,"min":0.0058062875,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":130},"run_count":81,"token_priced_attempt_count":130,"total":6.1442373},"codegen_latency_ms":{"attempt_count":130,"max_ms":4769864,"mean_ms":387335.3209876543,"min_ms":20868,"run_count":81},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":25,"max_ms":4769864,"mean_ms":1538065.3529411764,"min_ms":584445,"run_count":17},"medium":{"attempt_count":49,"max_ms":1064325,"mean_ms":119877.59375,"min_ms":36200,"run_count":32},"none":{"attempt_count":56,"max_ms":101610,"mean_ms":43467.71875,"min_ms":20868,"run_count":32}},"codegen_output_tokens":{"attempt_count":130,"output_max":316330,"output_mean":57506.49382716049,"output_min":2711,"run_count":81},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":25,"output_max":316330,"output_mean":230905.0,"output_min":131376,"run_count":17},"medium":{"attempt_count":49,"output_max":27931,"output_mean":17655.9375,"output_min":7818,"run_count":32},"none":{"attempt_count":56,"output_max":10894,"output_mean":5239.09375,"output_min":2711,"run_count":32}},"display_name":"GPT-5.4 Nano","economics":{"all":37.83950547362281,"highest":43.09094210307414,"medium":34.61949948982014,"none":35.80807482797414},"first_seen_at":null,"generation_metadata":{"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-5.4-nano","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openai","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":25,"evaluated_cells":32,"failed_game_aliases":["GB2-02","GB2-03","GB2-04","GB2-08"],"first_pass_admitted":13,"first_pass_rate":0.40625,"model_code_failure_rate":0.21875,"model_code_failures":7,"repaired_admitted":12,"repaired_rate":0.375},"baseline":{"admitted_plugins":25,"evaluated_cells":32,"failed_game_aliases":["GB2-03","GB2-04","GB2-05","GB2-06","GB2-07"],"first_pass_admitted":10,"first_pass_rate":0.3125,"model_code_failure_rate":0.21875,"model_code_failures":7,"repaired_admitted":15,"repaired_rate":0.46875},"intensive":{"admitted_plugins":15,"evaluated_cells":17,"failed_game_aliases":["GB2-02","GB2-03"],"first_pass_admitted":10,"first_pass_rate":0.5882352941176471,"infra_excluded_game_aliases":["GB2-01","GB2-03","GB2-04","GB2-05","GB2-06","GB2-07"],"infra_failures_excluded":9,"model_code_failure_rate":0.1176470588235294,"model_code_failures":2,"repaired_admitted":5,"repaired_rate":0.29411764705882354}},"id":"gpt-5.4-nano","is_recent_addition":false,"last_measured_at":"2026-07-27T11:59:44Z","match_totals_all":{"draws":1320,"losses":1541,"wins":1080},"match_totals_tracks":{"highest":{"draws":316,"losses":336,"wins":301},"medium":{"draws":411,"losses":669,"wins":404},"none":{"draws":593,"losses":536,"wins":375}},"model_slug":"gpt-5-4-nano","overall":{"max":54.484864054652334,"mean":34.34057217679145,"min":19.139574631625756},"per_game":{"GB2-01":26.6338275876808,"GB2-02":30.195055758003996,"GB2-03":33.451022699687655,"GB2-04":27.422092307108727,"GB2-05":59.64569065882853,"GB2-06":77.54832249268348,"GB2-07":47.26461648443617,"GB2-08":42.56690883616381},"per_game_all":{"GB2-01":27.42089040796257,"GB2-02":29.126609788784805,"GB2-03":34.12690837151781,"GB2-04":35.657771267750114,"GB2-05":41.19422584802658,"GB2-06":63.697645038112285,"GB2-07":33.85728722593547,"GB2-08":37.63470584089284},"per_game_match_totals_all":{"GB2-01":{"draws":165,"losses":319,"wins":122},"GB2-02":{"draws":460,"losses":39,"wins":12},"GB2-03":{"draws":98,"losses":91,"wins":59},"GB2-04":{"draws":205,"losses":84,"wins":79},"GB2-05":{"draws":0,"losses":335,"wins":248},"GB2-06":{"draws":24,"losses":213,"wins":239},"GB2-07":{"draws":0,"losses":322,"wins":165},"GB2-08":{"draws":368,"losses":138,"wins":156}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":38,"losses":64,"wins":16},"GB2-02":{"draws":116,"losses":14,"wins":6},"GB2-03":{"draws":13,"losses":23,"wins":12},"GB2-04":{"draws":41,"losses":43,"wins":38},"GB2-05":{"draws":0,"losses":58,"wins":75},"GB2-06":{"draws":5,"losses":19,"wins":32},"GB2-07":{"draws":0,"losses":71,"wins":57},"GB2-08":{"draws":103,"losses":44,"wins":65}},"medium":{"GB2-01":{"draws":51,"losses":138,"wins":39},"GB2-02":{"draws":149,"losses":11,"wins":3},"GB2-03":{"draws":24,"losses":15,"wins":9},"GB2-04":{"draws":77,"losses":21,"wins":30},"GB2-05":{"draws":0,"losses":141,"wins":113},"GB2-06":{"draws":17,"losses":120,"wins":105},"GB2-07":{"draws":0,"losses":175,"wins":58},"GB2-08":{"draws":93,"losses":48,"wins":47}},"none":{"GB2-01":{"draws":76,"losses":117,"wins":67},"GB2-02":{"draws":195,"losses":14,"wins":3},"GB2-03":{"draws":61,"losses":53,"wins":38},"GB2-04":{"draws":87,"losses":20,"wins":11},"GB2-05":{"draws":0,"losses":136,"wins":60},"GB2-06":{"draws":2,"losses":74,"wins":102},"GB2-07":{"draws":0,"losses":76,"wins":50},"GB2-08":{"draws":172,"losses":46,"wins":44}}},"per_game_raw_elo_all":{"GB2-01":1343.1530577765086,"GB2-02":1480.3541330899006,"GB2-03":1429.2834092485282,"GB2-04":1495.9978447753938,"GB2-05":1465.7632889587167,"GB2-06":1586.4222569302472,"GB2-07":1392.3639098351025,"GB2-08":1507.560398140886},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1337.52818990007,"GB2-02":1480.8383080708227,"GB2-03":1425.7024844756863,"GB2-04":1454.7985958238055,"GB2-05":1619.6763359283814,"GB2-06":1691.0689393099397,"GB2-07":1494.0376407858525,"GB2-08":1537.8079299083918},"medium":{"GB2-01":1280.700601387579,"GB2-02":1481.0444737034147,"GB2-03":1411.064865920198,"GB2-04":1545.9269827773976,"GB2-05":1435.585169745014,"GB2-06":1516.80550194545,"GB2-07":1304.2443438279372,"GB2-08":1511.3185496845663},"none":{"GB2-01":1411.2303820418765,"GB2-02":1479.1796174954648,"GB2-03":1451.0828773497008,"GB2-04":1487.2679557249785,"GB2-05":1342.0283612027545,"GB2-06":1551.3923295353513,"GB2-07":1378.8097448915178,"GB2-08":1473.5547148296998}},"per_game_tracks":{"highest":{"GB2-01":26.6338275876808,"GB2-02":30.195055758003996,"GB2-03":33.451022699687655,"GB2-04":27.422092307108727,"GB2-05":59.64569065882853,"GB2-06":77.54832249268348,"GB2-07":47.26461648443617,"GB2-08":42.56690883616381},"medium":{"GB2-01":19.139574631625756,"GB2-02":28.875429548217255,"GB2-03":30.973667967146064,"GB2-04":45.804624380131344,"GB2-05":37.5178295193274,"GB2-06":54.484864054652334,"GB2-07":22.14962114886749,"GB2-08":38.01038466859352},"none":{"GB2-01":36.489269004581146,"GB2-02":28.309344060133164,"GB2-03":37.956034447719695,"GB2-04":33.746597116010264,"GB2-05":26.419157365923827,"GB2-06":59.05974856700104,"GB2-07":32.157624044502754,"GB2-08":32.3268240179212}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":41.25558005932039,"medium":31.32861821186002,"none":30.437518259193915},"reasoning_agg":{"highest":{"max":42.56690883616381,"mean":41.25558005932039,"min":42.56690883616381},"medium":{"max":54.484864054652334,"mean":31.32861821186002,"min":19.139574631625756},"none":{"max":36.489269004581146,"mean":30.437518259193915,"min":28.309344060133164}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"score_diagnostics":{"ceiling_score":54.484864054652334,"expected_score":30.17500950181676,"reasoning_variance":10.818061800126472,"reliability_score":79.43920498224597,"uncertainty_avg":20.56079501775404,"uncertainty_penalty":-4.165562674974687},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":42.56690883616381,"expected_score":27.48803155024699,"reliability_score":80.21879107326333,"uncertainty_avg":19.781208926736667,"uncertainty_penalty":-13.767548509073396},"medium":{"ceiling_score":54.484864054652334,"expected_score":29.09887079261224,"reliability_score":78.62672285328094,"uncertainty_avg":21.37327714671907,"uncertainty_penalty":-2.229747419247783},"none":{"ceiling_score":36.489269004581146,"expected_score":33.93812616259106,"reliability_score":79.47210102019362,"uncertainty_avg":20.527898979806384,"uncertainty_penalty":3.500607903397146}}},{"codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":15,"cell_count":8,"cost_basis_counts":{"provider_reported":46},"evidence_basis":"Provider-reported","failed_cell_count":6,"max":0.02904086,"mean":0.020196066154166664,"median":0.0210709803,"min":0.0085050301,"recorded_attempt_count":46,"run_count":21,"total":0.426437947},"none":{"admitted_cell_count":17,"cell_count":8,"cost_basis_counts":{"provider_reported":35},"evidence_basis":"Provider-reported","failed_cell_count":7,"max":0.004834030033333333,"mean":0.0027724950333333333,"median":0.002243999216666667,"min":0.0016912200000000002,"recorded_attempt_count":35,"run_count":24,"total":0.0665398808}},"codegen_cost_usd":{"admitted_cell_count":32,"cell_count":16,"cost_basis_counts":{"provider_reported":81},"evidence_basis":"Provider-reported","failed_cell_count":13,"max":0.02904086,"mean":0.01148428059375,"median":0.006669530066666667,"min":0.0016912200000000002,"recorded_attempt_count":81,"run_count":45,"total":0.4929778278},"codegen_latency_ms":{"attempt_count":81,"max_ms":2511116,"mean_ms":633843.1555555556,"min_ms":19112,"run_count":45},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":46,"max_ms":2511116,"mean_ms":1185686.761904762,"min_ms":46510,"run_count":21},"none":{"attempt_count":35,"max_ms":1132276,"mean_ms":150980.0,"min_ms":19112,"run_count":24}},"codegen_output_tokens":{"attempt_count":79,"output_max":146589,"output_mean":36322.91111111111,"output_min":1540,"run_count":45},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":46,"output_max":146589,"output_mean":73252.28571428571,"output_min":6076,"run_count":21},"none":{"attempt_count":33,"output_max":23326,"output_mean":4009.7083333333335,"output_min":1540,"run_count":24}},"display_name":"MiMo-V2.5","economics":{"all":32.35680856490188,"highest":31.61899034274135,"medium":32.582209613542744,"none":37.984104557629735},"first_seen_at":null,"generation_metadata":{"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"xiaomi","provider_model":"xiaomi/mimo-v2.5","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":15,"evaluated_cells":21,"failed_game_aliases":["GB2-01","GB2-03","GB2-06","GB2-08"],"first_pass_admitted":1,"first_pass_rate":0.047619047619047616,"infra_excluded_game_aliases":["GB2-03","GB2-06","GB2-07"],"infra_failures_excluded":3,"model_code_failure_rate":0.2857142857142857,"model_code_failures":6,"repaired_admitted":14,"repaired_rate":0.6666666666666666},"baseline":{"admitted_plugins":17,"evaluated_cells":24,"failed_game_aliases":["GB2-02","GB2-03","GB2-04","GB2-07","GB2-08"],"first_pass_admitted":12,"first_pass_rate":0.5,"model_code_failure_rate":0.2916666666666667,"model_code_failures":7,"repaired_admitted":5,"repaired_rate":0.20833333333333337}},"id":"xiaomi/mimo-v2.5","is_recent_addition":false,"last_measured_at":"2026-07-27T11:54:00Z","match_totals_all":{"draws":822,"losses":728,"wins":582},"match_totals_tracks":{"highest":{"draws":135,"losses":43,"wins":24},"medium":{"draws":375,"losses":313,"wins":236},"none":{"draws":312,"losses":372,"wins":322}},"model_slug":"xiaomi-mimo-v2-5","overall":{"max":51.110878446006915,"mean":33.58432834211232,"min":21.605010778009973},"per_game":{"GB2-01":21.605010778009973,"GB2-02":27.082403158201195,"GB2-04":32.97295544313002,"GB2-06":51.110878446006915,"GB2-08":25.32370388835863},"per_game_all":{"GB2-01":36.462428213089225,"GB2-02":26.54153684210554,"GB2-04":31.432198969766844,"GB2-06":44.053985572598265,"GB2-08":23.293893226949553},"per_game_match_totals_all":{"GB2-01":{"draws":97,"losses":162,"wins":127},"GB2-02":{"draws":243,"losses":15,"wins":8},"GB2-03":{"draws":28,"losses":9,"wins":9},"GB2-04":{"draws":245,"losses":40,"wins":27},"GB2-05":{"draws":0,"losses":160,"wins":160},"GB2-06":{"draws":9,"losses":137,"wins":112},"GB2-07":{"draws":0,"losses":139,"wins":119},"GB2-08":{"draws":200,"losses":66,"wins":20}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":31,"losses":11,"wins":0},"GB2-02":{"draws":33,"losses":3,"wins":2},"GB2-04":{"draws":28,"losses":6,"wins":4},"GB2-06":{"draws":6,"losses":18,"wins":16},"GB2-08":{"draws":37,"losses":5,"wins":2}},"medium":{"GB2-01":{"draws":15,"losses":69,"wins":56},"GB2-02":{"draws":157,"losses":9,"wins":6},"GB2-04":{"draws":134,"losses":28,"wins":10},"GB2-05":{"draws":0,"losses":69,"wins":67},"GB2-06":{"draws":3,"losses":35,"wins":18},"GB2-07":{"draws":0,"losses":63,"wins":63},"GB2-08":{"draws":66,"losses":40,"wins":16}},"none":{"GB2-01":{"draws":51,"losses":82,"wins":71},"GB2-02":{"draws":53,"losses":3,"wins":0},"GB2-03":{"draws":28,"losses":9,"wins":9},"GB2-04":{"draws":83,"losses":6,"wins":13},"GB2-05":{"draws":0,"losses":91,"wins":93},"GB2-06":{"draws":0,"losses":84,"wins":78},"GB2-07":{"draws":0,"losses":76,"wins":56},"GB2-08":{"draws":97,"losses":21,"wins":2}}},"per_game_raw_elo_all":{"GB2-01":1420.3285001196016,"GB2-02":1480.7710151929357,"GB2-04":1488.3864345855488,"GB2-06":1451.331124284533,"GB2-08":1426.898889624932},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1308.1269234889603,"GB2-02":1483.571469812471,"GB2-04":1495.7904116780787,"GB2-06":1502.9248303375296,"GB2-08":1438.8587143860132},"medium":{"GB2-01":1457.4978861248828,"GB2-02":1490.1593860965586,"GB2-04":1469.7704001821894,"GB2-05":1463.883778294188,"GB2-06":1384.079848744715,"GB2-07":1463.9651854578856,"GB2-08":1432.644289501747},"none":{"GB2-01":1495.360690744961,"GB2-02":1468.5821896697769,"GB2-03":1525.5217643839485,"GB2-04":1499.5984918963782,"GB2-05":1455.8411759214753,"GB2-06":1466.9886937713543,"GB2-07":1402.083848243849,"GB2-08":1409.1936649870358}},"per_game_tracks":{"highest":{"GB2-01":21.605010778009973,"GB2-02":27.082403158201195,"GB2-04":32.97295544313002,"GB2-06":51.110878446006915,"GB2-08":25.32370388835863},"medium":{"GB2-01":40.22743264582813,"GB2-02":26.396318186763295,"GB2-04":25.89649759084934,"GB2-05":38.75915984031178,"GB2-06":33.615449335199195,"GB2-07":40.65095770356271,"GB2-08":22.529651992284748},"none":{"GB2-01":47.554841215429576,"GB2-02":26.14588918135212,"GB2-03":50.14138536541297,"GB2-04":35.42714387532118,"GB2-05":39.84236148945967,"GB2-06":47.43562893658869,"GB2-07":35.29726259726838,"GB2-08":22.028323800205285}},"provider_color":"#FF6900","provider_company":"Xiaomi","provider_key":"xiaomi","provider_text_color":"#fff7f1","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":31.61899034274135,"medium":27.902049817221116,"none":41.23194486637451},"reasoning_agg":{"highest":{"max":51.110878446006915,"mean":31.61899034274135,"min":21.605010778009973},"medium":{"max":38.75915984031178,"mean":27.902049817221116,"min":25.89649759084934},"none":{"max":47.554841215429576,"mean":41.23194486637451,"min":39.84236148945967}},"reasoning_labels":{"highest":"Highest","medium":"Reasoning enabled","none":"Reasoning disabled"},"score_diagnostics":{"ceiling_score":51.110878446006915,"expected_score":21.885605753686544,"reasoning_variance":13.329895049153397,"reliability_score":66.0009274182446,"uncertainty_avg":33.9990725817554,"uncertainty_penalty":-11.698722588425778},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":51.110878446006915,"expected_score":14.887181576344739,"reliability_score":65.9500161668629,"uncertainty_avg":34.0499838331371,"uncertainty_penalty":-16.73180876639661},"medium":{"ceiling_score":38.75915984031178,"expected_score":28.339768484976855,"reliability_score":54.86737741697699,"uncertainty_avg":45.13262258302301,"uncertainty_penalty":0.437718667755739},"none":{"ceiling_score":47.554841215429576,"expected_score":38.25213616983026,"reliability_score":78.07706609156172,"uncertainty_avg":21.922933908438278,"uncertainty_penalty":-2.9798086965442536}}},{"codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":37},"evidence_basis":"Provider-reported","failed_cell_count":11,"max":0.213668025,"mean":0.180929025625,"median":0.1746528825,"min":0.16318875,"recorded_attempt_count":37,"run_count":16,"total":2.89486441},"medium":{"admitted_cell_count":11,"cell_count":8,"cost_basis_counts":{"provider_reported":37},"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.07934969,"mean":0.053583788125,"median":0.0553142075,"min":0.02549349,"recorded_attempt_count":37,"run_count":16,"total":0.85734061},"none":{"admitted_cell_count":12,"cell_count":8,"cost_basis_counts":{"provider_reported":28},"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.053540475,"mean":0.026315053125,"median":0.024512850000000003,"min":0.012912625,"recorded_attempt_count":28,"run_count":16,"total":0.42104085}},"codegen_cost_usd":{"admitted_cell_count":28,"cell_count":24,"cost_basis_counts":{"provider_reported":102},"evidence_basis":"Provider-reported","failed_cell_count":20,"max":0.213668025,"mean":0.08694262229166666,"median":0.059337825,"min":0.012912625,"recorded_attempt_count":102,"run_count":48,"total":4.17324587},"codegen_latency_ms":{"attempt_count":102,"max_ms":555301,"mean_ms":164986.0625,"min_ms":16963,"run_count":48},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":37,"max_ms":555301,"mean_ms":365326.75,"min_ms":229871,"run_count":16},"medium":{"attempt_count":37,"max_ms":241627,"mean_ms":93984.5625,"min_ms":43075,"run_count":16},"none":{"attempt_count":28,"max_ms":81344,"mean_ms":35646.875,"min_ms":16963,"run_count":16}},"codegen_output_tokens":{"attempt_count":102,"output_max":55341,"output_mean":17791.3125,"output_min":1372,"run_count":48},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":37,"output_max":55341,"output_mean":40717.5625,"output_min":32915,"run_count":16},"medium":{"attempt_count":37,"output_max":17296,"output_mean":9330.3125,"output_min":3762,"run_count":16},"none":{"attempt_count":28,"output_max":6979,"output_mean":3326.0625,"output_min":1372,"run_count":16}},"display_name":"Inkling","economics":{"all":37.62075233805024,"highest":32.72427770487978,"medium":37.25115386936458,"none":38.70478012142812},"first_seen_at":null,"generation_metadata":{"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"other","provider_model":"thinkingmachines/inkling","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":11,"evaluated_cells":16,"failed_game_aliases":["GB2-02","GB2-03","GB2-06","GB2-08"],"model_code_failure_rate":0.3125,"model_code_failures":5,"repaired_admitted":11,"repaired_rate":0.6875},"baseline":{"admitted_plugins":12,"evaluated_cells":16,"failed_game_aliases":["GB2-02","GB2-06","GB2-07","GB2-08"],"first_pass_admitted":7,"first_pass_rate":0.4375,"model_code_failure_rate":0.25,"model_code_failures":4,"repaired_admitted":5,"repaired_rate":0.3125},"intensive":{"admitted_plugins":5,"evaluated_cells":16,"failed_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-05","GB2-06","GB2-07","GB2-08"],"model_code_failure_rate":0.6875,"model_code_failures":11,"repaired_admitted":5,"repaired_rate":0.3125}},"id":"thinkingmachines/inkling","is_recent_addition":false,"last_measured_at":"2026-07-27T11:37:44Z","match_totals_all":{"draws":503,"losses":668,"wins":463},"match_totals_tracks":{"highest":{"draws":73,"losses":80,"wins":47},"medium":{"draws":183,"losses":285,"wins":230},"none":{"draws":247,"losses":303,"wins":186}},"model_slug":"thinkingmachines-inkling","overall":{"max":55.633695043376434,"mean":33.31537421869243,"min":21.92797491218185},"per_game":{"GB2-02":23.232137065202014,"GB2-05":30.446555315679618,"GB2-06":55.633695043376434,"GB2-07":32.381026187959016,"GB2-08":21.92797491218185},"per_game_all":{"GB2-02":28.956038689213898,"GB2-05":33.152648768893826,"GB2-06":43.42613383364422,"GB2-07":38.449841910475655,"GB2-08":44.119098488023575},"per_game_match_totals_all":{"GB2-01":{"draws":90,"losses":99,"wins":55},"GB2-02":{"draws":164,"losses":9,"wins":1},"GB2-03":{"draws":45,"losses":26,"wins":25},"GB2-04":{"draws":167,"losses":39,"wins":20},"GB2-05":{"draws":0,"losses":189,"wins":125},"GB2-06":{"draws":4,"losses":90,"wins":72},"GB2-07":{"draws":0,"losses":132,"wins":104},"GB2-08":{"draws":33,"losses":84,"wins":61}},"per_game_match_totals_tracks":{"highest":{"GB2-02":{"draws":37,"losses":3,"wins":0},"GB2-05":{"draws":0,"losses":26,"wins":14},"GB2-06":{"draws":4,"losses":16,"wins":20},"GB2-07":{"draws":0,"losses":27,"wins":13},"GB2-08":{"draws":32,"losses":8,"wins":0}},"medium":{"GB2-01":{"draws":33,"losses":49,"wins":40},"GB2-02":{"draws":63,"losses":5,"wins":0},"GB2-04":{"draws":87,"losses":17,"wins":10},"GB2-05":{"draws":0,"losses":78,"wins":54},"GB2-06":{"draws":0,"losses":35,"wins":27},"GB2-07":{"draws":0,"losses":63,"wins":67},"GB2-08":{"draws":0,"losses":38,"wins":32}},"none":{"GB2-01":{"draws":57,"losses":50,"wins":15},"GB2-02":{"draws":64,"losses":1,"wins":1},"GB2-03":{"draws":45,"losses":26,"wins":25},"GB2-04":{"draws":80,"losses":22,"wins":10},"GB2-05":{"draws":0,"losses":85,"wins":57},"GB2-06":{"draws":0,"losses":39,"wins":25},"GB2-07":{"draws":0,"losses":42,"wins":24},"GB2-08":{"draws":1,"losses":38,"wins":29}}},"per_game_raw_elo_all":{"GB2-02":1480.5252513866828,"GB2-05":1401.9994445277644,"GB2-06":1437.1678017780052,"GB2-07":1430.4701091874704,"GB2-08":1553.2546189681414},"per_game_raw_elo_tracks":{"highest":{"GB2-02":1465.8763415935357,"GB2-05":1388.981231901262,"GB2-06":1536.7350100578335,"GB2-07":1392.94803374959,"GB2-08":1419.7799946445818},"medium":{"GB2-01":1381.0155302257313,"GB2-02":1476.5603955656177,"GB2-04":1472.8755524653086,"GB2-05":1366.8065500421274,"GB2-06":1356.7474097662753,"GB2-07":1540.3330460767777,"GB2-08":1602.2012432700476},"none":{"GB2-01":1332.7271647404896,"GB2-02":1499.1390170008954,"GB2-03":1523.1433202477533,"GB2-04":1472.803460952347,"GB2-05":1450.2105516399035,"GB2-06":1418.0209855099072,"GB2-07":1358.1292477360432,"GB2-08":1637.7826189897944}},"per_game_tracks":{"highest":{"GB2-02":23.232137065202014,"GB2-05":30.446555315679618,"GB2-06":55.633695043376434,"GB2-07":32.381026187959016,"GB2-08":21.92797491218185},"medium":{"GB2-01":32.38564662410492,"GB2-02":29.205662826109684,"GB2-04":30.70360759272194,"GB2-05":29.420591696289264,"GB2-06":33.17178175285869,"GB2-07":53.3592866591907,"GB2-08":52.51149993427681},"none":{"GB2-01":26.11987489541008,"GB2-02":34.43031617632999,"GB2-03":49.94247004323288,"GB2-04":30.55482235515263,"GB2-05":39.590799294712596,"GB2-06":41.47292470469752,"GB2-07":29.609212884277255,"GB2-08":57.91782061761204}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":32.72427770487978,"medium":33.20638391452173,"none":34.01546103667579},"reasoning_agg":{"highest":{"max":55.633695043376434,"mean":32.72427770487978,"min":21.92797491218185},"medium":{"max":53.3592866591907,"mean":33.20638391452173,"min":29.420591696289264},"none":{"max":49.94247004323288,"mean":34.01546103667579,"min":26.11987489541008}},"reasoning_labels":{"highest":"Max","medium":"Medium","none":"None"},"score_diagnostics":{"ceiling_score":55.633695043376434,"expected_score":31.41989148455989,"reasoning_variance":1.291183331796006,"reliability_score":77.15208606238274,"uncertainty_avg":22.847913937617268,"uncertainty_penalty":-1.8954827341325426},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":55.633695043376434,"expected_score":18.8535339718458,"reliability_score":65.66311905569697,"uncertainty_avg":34.33688094430304,"uncertainty_penalty":-13.870743733033983},"medium":{"ceiling_score":53.3592866591907,"expected_score":28.572478175800093,"reliability_score":81.69406657606251,"uncertainty_avg":18.305933423937493,"uncertainty_penalty":-4.633905738721637},"none":{"ceiling_score":49.94247004323288,"expected_score":41.99666315341641,"reliability_score":80.65644515062002,"uncertainty_avg":19.343554849379988,"uncertainty_penalty":7.981202116740619}}},{"codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":11,"cell_count":8,"cost_basis_counts":{"provider_reported":26},"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.015971877,"mean":0.00979196948,"median":0.009500477,"min":0.003562685,"recorded_attempt_count":26,"run_count":15,"total":0.14255357568000002},"none":{"admitted_cell_count":19,"cell_count":8,"cost_basis_counts":{"provider_reported":34},"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.0027823742,"mean":0.0022230800541666665,"median":0.002112839,"min":0.001825724,"recorded_attempt_count":34,"run_count":24,"total":0.0533539213}},"codegen_cost_usd":{"admitted_cell_count":30,"cell_count":16,"cost_basis_counts":{"provider_reported":60},"evidence_basis":"Provider-reported","failed_cell_count":9,"max":0.015971877,"mean":0.006007524767083333,"median":0.0031725295999999997,"min":0.001825724,"recorded_attempt_count":60,"run_count":39,"total":0.19590749698},"codegen_latency_ms":{"attempt_count":60,"max_ms":1394682,"mean_ms":253119.97435897432,"min_ms":18361,"run_count":39},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":26,"max_ms":1394682,"mean_ms":546872.0,"min_ms":61403,"run_count":15},"none":{"attempt_count":34,"max_ms":161045,"mean_ms":69524.95833333333,"min_ms":18361,"run_count":24}},"codegen_output_tokens":{"attempt_count":60,"output_max":82048,"output_mean":14181.94871794872,"output_min":1698,"run_count":39},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":26,"output_max":82048,"output_mean":31146.866666666665,"output_min":4091,"run_count":15},"none":{"attempt_count":34,"output_max":7189,"output_mean":3578.875,"output_min":1698,"run_count":24}},"display_name":"DeepSeek V4 Flash","economics":{"all":33.915348166742454,"highest":35.65980289732321,"medium":34.03657864577119,"none":34.065202319751236},"first_seen_at":null,"generation_metadata":{"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"deepseek","provider_model":"deepseek/deepseek-v4-flash","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"baseline":{"admitted_plugins":19,"evaluated_cells":24,"failed_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-06"],"first_pass_admitted":14,"first_pass_rate":0.5833333333333334,"model_code_failure_rate":0.20833333333333337,"model_code_failures":5,"repaired_admitted":5,"repaired_rate":0.20833333333333337},"intensive":{"admitted_plugins":11,"evaluated_cells":15,"failed_game_aliases":["GB2-03","GB2-04"],"first_pass_admitted":5,"first_pass_rate":0.3333333333333333,"infra_excluded_game_aliases":["GB2-08"],"infra_failures_excluded":1,"model_code_failure_rate":0.26666666666666666,"model_code_failures":4,"repaired_admitted":6,"repaired_rate":0.4}},"id":"deepseek/deepseek-v4-flash","is_recent_addition":false,"last_measured_at":"2026-07-27T11:59:44Z","match_totals_all":{"draws":869,"losses":945,"wins":594},"match_totals_tracks":{"highest":{"draws":182,"losses":310,"wins":202},"medium":{"draws":216,"losses":228,"wins":132},"none":{"draws":471,"losses":407,"wins":260}},"model_slug":"deepseek-deepseek-v4-flash","overall":{"max":51.48147323629893,"mean":33.12354951023329,"min":24.11930639666456},"per_game":{"GB2-01":41.39685486271934,"GB2-02":30.26185005867806,"GB2-05":36.14594446663055,"GB2-06":30.214944656619977,"GB2-07":49.87227457080003,"GB2-08":26.06694876849134},"per_game_all":{"GB2-01":43.557719975268355,"GB2-02":28.650662087689785,"GB2-05":35.03097983555876,"GB2-06":27.501309899543248,"GB2-07":42.46444792923975,"GB2-08":26.286969273154835},"per_game_match_totals_all":{"GB2-01":{"draws":78,"losses":111,"wins":83},"GB2-02":{"draws":278,"losses":16,"wins":6},"GB2-03":{"draws":53,"losses":43,"wins":40},"GB2-04":{"draws":176,"losses":24,"wins":4},"GB2-05":{"draws":0,"losses":259,"wins":169},"GB2-06":{"draws":2,"losses":211,"wins":99},"GB2-07":{"draws":0,"losses":228,"wins":178},"GB2-08":{"draws":282,"losses":53,"wins":15}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":30,"losses":53,"wins":39},"GB2-02":{"draws":104,"losses":8,"wins":6},"GB2-05":{"draws":0,"losses":86,"wins":54},"GB2-06":{"draws":0,"losses":87,"wins":37},"GB2-07":{"draws":0,"losses":62,"wins":62},"GB2-08":{"draws":48,"losses":14,"wins":4}},"medium":{"GB2-01":{"draws":25,"losses":37,"wins":22},"GB2-02":{"draws":68,"losses":6,"wins":0},"GB2-03":{"draws":9,"losses":9,"wins":12},"GB2-04":{"draws":33,"losses":4,"wins":1},"GB2-05":{"draws":0,"losses":55,"wins":39},"GB2-06":{"draws":2,"losses":52,"wins":28},"GB2-07":{"draws":0,"losses":57,"wins":29},"GB2-08":{"draws":79,"losses":8,"wins":1}},"none":{"GB2-01":{"draws":23,"losses":21,"wins":22},"GB2-02":{"draws":106,"losses":2,"wins":0},"GB2-03":{"draws":44,"losses":34,"wins":28},"GB2-04":{"draws":143,"losses":20,"wins":3},"GB2-05":{"draws":0,"losses":118,"wins":76},"GB2-06":{"draws":0,"losses":72,"wins":34},"GB2-07":{"draws":0,"losses":109,"wins":87},"GB2-08":{"draws":155,"losses":31,"wins":10}}},"per_game_raw_elo_all":{"GB2-01":1469.8676423482354,"GB2-02":1482.9931720966367,"GB2-05":1416.426712639883,"GB2-06":1319.5301666705511,"GB2-07":1461.0114066135545,"GB2-08":1438.00033501466},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1450.462126069157,"GB2-02":1484.4713582365903,"GB2-05":1421.697875125174,"GB2-06":1334.7200708029854,"GB2-07":1514.7809634969963,"GB2-08":1432.8957272786026},"medium":{"GB2-01":1478.9713630017695,"GB2-02":1472.025070521855,"GB2-03":1546.9358887216838,"GB2-04":1471.716990074414,"GB2-05":1393.1588342212412,"GB2-06":1331.1083724223636,"GB2-07":1440.1690757297024,"GB2-08":1444.349744639428},"none":{"GB2-01":1480.1694379737794,"GB2-02":1492.4830875314651,"GB2-03":1472.6397299598693,"GB2-04":1454.7935010604235,"GB2-05":1434.4234285732339,"GB2-06":1292.7620567863044,"GB2-07":1428.0841806139645,"GB2-08":1436.75553312595}},"per_game_tracks":{"highest":{"GB2-01":41.39685486271934,"GB2-02":30.26185005867806,"GB2-05":36.14594446663055,"GB2-06":30.214944656619977,"GB2-07":49.87227457080003,"GB2-08":26.06694876849134},"medium":{"GB2-01":43.773337420402555,"GB2-02":24.11930639666456,"GB2-03":51.48147323629893,"GB2-04":28.177411381216853,"GB2-05":31.50995183297395,"GB2-06":28.225170931660724,"GB2-07":38.83162319473614,"GB2-08":26.174354772215807},"none":{"GB2-01":45.502967642683174,"GB2-02":31.570829807726735,"GB2-03":41.7947922039493,"GB2-04":26.843121285289442,"GB2-05":37.437043207071774,"GB2-06":24.06381411034904,"GB2-07":38.6894460221831,"GB2-08":26.61960427875735}},"provider_color":"#4C8BF5","provider_company":"DeepSeek","provider_key":"deepseek","provider_text_color":"#f6f9ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":34.77469565398564,"medium":34.036578645771186,"none":30.559374230943043},"reasoning_agg":{"highest":{"max":49.87227457080003,"mean":34.77469565398564,"min":30.214944656619977},"medium":{"max":51.48147323629893,"mean":34.036578645771186,"min":24.11930639666456},"none":{"max":38.6894460221831,"mean":30.559374230943043,"min":26.61960427875735}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Reasoning disabled"},"score_diagnostics":{"ceiling_score":51.48147323629893,"expected_score":23.05878662926253,"reasoning_variance":4.215321423042596,"reliability_score":76.36044747966159,"uncertainty_avg":23.639552520338412,"uncertainty_penalty":-10.064762880970758},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":49.87227457080003,"expected_score":17.831824085173576,"reliability_score":81.31766588637613,"uncertainty_avg":18.68233411362387,"uncertainty_penalty":-16.942871568812063},"medium":{"ceiling_score":51.48147323629893,"expected_score":25.69445539616263,"reliability_score":65.43444294224412,"uncertainty_avg":34.56555705775589,"uncertainty_penalty":-8.342123249608555},"none":{"ceiling_score":38.6894460221831,"expected_score":30.79544246442015,"reliability_score":79.06025086378388,"uncertainty_avg":20.939749136216122,"uncertainty_penalty":0.23606823347710915}}},{"codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":17},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.09705768,"mean":0.0730637925,"median":0.07051098,"min":0.05225028,"recorded_attempt_count":17,"run_count":8,"total":0.58451034},"none":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.09803328,"mean":0.0253809975,"median":0.00943521,"min":0.00639384,"recorded_attempt_count":13,"run_count":8,"total":0.20304798}},"codegen_cost_usd":{"admitted_cell_count":13,"cell_count":16,"cost_basis_counts":{"provider_reported":30},"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.09803328,"mean":0.049222395,"median":0.05336871,"min":0.00639384,"recorded_attempt_count":30,"run_count":16,"total":0.78755832},"codegen_latency_ms":{"attempt_count":30,"max_ms":689304,"mean_ms":337511.375,"min_ms":47263,"run_count":16},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":17,"max_ms":689304,"mean_ms":510017.125,"min_ms":355427,"run_count":8},"none":{"attempt_count":13,"max_ms":622847,"mean_ms":165005.625,"min_ms":47263,"run_count":8}},"codegen_output_tokens":{"attempt_count":30,"output_max":78058,"output_mean":37255.0,"output_min":3462,"run_count":16},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":17,"output_max":76773,"output_mean":56941.375,"output_min":40677,"run_count":8},"none":{"attempt_count":13,"output_max":78058,"output_mean":17568.625,"output_min":3462,"run_count":8}},"display_name":"Minimax M3","economics":{"medium":28.831135463657088,"none":40.777893856075174},"first_seen_at":null,"generation_metadata":{"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"minimax","provider_model":"minimax/minimax-m3","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-03"],"model_code_failure_rate":0.125,"model_code_failures":1,"repaired_admitted":7,"repaired_rate":0.875},"baseline":{"admitted_plugins":6,"evaluated_cells":8,"failed_game_aliases":["GB2-04","GB2-06"],"first_pass_admitted":4,"first_pass_rate":0.5,"model_code_failure_rate":0.25,"model_code_failures":2,"repaired_admitted":2,"repaired_rate":0.25}},"id":"minimax/minimax-m3","is_recent_addition":false,"last_measured_at":"2026-07-27T11:52:47Z","match_totals_all":{"draws":254,"losses":312,"wins":226},"match_totals_tracks":{"medium":{"draws":157,"losses":177,"wins":86},"none":{"draws":97,"losses":135,"wins":140}},"model_slug":"minimax-minimax-m3","overall":{"max":52.69666989897096,"mean":32.916331924462284,"min":12.243419652002427},"per_game_match_totals_all":{"GB2-01":{"draws":19,"losses":63,"wins":56},"GB2-02":{"draws":111,"losses":6,"wins":1},"GB2-03":{"draws":20,"losses":11,"wins":21},"GB2-04":{"draws":43,"losses":3,"wins":2},"GB2-05":{"draws":0,"losses":88,"wins":40},"GB2-06":{"draws":0,"losses":37,"wins":19},"GB2-07":{"draws":0,"losses":61,"wins":57},"GB2-08":{"draws":61,"losses":43,"wins":30}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":4,"losses":40,"wins":24},"GB2-02":{"draws":56,"losses":5,"wins":1},"GB2-04":{"draws":43,"losses":3,"wins":2},"GB2-05":{"draws":0,"losses":51,"wins":7},"GB2-06":{"draws":0,"losses":37,"wins":19},"GB2-07":{"draws":0,"losses":31,"wins":29},"GB2-08":{"draws":54,"losses":10,"wins":4}},"none":{"GB2-01":{"draws":15,"losses":23,"wins":32},"GB2-02":{"draws":55,"losses":1,"wins":0},"GB2-03":{"draws":20,"losses":11,"wins":21},"GB2-05":{"draws":0,"losses":37,"wins":33},"GB2-07":{"draws":0,"losses":30,"wins":28},"GB2-08":{"draws":7,"losses":33,"wins":26}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1409.6814477369219,"GB2-02":1473.372937630626,"GB2-04":1496.3916661363678,"GB2-05":1247.4219158546216,"GB2-06":1364.522971792873,"GB2-07":1498.1236759239546,"GB2-08":1459.010175716237},"none":{"GB2-01":1497.3874694861893,"GB2-02":1475.919430546933,"GB2-03":1537.2180654375327,"GB2-05":1469.451876888559,"GB2-07":1424.7213899013211,"GB2-08":1499.683273236858}},"per_game_tracks":{"medium":{"GB2-01":33.92438548422537,"GB2-02":22.896721550174966,"GB2-04":29.759754221251917,"GB2-05":12.243419652002427,"GB2-06":30.999309214021814,"GB2-07":44.83748928548472,"GB2-08":27.156868838438402},"none":{"GB2-01":47.91834193923778,"GB2-02":27.899111953447644,"GB2-03":52.69666989897096,"GB2-05":41.85000638911461,"GB2-07":37.889795026123,"GB2-08":36.413437929557105}},"provider_color":"#00BFA5","provider_company":"MiniMax","provider_key":"minimax","provider_text_color":"#f2fffc","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":27.884557682511353,"none":37.94810616641322},"reasoning_agg":{"medium":{"max":44.83748928548472,"mean":27.884557682511353,"min":12.243419652002427},"none":{"max":52.69666989897096,"mean":37.94810616641322,"min":27.899111953447644}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"score_diagnostics":{"ceiling_score":52.69666989897096,"reasoning_variance":10.063548483901865},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":44.83748928548472,"expected_score":23.600233609088065,"reliability_score":53.08494495395188,"uncertainty_avg":46.91505504604812,"uncertainty_penalty":-4.284324073423289},"none":{"ceiling_score":52.69666989897096,"expected_score":42.0498636743743,"reliability_score":80.4559594474089,"uncertainty_avg":19.544040552591095,"uncertainty_penalty":4.101757507961082}}},{"codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":16},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.08827968,"mean":0.05437612,"median":0.0574344,"min":0.00733824,"recorded_attempt_count":16,"run_count":8,"total":0.43500896},"none":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.0154064,"mean":0.00874386,"median":0.0064215999999999995,"min":0.00524064,"recorded_attempt_count":13,"run_count":9,"total":0.08145696000000001}},"codegen_cost_usd":{"admitted_cell_count":12,"cell_count":16,"cost_basis_counts":{"provider_reported":29},"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.08827968,"mean":0.03155999,"median":0.01479536,"min":0.00524064,"recorded_attempt_count":29,"run_count":17,"total":0.51646592},"codegen_latency_ms":{"attempt_count":29,"max_ms":1361767,"mean_ms":422352.6470588235,"min_ms":51720,"run_count":17},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":16,"max_ms":1361767,"mean_ms":800306.75,"min_ms":68429,"run_count":8},"none":{"attempt_count":13,"max_ms":153912,"mean_ms":86393.44444444444,"min_ms":51720,"run_count":9}},"codegen_output_tokens":{"attempt_count":29,"output_max":62955,"output_mean":20190.70588235294,"output_min":2265,"run_count":17},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":16,"output_max":62955,"output_mean":38265.375,"output_min":3140,"run_count":8},"none":{"attempt_count":13,"output_max":7814,"output_mean":4124.333333333333,"output_min":2265,"run_count":9}},"display_name":"Qwen3.7 Plus","economics":{"medium":40.879144070193625,"none":30.833398047231174},"first_seen_at":null,"generation_metadata":{"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"qwen","provider_model":"qwen/qwen3.7-plus","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":6,"evaluated_cells":8,"failed_game_aliases":["GB2-03","GB2-04"],"first_pass_admitted":1,"first_pass_rate":0.125,"model_code_failure_rate":0.25,"model_code_failures":2,"repaired_admitted":5,"repaired_rate":0.625},"baseline":{"admitted_plugins":6,"evaluated_cells":9,"failed_game_aliases":["GB2-01","GB2-03","GB2-08"],"first_pass_admitted":4,"first_pass_rate":0.4444444444444444,"model_code_failure_rate":0.3333333333333333,"model_code_failures":3,"repaired_admitted":2,"repaired_rate":0.2222222222222222}},"id":"qwen/qwen3.7-plus","is_recent_addition":false,"last_measured_at":"2026-07-27T11:44:24Z","match_totals_all":{"draws":240,"losses":274,"wins":226},"match_totals_tracks":{"medium":{"draws":140,"losses":122,"wins":134},"none":{"draws":100,"losses":152,"wins":92}},"model_slug":"qwen-qwen3-7-plus","overall":{"max":58.39911627396981,"mean":32.81840659142981,"min":18.05367245403799},"per_game_match_totals_all":{"GB2-01":{"draws":28,"losses":61,"wins":45},"GB2-02":{"draws":111,"losses":2,"wins":1},"GB2-04":{"draws":34,"losses":3,"wins":3},"GB2-05":{"draws":0,"losses":68,"wins":72},"GB2-06":{"draws":11,"losses":64,"wins":45},"GB2-07":{"draws":0,"losses":72,"wins":60},"GB2-08":{"draws":56,"losses":4,"wins":0}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":10,"losses":29,"wins":29},"GB2-02":{"draws":63,"losses":2,"wins":1},"GB2-05":{"draws":0,"losses":31,"wins":39},"GB2-06":{"draws":11,"losses":20,"wins":29},"GB2-07":{"draws":0,"losses":36,"wins":36},"GB2-08":{"draws":56,"losses":4,"wins":0}},"none":{"GB2-01":{"draws":18,"losses":32,"wins":16},"GB2-02":{"draws":48,"losses":0,"wins":0},"GB2-04":{"draws":34,"losses":3,"wins":3},"GB2-05":{"draws":0,"losses":37,"wins":33},"GB2-06":{"draws":0,"losses":44,"wins":16},"GB2-07":{"draws":0,"losses":36,"wins":24}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1507.9573663660653,"GB2-02":1495.4643675592058,"GB2-05":1508.3722086805083,"GB2-06":1566.8929275335172,"GB2-07":1460.0772374862684,"GB2-08":1462.1361809829436},"none":{"GB2-01":1378.486150271109,"GB2-02":1495.4141301372438,"GB2-04":1508.141304108455,"GB2-05":1416.7106818294349,"GB2-06":1347.1351283730276,"GB2-07":1272.023445307137}},"per_game_tracks":{"medium":{"GB2-01":46.577603476802054,"GB2-02":28.702345229467554,"GB2-05":44.01048103554146,"GB2-06":58.39911627396981,"GB2-07":40.56507075019223,"GB2-08":27.02024765518864},"none":{"GB2-01":32.3088107693705,"GB2-02":31.562942122426243,"GB2-04":35.74840773334668,"GB2-05":35.55024026744643,"GB2-06":31.776314936759203,"GB2-07":18.05367245403799}},"provider_color":"#FF6A00","provider_company":"Alibaba","provider_key":"qwen","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":38.042330107656966,"none":27.594483075202657},"reasoning_agg":{"medium":{"max":58.39911627396981,"mean":38.042330107656966,"min":27.02024765518864},"none":{"max":35.74840773334668,"mean":27.594483075202657,"min":18.05367245403799}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"score_diagnostics":{"ceiling_score":58.39911627396981,"reasoning_variance":10.447847032454309},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":58.39911627396981,"expected_score":39.14354553757244,"reliability_score":56.93639978249186,"uncertainty_avg":43.06360021750814,"uncertainty_penalty":1.1012154299154773},"none":{"ceiling_score":35.74840773334668,"expected_score":30.291455999970125,"reliability_score":77.42064376773071,"uncertainty_avg":22.57935623226929,"uncertainty_penalty":2.6969729247674685}}},{"codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":18},"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.08193244999999999,"mean":0.05495368125,"median":0.056941025,"min":0.02174195,"recorded_attempt_count":18,"run_count":8,"total":0.43962945},"medium":{"admitted_cell_count":4,"cell_count":8,"cost_basis_counts":{"provider_reported":17},"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.0711619,"mean":0.0371769625,"median":0.029592175,"min":0.02387735,"recorded_attempt_count":17,"run_count":8,"total":0.2974157},"none":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":20},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.03772852,"mean":0.024905897500000003,"median":0.0260953,"min":0.00984735,"recorded_attempt_count":20,"run_count":8,"total":0.19924718}},"codegen_cost_usd":{"admitted_cell_count":16,"cell_count":24,"cost_basis_counts":{"provider_reported":55},"evidence_basis":"Provider-reported","failed_cell_count":8,"max":0.08193244999999999,"mean":0.03901218041666666,"median":0.03030545,"min":0.00984735,"recorded_attempt_count":55,"run_count":24,"total":0.9362923300000002},"codegen_latency_ms":{"attempt_count":55,"max_ms":388984,"mean_ms":191923.16666666663,"min_ms":73907,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":18,"max_ms":388984,"mean_ms":256781.125,"min_ms":132388,"run_count":8},"medium":{"attempt_count":17,"max_ms":302393,"mean_ms":191196.875,"min_ms":134501,"run_count":8},"none":{"attempt_count":20,"max_ms":209946,"mean_ms":127791.5,"min_ms":73907,"run_count":8}},"codegen_output_tokens":{"attempt_count":55,"output_max":67551,"output_mean":30962.125,"output_min":6729,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":18,"output_max":67551,"output_mean":44594.375,"output_min":16213,"run_count":8},"medium":{"attempt_count":17,"output_max":59186,"output_mean":29392.75,"output_min":18109,"run_count":8},"none":{"attempt_count":20,"output_max":28972,"output_mean":18899.25,"output_min":6729,"run_count":8}},"display_name":"Step 3.7 Flash","economics":{"all":40.498306634354506,"highest":30.663694734085276,"medium":40.98023139587707,"none":37.07527376145696},"first_seen_at":null,"generation_metadata":{"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"stepfun","provider_model":"stepfun/step-3.7-flash","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":4,"evaluated_cells":8,"failed_game_aliases":["GB2-01","GB2-03","GB2-07","GB2-08"],"model_code_failure_rate":0.5,"model_code_failures":4,"repaired_admitted":4,"repaired_rate":0.5},"baseline":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-02"],"first_pass_admitted":1,"first_pass_rate":0.125,"model_code_failure_rate":0.125,"model_code_failures":1,"repaired_admitted":6,"repaired_rate":0.75},"intensive":{"admitted_plugins":5,"evaluated_cells":8,"failed_game_aliases":["GB2-02","GB2-03","GB2-04"],"model_code_failure_rate":0.375,"model_code_failures":3,"repaired_admitted":5,"repaired_rate":0.625}},"id":"stepfun/step-3.7-flash","is_recent_addition":false,"last_measured_at":"2026-07-27T11:46:13Z","match_totals_all":{"draws":226,"losses":355,"wins":237},"match_totals_tracks":{"highest":{"draws":59,"losses":179,"wins":92},"medium":{"draws":92,"losses":64,"wins":58},"none":{"draws":75,"losses":112,"wins":87}},"model_slug":"stepfun-step-3-7-flash","overall":{"max":53.536938067285334,"mean":32.52748811060747,"min":19.24313559757037},"per_game":{"GB2-01":19.617975464814673,"GB2-05":40.40736615648161,"GB2-06":39.445251848942995,"GB2-07":28.69197294013675,"GB2-08":25.155907260050387},"per_game_all":{"GB2-05":43.51919585279254,"GB2-06":37.47741741591647},"per_game_match_totals_all":{"GB2-01":{"draws":17,"losses":70,"wins":31},"GB2-02":{"draws":49,"losses":4,"wins":1},"GB2-03":{"draws":21,"losses":10,"wins":9},"GB2-04":{"draws":55,"losses":6,"wins":13},"GB2-05":{"draws":0,"losses":80,"wins":80},"GB2-06":{"draws":2,"losses":91,"wins":57},"GB2-07":{"draws":0,"losses":71,"wins":43},"GB2-08":{"draws":82,"losses":23,"wins":3}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":4,"losses":45,"wins":13},"GB2-05":{"draws":0,"losses":35,"wins":31},"GB2-06":{"draws":1,"losses":37,"wins":24},"GB2-07":{"draws":0,"losses":47,"wins":21},"GB2-08":{"draws":54,"losses":15,"wins":3}},"medium":{"GB2-02":{"draws":49,"losses":4,"wins":1},"GB2-04":{"draws":42,"losses":3,"wins":5},"GB2-05":{"draws":0,"losses":24,"wins":32},"GB2-06":{"draws":1,"losses":33,"wins":20}},"none":{"GB2-01":{"draws":13,"losses":25,"wins":18},"GB2-03":{"draws":21,"losses":10,"wins":9},"GB2-04":{"draws":13,"losses":3,"wins":8},"GB2-05":{"draws":0,"losses":21,"wins":17},"GB2-06":{"draws":0,"losses":21,"wins":13},"GB2-07":{"draws":0,"losses":24,"wins":22},"GB2-08":{"draws":28,"losses":8,"wins":0}}},"per_game_raw_elo_all":{"GB2-05":1498.0206977371615,"GB2-06":1402.8448451237643},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1302.5506201377445,"GB2-05":1479.067627271918,"GB2-06":1424.6190995091226,"GB2-07":1370.1870771688791,"GB2-08":1445.1003995422361},"medium":{"GB2-02":1497.5007403786417,"GB2-04":1526.1505400202454,"GB2-05":1572.8040677708518,"GB2-06":1388.4103550666105},"none":{"GB2-01":1479.5735802409645,"GB2-03":1522.423633843672,"GB2-04":1529.6913005047602,"GB2-05":1442.1903981687146,"GB2-06":1395.505080795559,"GB2-07":1426.1484616915282,"GB2-08":1405.73919833146}},"per_game_tracks":{"highest":{"GB2-01":19.617975464814673,"GB2-05":40.40736615648161,"GB2-06":39.445251848942995,"GB2-07":28.69197294013675,"GB2-08":25.155907260050387},"medium":{"GB2-02":32.827810893590744,"GB2-04":40.6224615828462,"GB2-05":53.536938067285334,"GB2-06":36.933715039786},"none":{"GB2-01":44.89189158155693,"GB2-03":48.91915370704513,"GB2-04":36.549112144936515,"GB2-05":36.613283334610685,"GB2-06":36.05328535902041,"GB2-07":37.25705460545867,"GB2-08":19.24313559757037}},"provider_color":"#F59E0B","provider_company":"StepFun","provider_key":"stepfun","provider_text_color":"#1f1300","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":27.264308490671404,"medium":34.460129677060756,"none":35.858026164090255},"reasoning_agg":{"highest":{"max":40.40736615648161,"mean":27.264308490671404,"min":19.617975464814673},"medium":{"max":53.536938067285334,"mean":34.460129677060756,"min":32.827810893590744},"none":{"max":48.91915370704513,"mean":35.858026164090255,"min":19.24313559757037}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"score_diagnostics":{"ceiling_score":53.536938067285334,"expected_score":34.37044835303703,"reasoning_variance":8.593717673418851,"reliability_score":64.76762521178091,"uncertainty_avg":35.23237478821908,"uncertainty_penalty":1.8429602424295553},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":40.40736615648161,"expected_score":16.451408053030214,"reliability_score":57.20722402456279,"uncertainty_avg":42.79277597543721,"uncertainty_penalty":-10.81290043764119},"medium":{"ceiling_score":53.536938067285334,"expected_score":40.984922171010375,"reliability_score":75.97985136317473,"uncertainty_avg":24.020148636825276,"uncertainty_penalty":6.524792493949619},"none":{"ceiling_score":48.91915370704513,"expected_score":43.68976407056349,"reliability_score":63.17500134648909,"uncertainty_avg":36.82499865351091,"uncertainty_penalty":7.831737906473236}}},{"codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0056201515,"mean":0.0029446039375,"median":0.001956843,"min":0.001266762,"recorded_attempt_count":13,"run_count":9,"total":0.029176982999999997},"none":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.001632522,"mean":0.00126739675,"median":0.001232095,"min":0.00090937,"recorded_attempt_count":11,"run_count":8,"total":0.010139174}},"codegen_cost_usd":{"admitted_cell_count":13,"cell_count":16,"cost_basis_counts":{"provider_reported":24},"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.0056201515,"mean":0.00210600034375,"median":0.0014932259999999998,"min":0.00090937,"recorded_attempt_count":24,"run_count":17,"total":0.039316157},"codegen_latency_ms":{"attempt_count":24,"max_ms":257254,"mean_ms":73974.64705882352,"min_ms":16892,"run_count":17},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":13,"max_ms":257254,"mean_ms":112054.22222222222,"min_ms":27775,"run_count":9},"none":{"attempt_count":11,"max_ms":46063,"mean_ms":31135.125,"min_ms":16892,"run_count":8}},"codegen_output_tokens":{"attempt_count":24,"output_max":22587,"output_mean":7143.882352941177,"output_min":1430,"run_count":17},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":13,"output_max":22587,"output_mean":11299.555555555557,"output_min":2974,"run_count":9},"none":{"attempt_count":11,"output_max":3514,"output_mean":2468.75,"output_min":1430,"run_count":8}},"display_name":"Hy3 Preview","economics":{"highest":32.34261611083271,"none":38.897398778071},"first_seen_at":null,"generation_metadata":{"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"tencent","provider_model":"tencent/hy3-preview","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"baseline":{"admitted_plugins":6,"evaluated_cells":8,"failed_game_aliases":["GB2-06","GB2-07"],"first_pass_admitted":4,"first_pass_rate":0.5,"model_code_failure_rate":0.25,"model_code_failures":2,"repaired_admitted":2,"repaired_rate":0.25},"intensive":{"admitted_plugins":7,"evaluated_cells":9,"failed_game_aliases":["GB2-03","GB2-05"],"first_pass_admitted":5,"first_pass_rate":0.5555555555555556,"model_code_failure_rate":0.2222222222222222,"model_code_failures":2,"repaired_admitted":2,"repaired_rate":0.2222222222222222}},"id":"tencent/hy3-preview","is_recent_addition":false,"last_measured_at":"2026-07-27T11:48:11Z","match_totals_all":{"draws":323,"losses":316,"wins":247},"match_totals_tracks":{"highest":{"draws":130,"losses":208,"wins":144},"none":{"draws":193,"losses":108,"wins":103}},"model_slug":"tencent-hy3-preview","overall":{"max":71.25680984831166,"mean":31.86728280223101,"min":18.058264435137527},"per_game":{"GB2-01":51.729550125281335,"GB2-02":21.27542844920532,"GB2-04":18.058264435137527,"GB2-05":50.46607244200722,"GB2-06":28.004963816593822,"GB2-07":29.91154038722549,"GB2-08":26.952493120378215},"per_game_match_totals_all":{"GB2-01":{"draws":24,"losses":46,"wins":70},"GB2-02":{"draws":121,"losses":12,"wins":1},"GB2-03":{"draws":23,"losses":20,"wins":25},"GB2-04":{"draws":69,"losses":15,"wins":10},"GB2-05":{"draws":0,"losses":79,"wins":71},"GB2-06":{"draws":0,"losses":54,"wins":20},"GB2-07":{"draws":0,"losses":43,"wins":25},"GB2-08":{"draws":86,"losses":47,"wins":25}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":9,"losses":31,"wins":28},"GB2-02":{"draws":64,"losses":7,"wins":1},"GB2-04":{"draws":36,"losses":9,"wins":1},"GB2-05":{"draws":0,"losses":31,"wins":45},"GB2-06":{"draws":0,"losses":54,"wins":20},"GB2-07":{"draws":0,"losses":43,"wins":25},"GB2-08":{"draws":21,"losses":33,"wins":24}},"none":{"GB2-01":{"draws":15,"losses":15,"wins":42},"GB2-02":{"draws":57,"losses":5,"wins":0},"GB2-03":{"draws":23,"losses":20,"wins":25},"GB2-04":{"draws":33,"losses":6,"wins":9},"GB2-05":{"draws":0,"losses":48,"wins":26},"GB2-08":{"draws":65,"losses":14,"wins":1}}},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1547.2346974795885,"GB2-02":1461.2682908580343,"GB2-04":1439.8902675454406,"GB2-05":1559.2077630285235,"GB2-06":1332.7686768658655,"GB2-07":1379.5223503800132,"GB2-08":1453.7327498486231},"none":{"GB2-01":1676.59501851212,"GB2-02":1466.7923583848676,"GB2-03":1436.7909872054654,"GB2-04":1517.8546980180151,"GB2-05":1375.3160039220393,"GB2-08":1450.2389966102576}},"per_game_tracks":{"highest":{"GB2-01":51.729550125281335,"GB2-02":21.27542844920532,"GB2-04":18.058264435137527,"GB2-05":50.46607244200722,"GB2-06":28.004963816593822,"GB2-07":29.91154038722549,"GB2-08":26.952493120378215},"none":{"GB2-01":71.25680984831166,"GB2-02":26.336139967911993,"GB2-03":36.848972779507136,"GB2-04":38.74445802482134,"GB2-05":30.759058589728017,"GB2-08":29.438953458145875}},"provider_color":"#12B7F5","provider_company":"Tencent","provider_key":"tencent","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":27.536457295157074,"none":36.19810830930494},"reasoning_agg":{"highest":{"max":51.729550125281335,"mean":27.536457295157074,"min":18.058264435137527},"none":{"max":71.25680984831166,"mean":36.19810830930494,"min":26.336139967911993}},"reasoning_labels":{"highest":"High","medium":"Setting not tested","none":"None"},"score_diagnostics":{"ceiling_score":71.25680984831166,"reasoning_variance":8.661651014147868},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":51.729550125281335,"expected_score":17.19932347605386,"reliability_score":58.19832302256383,"uncertainty_avg":41.80167697743617,"uncertainty_penalty":-10.337133819103215},"none":{"ceiling_score":71.25680984831166,"expected_score":37.76256204840927,"reliability_score":82.67887785351489,"uncertainty_avg":17.32112214648511,"uncertainty_penalty":1.56445373910433}}},{"codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":18},"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.01660212,"mean":0.00855959175,"median":0.005979701,"min":0.00271606,"recorded_attempt_count":18,"run_count":8,"total":0.068476734},"medium":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":16},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.00444719,"mean":0.0024656575,"median":0.002155255,"min":0.001130258,"recorded_attempt_count":16,"run_count":8,"total":0.01972526},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"evidence_basis":"Provider-reported","max":0.0032939400000000004,"mean":0.0016413085,"median":0.0014119655,"min":0.00045831,"recorded_attempt_count":13,"run_count":8,"total":0.013130468}},"codegen_cost_usd":{"admitted_cell_count":20,"cell_count":24,"cost_basis_counts":{"provider_reported":47},"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.01660212,"mean":0.004222185916666667,"median":0.0025298300000000003,"min":0.00045831,"recorded_attempt_count":47,"run_count":24,"total":0.10133246200000004},"codegen_latency_ms":{"attempt_count":47,"max_ms":622759,"mean_ms":224913.25,"min_ms":19833,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":18,"max_ms":622759,"mean_ms":459174.25,"min_ms":329312,"run_count":8},"medium":{"attempt_count":16,"max_ms":213246,"mean_ms":118332.0,"min_ms":41554,"run_count":8},"none":{"attempt_count":13,"max_ms":226636,"mean_ms":97233.5,"min_ms":19833,"run_count":8}},"codegen_output_tokens":{"attempt_count":47,"output_max":43929,"output_mean":12093.125,"output_min":1331,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":18,"output_max":43929,"output_mean":27685.0,"output_min":18493,"run_count":8},"medium":{"attempt_count":16,"output_max":8961,"output_mean":5674.0,"output_min":2048,"run_count":8},"none":{"attempt_count":13,"output_max":5763,"output_mean":2920.375,"output_min":1331,"run_count":8}},"display_name":"GPT-OSS 120B","economics":{"all":31.100308675319038,"highest":33.62820028985485,"medium":33.28749406524547,"none":31.74085699621168},"first_seen_at":null,"generation_metadata":{"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"openai/gpt-oss-120b","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-07"],"first_pass_admitted":1,"first_pass_rate":0.125,"model_code_failure_rate":0.125,"model_code_failures":1,"repaired_admitted":6,"repaired_rate":0.75},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":5,"first_pass_rate":0.625,"model_code_failure_rate":0.0,"model_code_failures":0,"repaired_admitted":3,"repaired_rate":0.375},"intensive":{"admitted_plugins":5,"evaluated_cells":8,"failed_game_aliases":["GB2-01","GB2-03","GB2-05"],"model_code_failure_rate":0.375,"model_code_failures":3,"repaired_admitted":5,"repaired_rate":0.625}},"id":"openai/gpt-oss-120b","is_recent_addition":false,"last_measured_at":"2026-07-27T11:52:32Z","match_totals_all":{"draws":436,"losses":322,"wins":232},"match_totals_tracks":{"highest":{"draws":150,"losses":104,"wins":80},"medium":{"draws":173,"losses":112,"wins":83},"none":{"draws":113,"losses":106,"wins":69}},"model_slug":"openai-gpt-oss-120b","overall":{"max":60.76783956869306,"mean":31.27854371239756,"min":14.420068188974202},"per_game":{"GB2-02":19.179163036226186,"GB2-04":27.9194705568705,"GB2-06":60.76783956869306,"GB2-07":34.57852104475718,"GB2-08":25.696007242727312},"per_game_all":{"GB2-02":25.705788269555484,"GB2-04":24.349437772224352,"GB2-06":47.43196594193685,"GB2-08":26.91404271755947},"per_game_match_totals_all":{"GB2-01":{"draws":29,"losses":37,"wins":28},"GB2-02":{"draws":137,"losses":10,"wins":1},"GB2-03":{"draws":49,"losses":16,"wins":11},"GB2-04":{"draws":83,"losses":28,"wins":15},"GB2-05":{"draws":0,"losses":48,"wins":52},"GB2-06":{"draws":5,"losses":96,"wins":79},"GB2-07":{"draws":0,"losses":63,"wins":35},"GB2-08":{"draws":133,"losses":24,"wins":11}},"per_game_match_totals_tracks":{"highest":{"GB2-02":{"draws":53,"losses":7,"wins":0},"GB2-04":{"draws":36,"losses":14,"wins":10},"GB2-06":{"draws":3,"losses":33,"wins":42},"GB2-07":{"draws":0,"losses":40,"wins":22},"GB2-08":{"draws":58,"losses":10,"wins":6}},"medium":{"GB2-01":{"draws":18,"losses":22,"wins":16},"GB2-02":{"draws":45,"losses":2,"wins":1},"GB2-03":{"draws":28,"losses":11,"wins":7},"GB2-04":{"draws":36,"losses":4,"wins":4},"GB2-05":{"draws":0,"losses":29,"wins":33},"GB2-06":{"draws":1,"losses":34,"wins":19},"GB2-08":{"draws":45,"losses":10,"wins":3}},"none":{"GB2-01":{"draws":11,"losses":15,"wins":12},"GB2-02":{"draws":39,"losses":1,"wins":0},"GB2-03":{"draws":21,"losses":5,"wins":4},"GB2-04":{"draws":11,"losses":10,"wins":1},"GB2-05":{"draws":0,"losses":19,"wins":19},"GB2-06":{"draws":1,"losses":29,"wins":18},"GB2-07":{"draws":0,"losses":23,"wins":13},"GB2-08":{"draws":30,"losses":4,"wins":2}}},"per_game_raw_elo_all":{"GB2-02":1477.6147257486102,"GB2-04":1460.2262793877828,"GB2-06":1472.302672460759,"GB2-08":1450.686172585885},"per_game_raw_elo_tracks":{"highest":{"GB2-02":1458.3997310867876,"GB2-04":1478.6670650224664,"GB2-06":1579.6136430974516,"GB2-07":1419.3250538494135,"GB2-08":1447.3687877312982},"medium":{"GB2-01":1406.1009817298916,"GB2-02":1484.5879724595852,"GB2-03":1431.961147134627,"GB2-04":1480.001540532111,"GB2-05":1447.33708487285,"GB2-06":1369.2947045902554,"GB2-08":1464.2474413129037},"none":{"GB2-01":1413.0817228894214,"GB2-02":1489.8564736994583,"GB2-03":1478.271732610354,"GB2-04":1422.0102326087713,"GB2-05":1430.2908983914597,"GB2-06":1467.99966969457,"GB2-07":1369.5464379088992,"GB2-08":1440.4422887134535}},"per_game_tracks":{"highest":{"GB2-02":19.179163036226186,"GB2-04":27.9194705568705,"GB2-06":60.76783956869306,"GB2-07":34.57852104475718,"GB2-08":25.696007242727312},"medium":{"GB2-01":35.358279790014166,"GB2-02":28.976047880768927,"GB2-03":34.30664851641847,"GB2-04":30.70877457082836,"GB2-05":38.85920360288856,"GB2-06":34.37659816081083,"GB2-08":30.42690593498895},"none":{"GB2-01":34.827672532836864,"GB2-02":28.962153891671328,"GB2-03":39.860356628188114,"GB2-04":14.420068188974202,"GB2-05":35.1919263578203,"GB2-06":47.15146009630666,"GB2-07":28.89400329893377,"GB2-08":24.61921497496216}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":29.900168086056908,"medium":32.1946060549241,"none":31.740856996211672},"reasoning_agg":{"highest":{"max":60.76783956869306,"mean":29.900168086056908,"min":19.179163036226186},"medium":{"max":38.85920360288856,"mean":32.1946060549241,"min":28.976047880768927},"none":{"max":47.15146009630666,"mean":31.740856996211672,"min":14.420068188974202}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"score_diagnostics":{"ceiling_score":60.76783956869306,"expected_score":20.58409776053903,"reasoning_variance":2.294437968867193,"reliability_score":63.696386047806214,"uncertainty_avg":36.303613952193786,"uncertainty_penalty":-10.69444595185853},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":60.76783956869306,"expected_score":20.735892945312987,"reliability_score":56.50507191835876,"uncertainty_avg":43.49492808164124,"uncertainty_penalty":-9.164275140743921},"medium":{"ceiling_score":38.85920360288856,"expected_score":22.33493534032581,"reliability_score":75.08831359251839,"uncertainty_avg":24.911686407481607,"uncertainty_penalty":-9.859670714598291},"none":{"ceiling_score":47.15146009630666,"expected_score":28.992110691467552,"reliability_score":60.237193559344526,"uncertainty_avg":39.762806440655474,"uncertainty_penalty":-2.7487463047441203}}},{"codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":4,"cell_count":7,"cost_basis_counts":{"provider_reported":15},"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.0092087,"mean":0.006571171428571429,"median":0.00666192,"min":0.00456754,"recorded_attempt_count":15,"run_count":7,"total":0.0459982},"none":{"admitted_cell_count":6,"cell_count":7,"cost_basis_counts":{"provider_reported":8},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.00391754,"mean":0.0023617857142857143,"median":0.00186618,"min":0.00144036,"recorded_attempt_count":8,"run_count":7,"total":0.0165325}},"codegen_cost_usd":{"admitted_cell_count":10,"cell_count":14,"cost_basis_counts":{"provider_reported":23},"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.0092087,"mean":0.004466478571428571,"median":0.0042425399999999995,"min":0.00144036,"recorded_attempt_count":23,"run_count":14,"total":0.06253070000000001},"codegen_latency_ms":{"attempt_count":23,"max_ms":550842,"mean_ms":222264.07142857145,"min_ms":41984,"run_count":14},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":15,"max_ms":550842,"mean_ms":354649.85714285716,"min_ms":219950,"run_count":7},"none":{"attempt_count":8,"max_ms":161392,"mean_ms":89878.28571428571,"min_ms":41984,"run_count":7}},"codegen_output_tokens":{"attempt_count":23,"output_max":12552,"output_mean":5500.928571428572,"output_min":1283,"run_count":14},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":15,"output_max":12552,"output_mean":8851.57142857143,"output_min":6019,"run_count":7},"none":{"attempt_count":8,"output_max":4235,"output_mean":2150.285714285714,"output_min":1283,"run_count":7}},"display_name":"Gemma 4 31B","economics":{"medium":36.230230619845194,"none":32.157004896285834},"first_seen_at":null,"generation_metadata":{"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"google","provider_model":"google/gemma-4-31b-it","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":4,"evaluated_cells":7,"failed_game_aliases":["GB2-02","GB2-03","GB2-08"],"infra_excluded_game_aliases":["GB2-01"],"infra_failures_excluded":1,"model_code_failure_rate":0.42857142857142855,"model_code_failures":3,"repaired_admitted":4,"repaired_rate":0.5714285714285714},"baseline":{"admitted_plugins":6,"evaluated_cells":7,"failed_game_aliases":["GB2-03"],"first_pass_admitted":5,"first_pass_rate":0.7142857142857143,"infra_excluded_game_aliases":["GB2-02"],"infra_failures_excluded":1,"model_code_failure_rate":0.14285714285714285,"model_code_failures":1,"repaired_admitted":1,"repaired_rate":0.14285714285714285}},"id":"google/gemma-4-31b-it","is_recent_addition":false,"last_measured_at":"2026-07-27T11:24:44Z","match_totals_all":{"draws":147,"losses":245,"wins":180},"match_totals_tracks":{"medium":{"draws":47,"losses":108,"wins":83},"none":{"draws":100,"losses":137,"wins":97}},"model_slug":"google-gemma-4-31b-it","overall":{"max":44.68186759149837,"mean":31.220699476019774,"min":21.93738491295836},"per_game_match_totals_all":{"GB2-01":{"draws":16,"losses":17,"wins":25},"GB2-04":{"draws":86,"losses":12,"wins":8},"GB2-05":{"draws":0,"losses":70,"wins":50},"GB2-06":{"draws":2,"losses":70,"wins":42},"GB2-07":{"draws":0,"losses":66,"wins":54},"GB2-08":{"draws":43,"losses":10,"wins":1}},"per_game_match_totals_tracks":{"medium":{"GB2-04":{"draws":45,"losses":8,"wins":5},"GB2-05":{"draws":0,"losses":32,"wins":28},"GB2-06":{"draws":2,"losses":38,"wins":18},"GB2-07":{"draws":0,"losses":30,"wins":32}},"none":{"GB2-01":{"draws":16,"losses":17,"wins":25},"GB2-04":{"draws":41,"losses":4,"wins":3},"GB2-05":{"draws":0,"losses":38,"wins":22},"GB2-06":{"draws":0,"losses":32,"wins":24},"GB2-07":{"draws":0,"losses":36,"wins":22},"GB2-08":{"draws":43,"losses":10,"wins":1}}},"per_game_raw_elo_tracks":{"medium":{"GB2-04":1485.8821345908264,"GB2-05":1504.0748772526317,"GB2-06":1381.5813863174303,"GB2-07":1454.3672812155583},"none":{"GB2-01":1477.0492603937407,"GB2-04":1490.2406649219877,"GB2-05":1306.4883081561472,"GB2-06":1400.355913354061,"GB2-07":1349.90531693581,"GB2-08":1439.4942097257222}},"per_game_tracks":{"medium":{"GB2-04":29.15567824497275,"GB2-05":43.06115710405442,"GB2-06":33.46194565997123,"GB2-07":39.242141470382364},"none":{"GB2-01":44.68186759149837,"GB2-04":33.243606728345505,"GB2-05":21.93738491295836,"GB2-06":38.65939289391045,"GB2-07":28.115764310136107,"GB2-08":26.304012940866215}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#f5f9ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":31.500074891654457,"none":30.941324060385096},"reasoning_agg":{"medium":{"max":43.06115710405442,"mean":31.500074891654457,"min":29.15567824497275},"none":{"max":44.68186759149837,"mean":30.941324060385096,"min":21.93738491295836}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"score_diagnostics":{"ceiling_score":44.68186759149837,"reasoning_variance":0.5587508312693608},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":43.06115710405442,"expected_score":35.57409190945893,"reliability_score":53.22184643391362,"uncertainty_avg":46.77815356608638,"uncertainty_penalty":4.074017017804472},"none":{"ceiling_score":44.68186759149837,"expected_score":30.792241605558164,"reliability_score":77.20291225409672,"uncertainty_avg":22.797087745903283,"uncertainty_penalty":-0.1490824548269316}}},{"codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":17},"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.13491350000000002,"mean":0.10247140625,"median":0.113468875,"min":0.061553,"recorded_attempt_count":17,"run_count":8,"total":0.8197712500000001},"none":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":33},"evidence_basis":"Provider-reported","failed_cell_count":9,"max":0.2156775,"mean":0.157461515625,"median":0.15705206249999998,"min":0.098579625,"recorded_attempt_count":33,"run_count":16,"total":2.51938425}},"codegen_cost_usd":{"admitted_cell_count":12,"cell_count":16,"cost_basis_counts":{"provider_reported":50},"evidence_basis":"Provider-reported","failed_cell_count":12,"max":0.2156775,"mean":0.12996646093750003,"median":0.12798825,"min":0.061553,"recorded_attempt_count":50,"run_count":24,"total":3.3391555},"codegen_latency_ms":{"attempt_count":50,"max_ms":1200477,"mean_ms":884695.875,"min_ms":390884,"run_count":24},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":17,"max_ms":1097898,"mean_ms":822157.625,"min_ms":490730,"run_count":8},"none":{"attempt_count":33,"max_ms":1200477,"mean_ms":915965.0,"min_ms":390884,"run_count":16}},"codegen_output_tokens":{"attempt_count":50,"output_max":131072,"output_mean":108502.5,"output_min":55627,"run_count":24},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":17,"output_max":131072,"output_mean":95066.75,"output_min":57337,"run_count":8},"none":{"attempt_count":33,"output_max":131072,"output_mean":115220.375,"output_min":55627,"run_count":16}},"display_name":"Nex N2 Pro","economics":{"medium":27.985882592823224,"none":36.96068238360197},"first_seen_at":null,"generation_metadata":{"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"nex-agi","provider_model":"nex-agi/nex-n2-pro","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":5,"evaluated_cells":8,"failed_game_aliases":["GB2-01","GB2-02","GB2-04"],"model_code_failure_rate":0.375,"model_code_failures":3,"repaired_admitted":5,"repaired_rate":0.625},"baseline":{"admitted_plugins":7,"evaluated_cells":16,"failed_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-05","GB2-06","GB2-07","GB2-08"],"model_code_failure_rate":0.5625,"model_code_failures":9,"repaired_admitted":7,"repaired_rate":0.4375}},"id":"nex-agi/nex-n2-pro","is_recent_addition":false,"last_measured_at":"2026-07-27T11:59:44Z","match_totals_all":{"draws":217,"losses":298,"wins":185},"match_totals_tracks":{"medium":{"draws":49,"losses":168,"wins":79},"none":{"draws":168,"losses":130,"wins":106}},"model_slug":"nex-agi-nex-n2-pro","overall":{"max":68.47656737578293,"mean":30.92202088844704,"min":3.452798895447958},"per_game_match_totals_all":{"GB2-02":{"draws":46,"losses":5,"wins":1},"GB2-03":{"draws":57,"losses":25,"wins":14},"GB2-04":{"draws":45,"losses":3,"wins":2},"GB2-05":{"draws":0,"losses":86,"wins":54},"GB2-06":{"draws":9,"losses":79,"wins":40},"GB2-07":{"draws":0,"losses":55,"wins":69},"GB2-08":{"draws":60,"losses":45,"wins":5}},"per_game_match_totals_tracks":{"medium":{"GB2-03":{"draws":30,"losses":12,"wins":8},"GB2-05":{"draws":0,"losses":44,"wins":20},"GB2-06":{"draws":7,"losses":39,"wins":20},"GB2-07":{"draws":0,"losses":35,"wins":27},"GB2-08":{"draws":12,"losses":38,"wins":4}},"none":{"GB2-02":{"draws":46,"losses":5,"wins":1},"GB2-03":{"draws":27,"losses":13,"wins":6},"GB2-04":{"draws":45,"losses":3,"wins":2},"GB2-05":{"draws":0,"losses":42,"wins":34},"GB2-06":{"draws":2,"losses":40,"wins":20},"GB2-07":{"draws":0,"losses":20,"wins":42},"GB2-08":{"draws":48,"losses":7,"wins":1}}},"per_game_raw_elo_tracks":{"medium":{"GB2-03":1486.0822555481582,"GB2-05":1360.9092359313067,"GB2-06":1362.877850832631,"GB2-07":1449.4234555848545,"GB2-08":1313.972577700416},"none":{"GB2-02":1466.422044691208,"GB2-03":1424.386156653482,"GB2-04":1491.333286691229,"GB2-05":1459.739093474812,"GB2-06":1338.9971736131567,"GB2-07":1657.169899748788,"GB2-08":1440.8610223975368}},"per_game_tracks":{"medium":{"GB2-03":40.05712610425944,"GB2-05":26.238020657975618,"GB2-06":31.529723961553977,"GB2-07":38.65174334487914,"GB2-08":3.452798895447958},"none":{"GB2-02":25.16068625041128,"GB2-03":33.02461357020887,"GB2-04":33.686693364975824,"GB2-05":40.915245999404725,"GB2-06":30.7973175132515,"GB2-07":68.47656737578293,"GB2-08":26.6636526111786}},"provider_color":"#111827","provider_company":"Nex AGI","provider_key":"nex-agi","provider_text_color":"#f8fafc","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":24.883359393292118,"none":36.96068238360196},"reasoning_agg":{"medium":{"max":40.05712610425944,"mean":24.883359393292118,"min":3.452798895447958},"none":{"max":68.47656737578293,"mean":36.96068238360196,"min":25.16068625041128}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"score_diagnostics":{"ceiling_score":68.47656737578293,"reasoning_variance":12.077322990309845},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":40.05712610425944,"expected_score":18.402338703169477,"reliability_score":52.80294089385333,"uncertainty_avg":47.19705910614667,"uncertainty_penalty":-6.481020690122641},"none":{"ceiling_score":68.47656737578293,"expected_score":36.405520787038895,"reliability_score":77.91830776035631,"uncertainty_avg":22.08169223964369,"uncertainty_penalty":-0.5551615965630674}}},{"codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":9,"cell_count":8,"cost_basis_counts":{"provider_reported":33},"evidence_basis":"Provider-reported","failed_cell_count":7,"max":0.039679950000000005,"mean":0.029276065625,"median":0.0306386,"min":0.01864685,"recorded_attempt_count":33,"run_count":16,"total":0.46841705},"medium":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":19},"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.0445032,"mean":0.03204184375,"median":0.0312573,"min":0.0200767,"recorded_attempt_count":19,"run_count":9,"total":0.2854256}},"codegen_cost_usd":{"admitted_cell_count":14,"cell_count":16,"cost_basis_counts":{"provider_reported":52},"evidence_basis":"Provider-reported","failed_cell_count":11,"max":0.0445032,"mean":0.030658954687500004,"median":0.0312573,"min":0.01864685,"recorded_attempt_count":52,"run_count":25,"total":0.75384265},"codegen_latency_ms":{"attempt_count":52,"max_ms":622714,"mean_ms":82027.44,"min_ms":23604,"run_count":25},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":33,"max_ms":622714,"mean_ms":92202.3125,"min_ms":23604,"run_count":16},"medium":{"attempt_count":19,"max_ms":124322,"mean_ms":63938.77777777778,"min_ms":25332,"run_count":9}},"codegen_output_tokens":{"attempt_count":52,"output_max":14193,"output_mean":7210.36,"output_min":2728,"run_count":25},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":33,"output_max":14193,"output_mean":7320.375,"output_min":2728,"run_count":16},"medium":{"attempt_count":19,"output_max":10495,"output_mean":7014.777777777777,"output_min":4525,"run_count":9}},"display_name":"Nemotron 3 Ultra 550B A55B","economics":{"all":38.777223136084984,"highest":30.52965355512906,"medium":33.72406167819707,"none":35.241132026567165},"first_seen_at":null,"generation_metadata":{"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"nvidia","provider_model":"nvidia/nemotron-3-ultra-550b-a55b","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":5,"evaluated_cells":9,"failed_game_aliases":["GB2-03","GB2-04","GB2-05"],"model_code_failure_rate":0.4444444444444444,"model_code_failures":4,"repaired_admitted":5,"repaired_rate":0.5555555555555556},"intensive":{"admitted_plugins":9,"evaluated_cells":16,"failed_game_aliases":["GB2-01","GB2-03","GB2-04","GB2-06","GB2-07"],"first_pass_admitted":2,"first_pass_rate":0.125,"model_code_failure_rate":0.4375,"model_code_failures":7,"repaired_admitted":7,"repaired_rate":0.4375}},"id":"nvidia/nemotron-3-ultra-550b-a55b","is_recent_addition":false,"last_measured_at":"2026-07-27T11:52:38Z","match_totals_all":{"draws":500,"losses":413,"wins":264},"match_totals_tracks":{"highest":{"draws":294,"losses":191,"wins":106},"medium":{"draws":112,"losses":110,"wins":76},"none":{"draws":94,"losses":112,"wins":82}},"model_slug":"nvidia-nemotron-3-ultra-550b-a55b","overall":{"max":59.81864880409941,"mean":29.420353974702792,"min":5.146710224123554},"per_game":{"GB2-01":31.194596093189162,"GB2-02":25.918855105037668,"GB2-04":24.703970098862882,"GB2-05":31.89087169341551,"GB2-06":44.47139940280178,"GB2-08":24.99822893746736},"per_game_all":{"GB2-01":44.55490838868735,"GB2-06":45.65282308923495,"GB2-08":26.12393793033264},"per_game_match_totals_all":{"GB2-01":{"draws":43,"losses":72,"wins":53},"GB2-02":{"draws":165,"losses":12,"wins":3},"GB2-03":{"draws":18,"losses":9,"wins":3},"GB2-04":{"draws":77,"losses":15,"wins":8},"GB2-05":{"draws":0,"losses":103,"wins":79},"GB2-06":{"draws":8,"losses":84,"wins":75},"GB2-07":{"draws":0,"losses":79,"wins":27},"GB2-08":{"draws":189,"losses":39,"wins":16}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":18,"losses":29,"wins":13},"GB2-02":{"draws":113,"losses":10,"wins":3},"GB2-04":{"draws":50,"losses":9,"wins":3},"GB2-05":{"draws":0,"losses":87,"wins":47},"GB2-06":{"draws":4,"losses":33,"wins":28},"GB2-08":{"draws":109,"losses":23,"wins":12}},"medium":{"GB2-01":{"draws":14,"losses":26,"wins":24},"GB2-02":{"draws":52,"losses":2,"wins":0},"GB2-06":{"draws":4,"losses":26,"wins":32},"GB2-07":{"draws":0,"losses":45,"wins":17},"GB2-08":{"draws":42,"losses":11,"wins":3}},"none":{"GB2-01":{"draws":11,"losses":17,"wins":16},"GB2-03":{"draws":18,"losses":9,"wins":3},"GB2-04":{"draws":27,"losses":6,"wins":5},"GB2-05":{"draws":0,"losses":16,"wins":32},"GB2-06":{"draws":0,"losses":25,"wins":15},"GB2-07":{"draws":0,"losses":34,"wins":10},"GB2-08":{"draws":38,"losses":5,"wins":1}}},"per_game_raw_elo_all":{"GB2-01":1484.3942513655263,"GB2-06":1460.3601837746094,"GB2-08":1444.0914155756254},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1392.986063334523,"GB2-02":1485.6612365441383,"GB2-04":1460.9657967166772,"GB2-05":1407.281846728603,"GB2-06":1460.076493018715,"GB2-08":1443.6062775081773},"medium":{"GB2-01":1508.9996053111847,"GB2-02":1479.6156043304468,"GB2-06":1555.945264596268,"GB2-07":1172.4066172061932,"GB2-08":1436.2781128307956},"none":{"GB2-01":1551.1970854508706,"GB2-03":1419.261890549445,"GB2-04":1495.9623564264125,"GB2-05":1544.427991149785,"GB2-06":1365.0587937088449,"GB2-07":1301.0437601099366,"GB2-08":1452.3898563879034}},"per_game_tracks":{"highest":{"GB2-01":31.194596093189162,"GB2-02":25.918855105037668,"GB2-04":24.703970098862882,"GB2-05":31.89087169341551,"GB2-06":44.47139940280178,"GB2-08":24.99822893746736},"medium":{"GB2-01":49.14708051635627,"GB2-02":28.554184291069387,"GB2-06":59.81864880409941,"GB2-07":5.146710224123554,"GB2-08":25.953684555336736},"none":{"GB2-01":53.32304855651662,"GB2-03":29.873191643532166,"GB2-04":33.00720768323213,"GB2-05":49.650421679977455,"GB2-06":32.66842106080365,"GB2-07":20.745733263714285,"GB2-08":27.41990029819383}},"provider_color":"#76B900","provider_company":"NVIDIA","provider_key":"nvidia","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":23.904597767588164,"medium":29.11533212995305,"none":35.241132026567165},"reasoning_agg":{"highest":{"max":31.89087169341551,"mean":23.904597767588164,"min":24.99822893746736},"medium":{"max":59.81864880409941,"mean":29.11533212995305,"min":5.146710224123554},"none":{"max":53.32304855651662,"mean":35.241132026567165,"min":20.745733263714285}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Reasoning disabled"},"score_diagnostics":{"ceiling_score":59.81864880409941,"expected_score":29.237756962658683,"reasoning_variance":11.336534258979,"reliability_score":68.41626100185452,"uncertainty_avg":31.58373899814548,"uncertainty_penalty":-0.18259701204410916},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":31.89087169341551,"expected_score":15.44381878662574,"reliability_score":56.643441208227195,"uncertainty_avg":43.356558791772805,"uncertainty_penalty":-8.460778980962424},"medium":{"ceiling_score":59.81864880409941,"expected_score":25.26834390566386,"reliability_score":79.41957418721539,"uncertainty_avg":20.580425812784608,"uncertainty_penalty":-3.8469882242891913},"none":{"ceiling_score":53.32304855651662,"expected_score":36.78035513435295,"reliability_score":66.18014599445937,"uncertainty_avg":33.81985400554064,"uncertainty_penalty":1.5392231077857872}}},{"codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":34},"evidence_basis":"Provider-reported","failed_cell_count":8,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":34,"run_count":15,"total":0.0},"none":{"admitted_cell_count":10,"cell_count":8,"cost_basis_counts":{"provider_reported":29},"evidence_basis":"Provider-reported","failed_cell_count":6,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":29,"run_count":16,"total":0.0}},"codegen_cost_usd":{"admitted_cell_count":17,"cell_count":16,"cost_basis_counts":{"provider_reported":63},"evidence_basis":"Provider-reported","failed_cell_count":14,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":63,"run_count":31,"total":0.0},"codegen_latency_ms":{"attempt_count":64,"max_ms":235183,"mean_ms":106145.67741935483,"min_ms":16415,"run_count":31},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":35,"max_ms":235183,"mean_ms":183971.06666666668,"min_ms":161500,"run_count":15},"none":{"attempt_count":29,"max_ms":62224,"mean_ms":33184.375,"min_ms":16415,"run_count":16}},"codegen_output_tokens":{"attempt_count":63,"output_max":52074,"output_mean":22315.225806451617,"output_min":1505,"run_count":31},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":34,"output_max":52074,"output_mean":40986.933333333334,"output_min":20000,"run_count":15},"none":{"attempt_count":29,"output_max":10355,"output_mean":4810.5,"output_min":1505,"run_count":16}},"display_name":"Ling 3.0 Flash","economics":{"medium":28.264678471970843,"none":29.144249871033185},"first_seen_at":null,"generation_metadata":{"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"inclusionai","provider_model":"inclusionai/ling-3.0-flash","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":7,"evaluated_cells":15,"failed_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-05","GB2-08"],"infra_excluded_game_aliases":["GB2-05"],"infra_failures_excluded":1,"model_code_failure_rate":0.5333333333333333,"model_code_failures":8,"repaired_admitted":7,"repaired_rate":0.4666666666666667},"baseline":{"admitted_plugins":10,"evaluated_cells":16,"failed_game_aliases":["GB2-02","GB2-04","GB2-05","GB2-07"],"first_pass_admitted":6,"first_pass_rate":0.375,"model_code_failure_rate":0.375,"model_code_failures":6,"repaired_admitted":4,"repaired_rate":0.25}},"id":"inclusionai/ling-3.0-flash","is_recent_addition":false,"last_measured_at":"2026-07-27T11:37:35Z","match_totals_all":{"draws":386,"losses":345,"wins":155},"match_totals_tracks":{"medium":{"draws":84,"losses":130,"wins":68},"none":{"draws":302,"losses":215,"wins":87}},"model_slug":"inclusionai-ling-3-0-flash","overall":{"max":44.131890322774105,"mean":27.827749194310456,"min":18.594475422927694},"per_game_match_totals_all":{"GB2-01":{"draws":49,"losses":75,"wins":40},"GB2-02":{"draws":93,"losses":7,"wins":2},"GB2-03":{"draws":38,"losses":41,"wins":17},"GB2-04":{"draws":91,"losses":9,"wins":2},"GB2-06":{"draws":4,"losses":145,"wins":55},"GB2-07":{"draws":0,"losses":45,"wins":35},"GB2-08":{"draws":111,"losses":23,"wins":4}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":14,"losses":22,"wins":4},"GB2-02":{"draws":33,"losses":5,"wins":2},"GB2-04":{"draws":36,"losses":5,"wins":1},"GB2-06":{"draws":1,"losses":53,"wins":26},"GB2-07":{"draws":0,"losses":45,"wins":35}},"none":{"GB2-01":{"draws":35,"losses":53,"wins":36},"GB2-02":{"draws":60,"losses":2,"wins":0},"GB2-03":{"draws":38,"losses":41,"wins":17},"GB2-04":{"draws":55,"losses":4,"wins":1},"GB2-06":{"draws":3,"losses":92,"wins":29},"GB2-08":{"draws":111,"losses":23,"wins":4}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1301.4844814069097,"GB2-02":1466.728730509414,"GB2-04":1450.768790271424,"GB2-06":1343.802645127367,"GB2-07":1473.4501921154751},"none":{"GB2-01":1471.1495141356838,"GB2-02":1472.8398095919308,"GB2-03":1394.10982893775,"GB2-04":1477.6032838196008,"GB2-06":1247.794253674446,"GB2-08":1420.8052557973037}},"per_game_tracks":{"medium":{"GB2-01":20.552351615993096,"GB2-02":23.435814126241773,"GB2-04":24.61236711374963,"GB2-06":29.824967923441967,"GB2-07":42.89789158042775},"none":{"GB2-01":44.131890322774105,"GB2-02":27.7811694206549,"GB2-03":28.098050691260877,"GB2-04":31.907085942540736,"GB2-06":18.594475422927694,"GB2-08":24.35282742604081}},"provider_color":"#1677FF","provider_company":"InclusionAI","provider_key":"inclusionai","provider_text_color":"#f8fbff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":30.053333230294534,"none":25.602165158326375},"reasoning_agg":{"medium":{"max":42.89789158042775,"mean":30.053333230294534,"min":29.824967923441967},"none":{"max":44.131890322774105,"mean":25.602165158326375,"min":18.594475422927694}},"reasoning_labels":{"highest":"Setting not tested","medium":"Enabled","none":"None"},"score_diagnostics":{"ceiling_score":44.131890322774105,"reasoning_variance":4.451168071968159},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":42.89789158042775,"expected_score":14.149238132730662,"reliability_score":66.0306382112971,"uncertainty_avg":33.9693617887029,"uncertainty_penalty":-15.904095097563872},"none":{"ceiling_score":44.131890322774105,"expected_score":17.929667770734586,"reliability_score":79.69596267905763,"uncertainty_avg":20.304037320942378,"uncertainty_penalty":-7.67249738759179}}},{"codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":15},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":15,"run_count":8,"total":0.0},"none":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":29},"evidence_basis":"Provider-reported","failed_cell_count":11,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":29,"run_count":16,"total":0.0}},"codegen_cost_usd":{"admitted_cell_count":11,"cell_count":16,"cost_basis_counts":{"provider_reported":44},"evidence_basis":"Provider-reported","failed_cell_count":13,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":44,"run_count":24,"total":0.0},"codegen_latency_ms":{"attempt_count":44,"max_ms":905283,"mean_ms":194108.25,"min_ms":21975,"run_count":24},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":15,"max_ms":905283,"mean_ms":509118.375,"min_ms":288605,"run_count":8},"none":{"attempt_count":29,"max_ms":62079,"mean_ms":36603.1875,"min_ms":21975,"run_count":16}},"codegen_output_tokens":{"attempt_count":44,"output_max":52275,"output_mean":12258.958333333334,"output_min":1733,"run_count":24},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":15,"output_max":52275,"output_mean":30105.875,"output_min":9014,"run_count":8},"none":{"attempt_count":29,"output_max":6330,"output_mean":3335.5,"output_min":1733,"run_count":16}},"display_name":"North Mini Code","economics":{"medium":32.263585884549634,"none":27.785229416209372},"first_seen_at":null,"generation_metadata":{"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"other","provider_model":"cohere/north-mini-code","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":6,"evaluated_cells":8,"failed_game_aliases":["GB2-01","GB2-02"],"first_pass_admitted":3,"first_pass_rate":0.375,"model_code_failure_rate":0.25,"model_code_failures":2,"repaired_admitted":3,"repaired_rate":0.375},"baseline":{"admitted_plugins":5,"evaluated_cells":16,"failed_game_aliases":["GB2-02","GB2-03","GB2-04","GB2-05","GB2-06","GB2-08"],"first_pass_admitted":3,"first_pass_rate":0.1875,"model_code_failure_rate":0.6875,"model_code_failures":11,"repaired_admitted":2,"repaired_rate":0.125}},"id":"cohere/north-mini-code","is_recent_addition":false,"last_measured_at":"2026-07-27T11:52:47Z","match_totals_all":{"draws":220,"losses":296,"wins":158},"match_totals_tracks":{"medium":{"draws":110,"losses":142,"wins":98},"none":{"draws":110,"losses":154,"wins":60}},"model_slug":"cohere-north-mini-code","overall":{"max":42.997436567986185,"mean":25.24402606113204,"min":19.858838132294075},"per_game_match_totals_all":{"GB2-01":{"draws":61,"losses":55,"wins":16},"GB2-03":{"draws":23,"losses":19,"wins":8},"GB2-04":{"draws":35,"losses":7,"wins":4},"GB2-05":{"draws":0,"losses":31,"wins":37},"GB2-06":{"draws":1,"losses":39,"wins":18},"GB2-07":{"draws":0,"losses":123,"wins":71},"GB2-08":{"draws":100,"losses":22,"wins":4}},"per_game_match_totals_tracks":{"medium":{"GB2-03":{"draws":23,"losses":19,"wins":8},"GB2-04":{"draws":35,"losses":7,"wins":4},"GB2-05":{"draws":0,"losses":31,"wins":37},"GB2-06":{"draws":1,"losses":39,"wins":18},"GB2-07":{"draws":0,"losses":33,"wins":31},"GB2-08":{"draws":51,"losses":13,"wins":0}},"none":{"GB2-01":{"draws":61,"losses":55,"wins":16},"GB2-07":{"draws":0,"losses":90,"wins":40},"GB2-08":{"draws":49,"losses":9,"wins":4}}},"per_game_raw_elo_tracks":{"medium":{"GB2-03":1435.7925093127453,"GB2-04":1483.3259674335122,"GB2-05":1469.1507038419907,"GB2-06":1379.3228938160337,"GB2-07":1481.7615272516564,"GB2-08":1413.5850826874466},"none":{"GB2-01":1342.0779950278898,"GB2-07":1339.7266305359383,"GB2-08":1450.883258777918}},"per_game_tracks":{"medium":{"GB2-03":31.48623719869417,"GB2-04":26.71086962365695,"GB2-05":39.36830859417666,"GB2-06":33.15982519048976,"GB2-07":42.997436567986185,"GB2-08":19.858838132294075},"none":{"GB2-01":27.58246377184411,"GB2-07":27.1563438776522,"GB2-08":28.6168805991318}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":30.024649796219794,"none":20.46340232604428},"reasoning_agg":{"medium":{"max":42.997436567986185,"mean":30.024649796219794,"min":19.858838132294075},"none":{"max":27.58246377184411,"mean":20.46340232604428,"min":27.1563438776522}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"score_diagnostics":{"ceiling_score":42.997436567986185,"reasoning_variance":9.561247470175513},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":42.997436567986185,"expected_score":27.7024129672262,"reliability_score":51.55814342869858,"uncertainty_avg":48.44185657130142,"uncertainty_penalty":-2.3222368289935957},"none":{"ceiling_score":27.58246377184411,"expected_score":16.726272761678167,"reliability_score":81.86657650333532,"uncertainty_avg":18.13342349666468,"uncertainty_penalty":-3.737129564366114}}},{"codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":18},"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.0422995,"mean":0.0264053125,"median":0.022682375,"min":0.01946775,"recorded_attempt_count":18,"run_count":8,"total":0.2112425},"medium":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":16},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0149315,"mean":0.00915140625,"median":0.00943475,"min":0.00402875,"recorded_attempt_count":16,"run_count":8,"total":0.07321125}},"codegen_cost_usd":{"admitted_cell_count":11,"cell_count":16,"cost_basis_counts":{"provider_reported":34},"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.0422995,"mean":0.017778359375,"median":0.017199625,"min":0.00402875,"recorded_attempt_count":34,"run_count":16,"total":0.28445375},"codegen_latency_ms":{"attempt_count":34,"max_ms":98448,"mean_ms":41366.3125,"min_ms":14244,"run_count":16},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":18,"max_ms":98448,"mean_ms":60993.75,"min_ms":43206,"run_count":8},"medium":{"attempt_count":16,"max_ms":27929,"mean_ms":21738.875,"min_ms":14244,"run_count":8}},"codegen_output_tokens":{"attempt_count":34,"output_max":22966,"output_mean":8901.4375,"output_min":1329,"run_count":16},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":18,"output_max":22966,"output_mean":14376.25,"output_min":9966,"run_count":8},"medium":{"attempt_count":16,"output_max":5938,"output_mean":3426.625,"output_min":1329,"run_count":8}},"display_name":"Gemini 3.1 Flash Lite","economics":{"all":23.860408533379566,"highest":26.57119754825589,"medium":29.652763827122893,"none":23.388684213793677},"first_seen_at":null,"generation_metadata":{"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"google","provider_model":"google/gemini-3.1-flash-lite","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":6,"evaluated_cells":8,"failed_game_aliases":["GB2-02","GB2-03"],"first_pass_admitted":2,"first_pass_rate":0.25,"model_code_failure_rate":0.25,"model_code_failures":2,"repaired_admitted":4,"repaired_rate":0.5},"intensive":{"admitted_plugins":5,"evaluated_cells":8,"failed_game_aliases":["GB2-01","GB2-02","GB2-03"],"model_code_failure_rate":0.375,"model_code_failures":3,"repaired_admitted":5,"repaired_rate":0.625}},"id":"google/gemini-3.1-flash-lite","is_recent_addition":false,"last_measured_at":"2026-07-27T11:53:48Z","match_totals_all":{"draws":252,"losses":430,"wins":209},"match_totals_tracks":{"highest":{"draws":104,"losses":169,"wins":62},"medium":{"draws":90,"losses":154,"wins":100},"none":{"draws":58,"losses":107,"wins":47}},"model_slug":"google-gemini-3-1-flash-lite","overall":{"max":42.33396509337835,"mean":24.869732355730434,"min":0.0},"per_game":{"GB2-04":26.144079418299455,"GB2-05":15.144663326584237,"GB2-06":29.658776025462103,"GB2-07":37.38497422902105,"GB2-08":24.52349474191262},"per_game_all":{"GB2-05":19.99317015851531,"GB2-06":37.33863600184412,"GB2-07":14.249419439779258},"per_game_match_totals_all":{"GB2-01":{"draws":52,"losses":33,"wins":19},"GB2-02":{"draws":34,"losses":3,"wins":1},"GB2-04":{"draws":71,"losses":8,"wins":7},"GB2-05":{"draws":0,"losses":121,"wins":53},"GB2-06":{"draws":1,"losses":98,"wins":64},"GB2-07":{"draws":0,"losses":134,"wins":38},"GB2-08":{"draws":94,"losses":33,"wins":27}},"per_game_match_totals_tracks":{"highest":{"GB2-04":{"draws":35,"losses":6,"wins":3},"GB2-05":{"draws":0,"losses":54,"wins":10},"GB2-06":{"draws":0,"losses":50,"wins":21},"GB2-07":{"draws":0,"losses":50,"wins":24},"GB2-08":{"draws":69,"losses":9,"wins":4}},"medium":{"GB2-01":{"draws":29,"losses":16,"wins":13},"GB2-04":{"draws":36,"losses":2,"wins":4},"GB2-05":{"draws":0,"losses":37,"wins":27},"GB2-06":{"draws":0,"losses":29,"wins":23},"GB2-07":{"draws":0,"losses":46,"wins":10},"GB2-08":{"draws":25,"losses":24,"wins":23}},"none":{"GB2-01":{"draws":23,"losses":17,"wins":6},"GB2-02":{"draws":34,"losses":3,"wins":1},"GB2-05":{"draws":0,"losses":30,"wins":16},"GB2-06":{"draws":1,"losses":19,"wins":20},"GB2-07":{"draws":0,"losses":38,"wins":4}}},"per_game_raw_elo_all":{"GB2-05":1298.488574563872,"GB2-06":1398.7102942773993,"GB2-07":1251.3174617124973},"per_game_raw_elo_tracks":{"highest":{"GB2-04":1481.8316556844986,"GB2-05":1268.9210216510749,"GB2-06":1346.3039086212673,"GB2-07":1433.6870639522708,"GB2-08":1435.9046812811634},"medium":{"GB2-01":1458.4305805417964,"GB2-04":1497.0294371743323,"GB2-05":1321.2599404656255,"GB2-06":1429.7879988349669,"GB2-07":1176.6504298057089,"GB2-08":1457.7343014406704},"none":{"GB2-01":1340.1564195017108,"GB2-02":1495.250360698582,"GB2-05":1305.284761574915,"GB2-06":1420.038975375964,"GB2-07":1143.6148913795123}},"per_game_tracks":{"highest":{"GB2-04":26.144079418299455,"GB2-05":15.144663326584237,"GB2-06":29.658776025462103,"GB2-07":37.38497422902105,"GB2-08":24.52349474191262},"medium":{"GB2-01":42.26595649843005,"GB2-04":33.82771565073253,"GB2-05":23.893026239049423,"GB2-06":42.33396509337835,"GB2-07":5.363284090316728,"GB2-08":30.232635390830257},"none":{"GB2-01":26.105376543268523,"GB2-02":29.873056729095698,"GB2-05":20.941820909912263,"GB2-06":40.02316688669191,"GB2-07":0.0}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#f5f9ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":23.625506750070084,"medium":27.59500610332754,"none":23.388684213793677},"reasoning_agg":{"highest":{"max":37.38497422902105,"mean":23.625506750070084,"min":15.144663326584237},"medium":{"max":42.33396509337835,"mean":27.59500610332754,"min":5.363284090316728},"none":{"max":40.02316688669191,"mean":23.388684213793677,"min":0.0}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Reasoning disabled"},"score_diagnostics":{"ceiling_score":42.33396509337835,"expected_score":14.619787033518483,"reasoning_variance":4.206321889533861,"reliability_score":68.6127012626543,"uncertainty_avg":31.3872987373457,"uncertainty_penalty":-10.249945322211952},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":37.38497422902105,"expected_score":10.752849953067443,"reliability_score":56.78818927385296,"uncertainty_avg":43.21181072614704,"uncertainty_penalty":-12.87265679700264},"medium":{"ceiling_score":42.33396509337835,"expected_score":24.469508336077027,"reliability_score":77.61856977050326,"uncertainty_avg":22.381430229496747,"uncertainty_penalty":-3.1254977672505113},"none":{"ceiling_score":40.02316688669191,"expected_score":18.029078629297835,"reliability_score":67.6969530977913,"uncertainty_avg":32.3030469022087,"uncertainty_penalty":-5.359605584495842}}},{"codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":4,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.33185775,"mean":0.18266821875,"median":0.16804049999999998,"min":0.08751,"recorded_attempt_count":13,"run_count":9,"total":1.7932035000000002},"none":{"admitted_cell_count":4,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.06200699999999999,"mean":0.0429946875,"median":0.0423105,"min":0.0223935,"recorded_attempt_count":14,"run_count":8,"total":0.34395749999999997}},"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":16,"cost_basis_counts":{"provider_reported":27},"evidence_basis":"Provider-reported","failed_cell_count":9,"max":0.33185775,"mean":0.112831453125,"median":0.0747585,"min":0.0223935,"recorded_attempt_count":27,"run_count":17,"total":2.137161},"codegen_latency_ms":{"attempt_count":27,"max_ms":776640,"mean_ms":204801.0588235294,"min_ms":28440,"run_count":17},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":13,"max_ms":776640,"mean_ms":337673.77777777775,"min_ms":132587,"run_count":9},"none":{"attempt_count":14,"max_ms":130711,"mean_ms":55319.25,"min_ms":28440,"run_count":8}},"codegen_output_tokens":{"attempt_count":27,"output_max":52664,"output_mean":14286.941176470587,"output_min":1452,"run_count":17},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":13,"output_max":52664,"output_mean":24216.444444444445,"output_min":10169,"run_count":9},"none":{"attempt_count":14,"output_max":5014,"output_mean":3116.25,"output_min":1452,"run_count":8}},"display_name":"Mistral Medium 3.5","economics":{"highest":21.2286991885296,"none":32.10501667536629},"first_seen_at":null,"generation_metadata":{"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"mistral","provider_model":"mistralai/mistral-medium-3-5","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"baseline":{"admitted_plugins":4,"evaluated_cells":8,"failed_game_aliases":["GB2-02","GB2-03","GB2-04","GB2-07"],"first_pass_admitted":2,"first_pass_rate":0.25,"model_code_failure_rate":0.5,"model_code_failures":4,"repaired_admitted":2,"repaired_rate":0.25},"intensive":{"admitted_plugins":4,"evaluated_cells":9,"failed_game_aliases":["GB2-02","GB2-03","GB2-04","GB2-08"],"first_pass_admitted":2,"first_pass_rate":0.2222222222222222,"model_code_failure_rate":0.5555555555555556,"model_code_failures":5,"repaired_admitted":2,"repaired_rate":0.2222222222222222}},"id":"mistralai/mistral-medium-3-5","is_recent_addition":false,"last_measured_at":"2026-07-27T11:52:31Z","match_totals_all":{"draws":77,"losses":308,"wins":142},"match_totals_tracks":{"highest":{"draws":19,"losses":195,"wins":64},"none":{"draws":58,"losses":113,"wins":78}},"model_slug":"mistralai-mistral-medium-3-5","overall":{"max":38.70088877553203,"mean":22.165076869476923,"min":14.82966031579288},"per_game":{"GB2-01":24.74431399881591,"GB2-05":16.976547721664623,"GB2-06":28.364274717844992,"GB2-07":14.82966031579288},"per_game_match_totals_all":{"GB2-01":{"draws":25,"losses":74,"wins":32},"GB2-05":{"draws":0,"losses":93,"wins":53},"GB2-06":{"draws":5,"losses":77,"wins":46},"GB2-07":{"draws":0,"losses":59,"wins":11},"GB2-08":{"draws":47,"losses":5,"wins":0}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":19,"losses":37,"wins":14},"GB2-05":{"draws":0,"losses":54,"wins":16},"GB2-06":{"draws":0,"losses":45,"wins":23},"GB2-07":{"draws":0,"losses":59,"wins":11}},"none":{"GB2-01":{"draws":6,"losses":37,"wins":18},"GB2-05":{"draws":0,"losses":39,"wins":37},"GB2-06":{"draws":5,"losses":32,"wins":23},"GB2-08":{"draws":47,"losses":5,"wins":0}}},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1338.1622966328277,"GB2-05":1280.5829410962074,"GB2-06":1338.0261125347924,"GB2-07":1262.9714053829541},"none":{"GB2-01":1393.6204375879504,"GB2-05":1441.2006518851858,"GB2-06":1331.884389148848,"GB2-08":1438.2888976809872}},"per_game_tracks":{"highest":{"GB2-01":24.74431399881591,"GB2-05":16.976547721664623,"GB2-06":28.364274717844992,"GB2-07":14.82966031579288},"none":{"GB2-01":34.02186953365919,"GB2-05":38.70088877553203,"GB2-06":29.736210534597397,"GB2-08":25.961097857676517}},"provider_color":"#FF7000","provider_company":"Mistral","provider_key":"mistral","provider_text_color":"#fff8f3","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":17.33316030497761,"none":26.996993433976236},"reasoning_agg":{"highest":{"max":28.364274717844992,"mean":17.33316030497761,"min":14.82966031579288},"none":{"max":38.70088877553203,"mean":26.996993433976236,"min":25.961097857676517}},"reasoning_labels":{"highest":"High","medium":"Setting not tested","none":"None"},"score_diagnostics":{"ceiling_score":38.70088877553203,"reasoning_variance":9.663833128998625},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":28.364274717844992,"expected_score":2.210633662080387,"reliability_score":59.9575543016399,"uncertainty_avg":40.0424456983601,"uncertainty_penalty":-15.122526642897224},"none":{"ceiling_score":38.70088877553203,"expected_score":23.628299783526366,"reliability_score":80.45523158232332,"uncertainty_avg":19.544768417676682,"uncertainty_penalty":-3.3686936504498703}}}],"public_release_id":"gb2-20260727-b63faa64fdbb","results_cut_id":"gb2-20260727-b63faa64fdbb","snapshot_id":"20260727_140229","suite_line_id":"gamebench2","suite_version":"2-known8-r3","version_display":"2026-07-27 14:02 UTC","versus_totals_all":{"claude-fable-5":{"claude-fable-5":{"draws":2,"losses":5,"wins":5},"claude-opus-4-5":{"draws":3,"losses":2,"wins":19},"claude-opus-4-8":{"draws":2,"losses":13,"wins":15},"claude-opus-5":{"draws":19,"losses":30,"wins":33},"claude-sonnet-5":{"draws":6,"losses":0,"wins":16},"deepseek/deepseek-v4-flash":{"draws":2,"losses":2,"wins":12},"deepseek/deepseek-v4-pro":{"draws":1,"losses":0,"wins":11},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":4},"google/gemini-3.5-flash":{"draws":5,"losses":9,"wins":16},"google/gemini-3.6-flash":{"draws":2,"losses":3,"wins":3},"google/gemma-4-31b-it":{"draws":1,"losses":1,"wins":2},"gpt-4.1":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":2,"losses":1,"wins":17},"gpt-5.4":{"draws":6,"losses":14,"wins":16},"gpt-5.4-mini":{"draws":7,"losses":6,"wins":19},"gpt-5.4-nano":{"draws":7,"losses":10,"wins":45},"gpt-5.5":{"draws":7,"losses":13,"wins":12},"gpt-5.6-luna":{"draws":2,"losses":2,"wins":16},"gpt-5.6-sol":{"draws":8,"losses":14,"wins":26},"gpt-5.6-terra":{"draws":5,"losses":4,"wins":25},"meituan/longcat-2.0":{"draws":0,"losses":1,"wins":1},"minimax/minimax-m3":{"draws":1,"losses":0,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":8},"moonshotai/kimi-k3":{"draws":12,"losses":7,"wins":41},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":0,"wins":2},"o3":{"draws":0,"losses":1,"wins":15},"openai/gpt-oss-120b":{"draws":1,"losses":0,"wins":7},"poolside/laguna-s-2.1":{"draws":0,"losses":4,"wins":2},"qwen/qwen3.7-max":{"draws":1,"losses":2,"wins":7},"qwen/qwen3.7-plus":{"draws":1,"losses":0,"wins":7},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":10},"tencent/hy3-preview":{"draws":1,"losses":5,"wins":6},"thinkingmachines/inkling":{"draws":0,"losses":0,"wins":2},"x-ai/grok-4.5":{"draws":15,"losses":23,"wins":50},"x-ai/grok-build-0.1":{"draws":0,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":2,"losses":0,"wins":12},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":16},"z-ai/glm-5.2":{"draws":1,"losses":8,"wins":33}},"claude-opus-4-5":{"claude-fable-5":{"draws":1,"losses":3,"wins":0},"claude-opus-4-5":{"draws":10,"losses":2,"wins":6},"claude-opus-4-8":{"draws":0,"losses":4,"wins":4},"claude-opus-5":{"draws":3,"losses":14,"wins":1},"claude-sonnet-5":{"draws":4,"losses":2,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":6},"deepseek/deepseek-v4-flash":{"draws":11,"losses":1,"wins":6},"deepseek/deepseek-v4-pro":{"draws":2,"losses":5,"wins":5},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":0},"google/gemini-3.5-flash":{"draws":2,"losses":0,"wins":0},"google/gemini-3.5-flash-lite":{"draws":0,"losses":2,"wins":0},"google/gemini-3.6-flash":{"draws":0,"losses":1,"wins":1},"google/gemma-4-31b-it":{"draws":2,"losses":2,"wins":2},"gpt-5.4":{"draws":5,"losses":5,"wins":8},"gpt-5.4-mini":{"draws":12,"losses":4,"wins":14},"gpt-5.4-nano":{"draws":13,"losses":9,"wins":14},"gpt-5.5":{"draws":7,"losses":3,"wins":2},"gpt-5.6-luna":{"draws":8,"losses":1,"wins":5},"gpt-5.6-sol":{"draws":4,"losses":9,"wins":3},"gpt-5.6-terra":{"draws":9,"losses":5,"wins":6},"meituan/longcat-2.0":{"draws":4,"losses":1,"wins":3},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":2},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":7,"losses":17,"wins":4},"nex-agi/nex-n2-pro":{"draws":4,"losses":3,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":3,"wins":4},"o3":{"draws":2,"losses":3,"wins":5},"openai/gpt-oss-120b":{"draws":4,"losses":0,"wins":4},"qwen/qwen3.7-max":{"draws":1,"losses":3,"wins":4},"qwen/qwen3.7-plus":{"draws":4,"losses":0,"wins":4},"stepfun/step-3.7-flash":{"draws":4,"losses":1,"wins":1},"tencent/hy3-preview":{"draws":2,"losses":3,"wins":7},"thinkingmachines/inkling":{"draws":2,"losses":2,"wins":2},"x-ai/grok-4.5":{"draws":8,"losses":14,"wins":10},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":11,"losses":6,"wins":9},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":7,"wins":3},"z-ai/glm-5.2":{"draws":2,"losses":6,"wins":12}},"claude-opus-4-8":{"claude-fable-5":{"draws":2,"losses":15,"wins":13},"claude-opus-4-5":{"draws":3,"losses":7,"wins":22},"claude-opus-4-8":{"draws":4,"losses":6,"wins":6},"claude-opus-5":{"draws":10,"losses":20,"wins":12},"claude-sonnet-5":{"draws":13,"losses":12,"wins":21},"cohere/north-mini-code":{"draws":3,"losses":2,"wins":5},"deepseek/deepseek-v4-flash":{"draws":11,"losses":9,"wins":26},"deepseek/deepseek-v4-pro":{"draws":9,"losses":8,"wins":13},"google/gemini-3.1-flash-lite":{"draws":7,"losses":3,"wins":14},"google/gemini-3.5-flash":{"draws":7,"losses":9,"wins":4},"google/gemini-3.5-flash-lite":{"draws":1,"losses":1,"wins":6},"google/gemini-3.6-flash":{"draws":2,"losses":2,"wins":0},"google/gemma-4-31b-it":{"draws":6,"losses":0,"wins":4},"gpt-4.1":{"draws":1,"losses":2,"wins":7},"gpt-5":{"draws":7,"losses":4,"wins":17},"gpt-5.4":{"draws":6,"losses":18,"wins":16},"gpt-5.4-mini":{"draws":22,"losses":18,"wins":32},"gpt-5.4-nano":{"draws":20,"losses":20,"wins":42},"gpt-5.5":{"draws":8,"losses":21,"wins":9},"gpt-5.6-luna":{"draws":10,"losses":14,"wins":16},"gpt-5.6-sol":{"draws":8,"losses":21,"wins":11},"gpt-5.6-terra":{"draws":14,"losses":8,"wins":14},"meituan/longcat-2.0":{"draws":2,"losses":0,"wins":0},"minimax/minimax-m3":{"draws":6,"losses":0,"wins":8},"mistralai/mistral-medium-3-5":{"draws":0,"losses":2,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":3,"wins":3},"moonshotai/kimi-k3":{"draws":21,"losses":28,"wins":25},"nex-agi/nex-n2-pro":{"draws":10,"losses":2,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":8,"wins":15},"o3":{"draws":5,"losses":7,"wins":14},"openai/gpt-oss-120b":{"draws":8,"losses":5,"wins":7},"poolside/laguna-s-2.1":{"draws":0,"losses":1,"wins":5},"qwen/qwen3.7-max":{"draws":2,"losses":7,"wins":11},"qwen/qwen3.7-plus":{"draws":4,"losses":5,"wins":15},"stepfun/step-3.7-flash":{"draws":0,"losses":4,"wins":4},"tencent/hy3-preview":{"draws":3,"losses":4,"wins":11},"thinkingmachines/inkling":{"draws":0,"losses":3,"wins":7},"x-ai/grok-4.5":{"draws":18,"losses":37,"wins":29},"x-ai/grok-build-0.1":{"draws":5,"losses":5,"wins":4},"xiaomi/mimo-v2.5":{"draws":17,"losses":3,"wins":24},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":7,"wins":15},"z-ai/glm-5.2":{"draws":23,"losses":23,"wins":34}},"claude-opus-5":{"claude-fable-5":{"draws":19,"losses":33,"wins":30},"claude-opus-4-5":{"draws":16,"losses":14,"wins":100},"claude-opus-4-8":{"draws":10,"losses":12,"wins":20},"claude-opus-5":{"draws":44,"losses":160,"wins":160},"claude-sonnet-5":{"draws":13,"losses":5,"wins":44},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":8},"deepseek/deepseek-v4-flash":{"draws":3,"losses":0,"wins":1},"deepseek/deepseek-v4-pro":{"draws":1,"losses":1,"wins":14},"google/gemini-3.1-flash-lite":{"draws":0,"losses":1,"wins":11},"google/gemini-3.5-flash":{"draws":2,"losses":9,"wins":23},"google/gemini-3.5-flash-lite":{"draws":9,"losses":5,"wins":24},"google/gemini-3.6-flash":{"draws":8,"losses":23,"wins":49},"gpt-4.1":{"draws":6,"losses":0,"wins":18},"gpt-5":{"draws":3,"losses":1,"wins":10},"gpt-5.4":{"draws":10,"losses":26,"wins":34},"gpt-5.4-mini":{"draws":3,"losses":6,"wins":31},"gpt-5.4-nano":{"draws":9,"losses":12,"wins":43},"gpt-5.5":{"draws":7,"losses":19,"wins":26},"gpt-5.6-luna":{"draws":1,"losses":4,"wins":13},"gpt-5.6-sol":{"draws":16,"losses":18,"wins":40},"gpt-5.6-terra":{"draws":16,"losses":8,"wins":26},"inclusionai/ling-3.0-flash":{"draws":5,"losses":0,"wins":5},"meituan/longcat-2.0":{"draws":4,"losses":6,"wins":14},"minimax/minimax-m3":{"draws":0,"losses":1,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":1,"wins":8},"moonshotai/kimi-k3":{"draws":22,"losses":14,"wins":70},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":0,"wins":4},"o3":{"draws":0,"losses":0,"wins":22},"poolside/laguna-s-2.1":{"draws":2,"losses":2,"wins":30},"qwen/qwen3.7-max":{"draws":0,"losses":5,"wins":17},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":2},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":1,"losses":2,"wins":7},"thinkingmachines/inkling":{"draws":1,"losses":3,"wins":30},"x-ai/grok-4.5":{"draws":25,"losses":39,"wins":130},"x-ai/grok-build-0.1":{"draws":4,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":3,"losses":1,"wins":6},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":1,"wins":11},"z-ai/glm-5.2":{"draws":14,"losses":10,"wins":58}},"claude-sonnet-5":{"claude-fable-5":{"draws":6,"losses":16,"wins":0},"claude-opus-4-5":{"draws":20,"losses":14,"wins":16},"claude-opus-4-8":{"draws":13,"losses":21,"wins":12},"claude-opus-5":{"draws":13,"losses":44,"wins":5},"claude-sonnet-5":{"draws":8,"losses":10,"wins":10},"cohere/north-mini-code":{"draws":3,"losses":2,"wins":13},"deepseek/deepseek-v4-flash":{"draws":22,"losses":12,"wins":22},"deepseek/deepseek-v4-pro":{"draws":9,"losses":6,"wins":7},"google/gemini-3.1-flash-lite":{"draws":7,"losses":3,"wins":12},"google/gemini-3.5-flash":{"draws":8,"losses":10,"wins":6},"google/gemini-3.5-flash-lite":{"draws":4,"losses":1,"wins":9},"google/gemini-3.6-flash":{"draws":5,"losses":2,"wins":1},"google/gemma-4-31b-it":{"draws":6,"losses":2,"wins":6},"gpt-4.1":{"draws":5,"losses":1,"wins":6},"gpt-5":{"draws":19,"losses":17,"wins":12},"gpt-5.4":{"draws":12,"losses":18,"wins":6},"gpt-5.4-mini":{"draws":27,"losses":28,"wins":33},"gpt-5.4-nano":{"draws":33,"losses":18,"wins":25},"gpt-5.5":{"draws":12,"losses":12,"wins":8},"gpt-5.6-luna":{"draws":11,"losses":12,"wins":7},"gpt-5.6-sol":{"draws":6,"losses":28,"wins":8},"gpt-5.6-terra":{"draws":11,"losses":13,"wins":16},"inclusionai/ling-3.0-flash":{"draws":2,"losses":0,"wins":4},"meituan/longcat-2.0":{"draws":4,"losses":0,"wins":6},"minimax/minimax-m3":{"draws":8,"losses":1,"wins":3},"mistralai/mistral-medium-3-5":{"draws":2,"losses":4,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":1,"wins":4},"moonshotai/kimi-k3":{"draws":17,"losses":22,"wins":11},"nex-agi/nex-n2-pro":{"draws":4,"losses":4,"wins":14},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":25,"losses":9,"wins":14},"o3":{"draws":3,"losses":13,"wins":12},"openai/gpt-oss-120b":{"draws":4,"losses":6,"wins":12},"poolside/laguna-s-2.1":{"draws":3,"losses":0,"wins":1},"qwen/qwen3.7-max":{"draws":5,"losses":4,"wins":7},"qwen/qwen3.7-plus":{"draws":10,"losses":3,"wins":5},"stepfun/step-3.7-flash":{"draws":4,"losses":1,"wins":11},"tencent/hy3-preview":{"draws":7,"losses":7,"wins":10},"thinkingmachines/inkling":{"draws":4,"losses":1,"wins":3},"x-ai/grok-4.5":{"draws":23,"losses":34,"wins":15},"x-ai/grok-build-0.1":{"draws":1,"losses":1,"wins":10},"xiaomi/mimo-v2.5":{"draws":35,"losses":13,"wins":20},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":1,"wins":7},"z-ai/glm-5.2":{"draws":37,"losses":34,"wins":33}},"cohere/north-mini-code":{"claude-opus-4-5":{"draws":7,"losses":9,"wins":2},"claude-opus-4-8":{"draws":3,"losses":5,"wins":2},"claude-opus-5":{"draws":2,"losses":8,"wins":2},"claude-sonnet-5":{"draws":3,"losses":13,"wins":2},"cohere/north-mini-code":{"draws":2,"losses":3,"wins":3},"deepseek/deepseek-v4-flash":{"draws":14,"losses":9,"wins":11},"deepseek/deepseek-v4-pro":{"draws":4,"losses":6,"wins":0},"google/gemini-3.1-flash-lite":{"draws":0,"losses":10,"wins":8},"google/gemini-3.5-flash":{"draws":3,"losses":4,"wins":1},"google/gemini-3.5-flash-lite":{"draws":2,"losses":2,"wins":0},"google/gemini-3.6-flash":{"draws":2,"losses":2,"wins":2},"google/gemma-4-31b-it":{"draws":1,"losses":6,"wins":5},"gpt-4.1":{"draws":1,"losses":3,"wins":0},"gpt-5":{"draws":5,"losses":12,"wins":1},"gpt-5.4":{"draws":7,"losses":10,"wins":7},"gpt-5.4-mini":{"draws":17,"losses":22,"wins":7},"gpt-5.4-nano":{"draws":22,"losses":25,"wins":17},"gpt-5.5":{"draws":10,"losses":3,"wins":1},"gpt-5.6-luna":{"draws":5,"losses":5,"wins":12},"gpt-5.6-sol":{"draws":1,"losses":8,"wins":1},"gpt-5.6-terra":{"draws":2,"losses":10,"wins":2},"inclusionai/ling-3.0-flash":{"draws":6,"losses":1,"wins":1},"meituan/longcat-2.0":{"draws":4,"losses":0,"wins":0},"minimax/minimax-m3":{"draws":2,"losses":8,"wins":6},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":2},"moonshotai/kimi-k3":{"draws":5,"losses":12,"wins":1},"nex-agi/nex-n2-pro":{"draws":6,"losses":6,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":8,"wins":7},"o3":{"draws":1,"losses":9,"wins":4},"openai/gpt-oss-120b":{"draws":12,"losses":5,"wins":3},"poolside/laguna-s-2.1":{"draws":4,"losses":2,"wins":4},"qwen/qwen3.7-max":{"draws":3,"losses":7,"wins":2},"qwen/qwen3.7-plus":{"draws":7,"losses":8,"wins":3},"stepfun/step-3.7-flash":{"draws":2,"losses":10,"wins":2},"tencent/hy3-preview":{"draws":3,"losses":3,"wins":2},"thinkingmachines/inkling":{"draws":3,"losses":1,"wins":2},"x-ai/grok-4.5":{"draws":5,"losses":13,"wins":0},"x-ai/grok-build-0.1":{"draws":2,"losses":4,"wins":2},"xiaomi/mimo-v2.5":{"draws":19,"losses":14,"wins":13},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":4,"wins":6},"z-ai/glm-5.2":{"draws":14,"losses":4,"wins":2}},"deepseek/deepseek-v4-flash":{"claude-fable-5":{"draws":2,"losses":12,"wins":2},"claude-opus-4-5":{"draws":34,"losses":16,"wins":6},"claude-opus-4-8":{"draws":11,"losses":26,"wins":9},"claude-opus-5":{"draws":3,"losses":1,"wins":0},"claude-sonnet-5":{"draws":22,"losses":22,"wins":12},"cohere/north-mini-code":{"draws":14,"losses":11,"wins":9},"deepseek/deepseek-v4-flash":{"draws":44,"losses":54,"wins":54},"deepseek/deepseek-v4-pro":{"draws":16,"losses":21,"wins":11},"google/gemini-3.1-flash-lite":{"draws":14,"losses":11,"wins":19},"google/gemini-3.5-flash":{"draws":19,"losses":12,"wins":5},"google/gemini-3.5-flash-lite":{"draws":12,"losses":11,"wins":3},"google/gemini-3.6-flash":{"draws":13,"losses":6,"wins":5},"google/gemma-4-31b-it":{"draws":13,"losses":16,"wins":15},"gpt-4.1":{"draws":4,"losses":11,"wins":7},"gpt-5":{"draws":9,"losses":16,"wins":1},"gpt-5.4":{"draws":26,"losses":24,"wins":10},"gpt-5.4-mini":{"draws":78,"losses":62,"wins":40},"gpt-5.4-nano":{"draws":74,"losses":41,"wins":61},"gpt-5.5":{"draws":25,"losses":23,"wins":2},"gpt-5.6-luna":{"draws":39,"losses":18,"wins":17},"gpt-5.6-sol":{"draws":7,"losses":34,"wins":9},"gpt-5.6-terra":{"draws":20,"losses":43,"wins":13},"inclusionai/ling-3.0-flash":{"draws":10,"losses":6,"wins":10},"meituan/longcat-2.0":{"draws":6,"losses":5,"wins":5},"minimax/minimax-m3":{"draws":8,"losses":23,"wins":11},"mistralai/mistral-medium-3-5":{"draws":11,"losses":21,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":4,"wins":3},"moonshotai/kimi-k3":{"draws":28,"losses":49,"wins":11},"nex-agi/nex-n2-pro":{"draws":18,"losses":20,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":28,"losses":14,"wins":20},"o3":{"draws":9,"losses":25,"wins":12},"openai/gpt-oss-120b":{"draws":30,"losses":17,"wins":9},"poolside/laguna-s-2.1":{"draws":7,"losses":8,"wins":3},"qwen/qwen3.7-max":{"draws":14,"losses":16,"wins":8},"qwen/qwen3.7-plus":{"draws":17,"losses":15,"wins":14},"stepfun/step-3.7-flash":{"draws":18,"losses":24,"wins":20},"tencent/hy3-preview":{"draws":22,"losses":15,"wins":13},"thinkingmachines/inkling":{"draws":11,"losses":17,"wins":10},"x-ai/grok-4.5":{"draws":27,"losses":55,"wins":14},"x-ai/grok-build-0.1":{"draws":8,"losses":10,"wins":4},"xiaomi/mimo-v2.5":{"draws":36,"losses":40,"wins":34},"xiaomi/mimo-v2.5-pro":{"draws":14,"losses":15,"wins":15},"z-ai/glm-5.2":{"draws":45,"losses":55,"wins":40}},"deepseek/deepseek-v4-pro":{"claude-fable-5":{"draws":1,"losses":11,"wins":0},"claude-opus-4-5":{"draws":5,"losses":11,"wins":8},"claude-opus-4-8":{"draws":9,"losses":13,"wins":8},"claude-opus-5":{"draws":1,"losses":14,"wins":1},"claude-sonnet-5":{"draws":9,"losses":7,"wins":6},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":6},"deepseek/deepseek-v4-flash":{"draws":16,"losses":11,"wins":21},"deepseek/deepseek-v4-pro":{"draws":0,"losses":4,"wins":4},"google/gemini-3.1-flash-lite":{"draws":4,"losses":2,"wins":2},"google/gemini-3.5-flash":{"draws":1,"losses":2,"wins":1},"google/gemini-3.5-flash-lite":{"draws":1,"losses":1,"wins":2},"google/gemini-3.6-flash":{"draws":0,"losses":2,"wins":0},"google/gemma-4-31b-it":{"draws":4,"losses":2,"wins":6},"gpt-5":{"draws":0,"losses":5,"wins":11},"gpt-5.4":{"draws":4,"losses":17,"wins":5},"gpt-5.4-mini":{"draws":22,"losses":10,"wins":24},"gpt-5.4-nano":{"draws":23,"losses":17,"wins":24},"gpt-5.5":{"draws":7,"losses":11,"wins":2},"gpt-5.6-luna":{"draws":13,"losses":4,"wins":5},"gpt-5.6-sol":{"draws":2,"losses":13,"wins":7},"gpt-5.6-terra":{"draws":10,"losses":7,"wins":7},"inclusionai/ling-3.0-flash":{"draws":1,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":1,"losses":1,"wins":0},"minimax/minimax-m3":{"draws":3,"losses":5,"wins":4},"mistralai/mistral-medium-3-5":{"draws":2,"losses":1,"wins":7},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":1,"wins":3},"moonshotai/kimi-k3":{"draws":11,"losses":15,"wins":12},"nex-agi/nex-n2-pro":{"draws":2,"losses":7,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":5,"wins":7},"o3":{"draws":3,"losses":6,"wins":7},"openai/gpt-oss-120b":{"draws":4,"losses":3,"wins":3},"poolside/laguna-s-2.1":{"draws":0,"losses":2,"wins":2},"qwen/qwen3.7-max":{"draws":9,"losses":6,"wins":7},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":4},"stepfun/step-3.7-flash":{"draws":7,"losses":2,"wins":11},"tencent/hy3-preview":{"draws":4,"losses":6,"wins":6},"thinkingmachines/inkling":{"draws":2,"losses":1,"wins":5},"x-ai/grok-4.5":{"draws":9,"losses":31,"wins":14},"x-ai/grok-build-0.1":{"draws":8,"losses":1,"wins":1},"xiaomi/mimo-v2.5":{"draws":9,"losses":8,"wins":11},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":5,"wins":4},"z-ai/glm-5.2":{"draws":14,"losses":14,"wins":26}},"google/gemini-3.1-flash-lite":{"claude-fable-5":{"draws":0,"losses":4,"wins":0},"claude-opus-4-5":{"draws":9,"losses":17,"wins":0},"claude-opus-4-8":{"draws":7,"losses":14,"wins":3},"claude-opus-5":{"draws":0,"losses":11,"wins":1},"claude-sonnet-5":{"draws":7,"losses":12,"wins":3},"cohere/north-mini-code":{"draws":0,"losses":8,"wins":10},"deepseek/deepseek-v4-flash":{"draws":14,"losses":19,"wins":11},"deepseek/deepseek-v4-pro":{"draws":4,"losses":2,"wins":2},"google/gemini-3.1-flash-lite":{"draws":0,"losses":8,"wins":8},"google/gemini-3.5-flash":{"draws":3,"losses":3,"wins":0},"google/gemini-3.5-flash-lite":{"draws":2,"losses":9,"wins":3},"google/gemini-3.6-flash":{"draws":4,"losses":2,"wins":0},"google/gemma-4-31b-it":{"draws":6,"losses":7,"wins":5},"gpt-4.1":{"draws":4,"losses":3,"wins":3},"gpt-5":{"draws":6,"losses":8,"wins":2},"gpt-5.4":{"draws":1,"losses":7,"wins":0},"gpt-5.4-mini":{"draws":23,"losses":33,"wins":10},"gpt-5.4-nano":{"draws":17,"losses":36,"wins":27},"gpt-5.5":{"draws":9,"losses":7,"wins":2},"gpt-5.6-luna":{"draws":5,"losses":8,"wins":11},"gpt-5.6-sol":{"draws":5,"losses":6,"wins":3},"gpt-5.6-terra":{"draws":3,"losses":10,"wins":3},"inclusionai/ling-3.0-flash":{"draws":5,"losses":0,"wins":3},"meituan/longcat-2.0":{"draws":4,"losses":6,"wins":8},"minimax/minimax-m3":{"draws":3,"losses":3,"wins":10},"mistralai/mistral-medium-3-5":{"draws":2,"losses":7,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":4,"wins":0},"moonshotai/kimi-k3":{"draws":13,"losses":22,"wins":1},"nex-agi/nex-n2-pro":{"draws":2,"losses":10,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":15,"wins":11},"o3":{"draws":6,"losses":10,"wins":4},"openai/gpt-oss-120b":{"draws":6,"losses":8,"wins":6},"poolside/laguna-s-2.1":{"draws":4,"losses":1,"wins":1},"qwen/qwen3.7-max":{"draws":4,"losses":2,"wins":2},"qwen/qwen3.7-plus":{"draws":1,"losses":11,"wins":2},"stepfun/step-3.7-flash":{"draws":4,"losses":9,"wins":5},"tencent/hy3-preview":{"draws":2,"losses":6,"wins":6},"thinkingmachines/inkling":{"draws":7,"losses":7,"wins":6},"x-ai/grok-4.5":{"draws":6,"losses":17,"wins":1},"x-ai/grok-build-0.1":{"draws":7,"losses":10,"wins":1},"xiaomi/mimo-v2.5":{"draws":14,"losses":14,"wins":10},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":12,"wins":0},"z-ai/glm-5.2":{"draws":16,"losses":22,"wins":6}},"google/gemini-3.5-flash":{"claude-fable-5":{"draws":5,"losses":16,"wins":9},"claude-opus-4-5":{"draws":11,"losses":9,"wins":14},"claude-opus-4-8":{"draws":7,"losses":4,"wins":9},"claude-opus-5":{"draws":2,"losses":23,"wins":9},"claude-sonnet-5":{"draws":8,"losses":6,"wins":10},"cohere/north-mini-code":{"draws":3,"losses":1,"wins":4},"deepseek/deepseek-v4-flash":{"draws":19,"losses":5,"wins":12},"deepseek/deepseek-v4-pro":{"draws":1,"losses":1,"wins":2},"google/gemini-3.1-flash-lite":{"draws":3,"losses":0,"wins":3},"google/gemini-3.5-flash":{"draws":4,"losses":2,"wins":2},"google/gemini-3.5-flash-lite":{"draws":2,"losses":0,"wins":0},"google/gemini-3.6-flash":{"draws":4,"losses":1,"wins":3},"google/gemma-4-31b-it":{"draws":2,"losses":4,"wins":4},"gpt-4.1":{"draws":0,"losses":0,"wins":4},"gpt-5":{"draws":6,"losses":5,"wins":9},"gpt-5.4":{"draws":7,"losses":12,"wins":5},"gpt-5.4-mini":{"draws":18,"losses":19,"wins":23},"gpt-5.4-nano":{"draws":18,"losses":14,"wins":16},"gpt-5.5":{"draws":10,"losses":11,"wins":11},"gpt-5.6-luna":{"draws":13,"losses":5,"wins":8},"gpt-5.6-sol":{"draws":6,"losses":10,"wins":4},"gpt-5.6-terra":{"draws":9,"losses":8,"wins":13},"inclusionai/ling-3.0-flash":{"draws":6,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":3,"losses":1,"wins":0},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":2},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":4,"wins":2},"moonshotai/kimi-k3":{"draws":21,"losses":23,"wins":16},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":2,"wins":12},"o3":{"draws":0,"losses":7,"wins":3},"openai/gpt-oss-120b":{"draws":4,"losses":3,"wins":3},"poolside/laguna-s-2.1":{"draws":9,"losses":2,"wins":1},"qwen/qwen3.7-max":{"draws":3,"losses":7,"wins":2},"qwen/qwen3.7-plus":{"draws":2,"losses":1,"wins":9},"stepfun/step-3.7-flash":{"draws":2,"losses":2,"wins":4},"tencent/hy3-preview":{"draws":2,"losses":2,"wins":8},"thinkingmachines/inkling":{"draws":0,"losses":0,"wins":6},"x-ai/grok-4.5":{"draws":13,"losses":8,"wins":19},"x-ai/grok-build-0.1":{"draws":4,"losses":0,"wins":4},"xiaomi/mimo-v2.5":{"draws":13,"losses":6,"wins":7},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":2,"wins":3},"z-ai/glm-5.2":{"draws":17,"losses":16,"wins":21}},"google/gemini-3.5-flash-lite":{"claude-opus-4-5":{"draws":3,"losses":0,"wins":3},"claude-opus-4-8":{"draws":1,"losses":6,"wins":1},"claude-opus-5":{"draws":9,"losses":24,"wins":5},"claude-sonnet-5":{"draws":4,"losses":9,"wins":1},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":2},"deepseek/deepseek-v4-flash":{"draws":12,"losses":3,"wins":11},"deepseek/deepseek-v4-pro":{"draws":1,"losses":2,"wins":1},"google/gemini-3.1-flash-lite":{"draws":2,"losses":3,"wins":9},"google/gemini-3.5-flash":{"draws":2,"losses":0,"wins":0},"google/gemini-3.5-flash-lite":{"draws":120,"losses":112,"wins":112},"google/gemini-3.6-flash":{"draws":145,"losses":120,"wins":69},"google/gemma-4-31b-it":{"draws":0,"losses":2,"wins":0},"gpt-4.1":{"draws":0,"losses":1,"wins":1},"gpt-5":{"draws":2,"losses":0,"wins":0},"gpt-5.4":{"draws":6,"losses":2,"wins":0},"gpt-5.4-mini":{"draws":11,"losses":8,"wins":11},"gpt-5.4-nano":{"draws":17,"losses":7,"wins":26},"gpt-5.5":{"draws":2,"losses":0,"wins":0},"gpt-5.6-luna":{"draws":8,"losses":0,"wins":4},"gpt-5.6-sol":{"draws":5,"losses":3,"wins":2},"gpt-5.6-terra":{"draws":11,"losses":1,"wins":0},"inclusionai/ling-3.0-flash":{"draws":55,"losses":18,"wins":59},"meituan/longcat-2.0":{"draws":65,"losses":63,"wins":81},"minimax/minimax-m3":{"draws":3,"losses":2,"wins":1},"mistralai/mistral-medium-3-5":{"draws":0,"losses":4,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":66,"losses":80,"wins":28},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":3,"wins":6},"o3":{"draws":0,"losses":5,"wins":1},"openai/gpt-oss-120b":{"draws":6,"losses":0,"wins":0},"poolside/laguna-s-2.1":{"draws":86,"losses":77,"wins":49},"qwen/qwen3.7-max":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.7-plus":{"draws":4,"losses":3,"wins":3},"tencent/hy3-preview":{"draws":4,"losses":1,"wins":3},"thinkingmachines/inkling":{"draws":71,"losses":82,"wins":81},"x-ai/grok-4.5":{"draws":59,"losses":109,"wins":34},"x-ai/grok-build-0.1":{"draws":0,"losses":2,"wins":2},"xiaomi/mimo-v2.5":{"draws":6,"losses":1,"wins":3},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":1,"wins":5},"z-ai/glm-5.2":{"draws":9,"losses":9,"wins":6}},"google/gemini-3.6-flash":{"claude-fable-5":{"draws":2,"losses":3,"wins":3},"claude-opus-4-5":{"draws":3,"losses":3,"wins":4},"claude-opus-4-8":{"draws":2,"losses":0,"wins":2},"claude-opus-5":{"draws":8,"losses":49,"wins":23},"claude-sonnet-5":{"draws":5,"losses":1,"wins":2},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":2},"deepseek/deepseek-v4-flash":{"draws":13,"losses":5,"wins":6},"deepseek/deepseek-v4-pro":{"draws":0,"losses":0,"wins":2},"google/gemini-3.1-flash-lite":{"draws":4,"losses":0,"wins":2},"google/gemini-3.5-flash":{"draws":4,"losses":3,"wins":1},"google/gemini-3.5-flash-lite":{"draws":145,"losses":69,"wins":120},"google/gemini-3.6-flash":{"draws":96,"losses":80,"wins":80},"google/gemma-4-31b-it":{"draws":1,"losses":1,"wins":0},"gpt-4.1":{"draws":1,"losses":3,"wins":0},"gpt-5":{"draws":1,"losses":2,"wins":1},"gpt-5.4":{"draws":4,"losses":11,"wins":5},"gpt-5.4-mini":{"draws":10,"losses":2,"wins":10},"gpt-5.4-nano":{"draws":17,"losses":10,"wins":21},"gpt-5.5":{"draws":4,"losses":7,"wins":3},"gpt-5.6-luna":{"draws":2,"losses":3,"wins":3},"gpt-5.6-sol":{"draws":2,"losses":8,"wins":4},"gpt-5.6-terra":{"draws":2,"losses":2,"wins":2},"inclusionai/ling-3.0-flash":{"draws":75,"losses":14,"wins":41},"meituan/longcat-2.0":{"draws":64,"losses":47,"wins":83},"minimax/minimax-m3":{"draws":5,"losses":0,"wins":3},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":1},"moonshotai/kimi-k3":{"draws":57,"losses":51,"wins":42},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":2,"wins":1},"o3":{"draws":1,"losses":0,"wins":1},"openai/gpt-oss-120b":{"draws":1,"losses":0,"wins":1},"poolside/laguna-s-2.1":{"draws":66,"losses":26,"wins":66},"qwen/qwen3.7-max":{"draws":1,"losses":1,"wins":2},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":0},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":4,"losses":4,"wins":0},"thinkingmachines/inkling":{"draws":80,"losses":44,"wins":96},"x-ai/grok-4.5":{"draws":37,"losses":66,"wins":79},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":13,"losses":3,"wins":8},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":0,"wins":3},"z-ai/glm-5.2":{"draws":13,"losses":5,"wins":8}},"google/gemma-4-31b-it":{"claude-fable-5":{"draws":1,"losses":2,"wins":1},"claude-opus-4-5":{"draws":6,"losses":4,"wins":4},"claude-opus-4-8":{"draws":6,"losses":4,"wins":0},"claude-sonnet-5":{"draws":6,"losses":6,"wins":2},"cohere/north-mini-code":{"draws":1,"losses":5,"wins":6},"deepseek/deepseek-v4-flash":{"draws":13,"losses":15,"wins":16},"deepseek/deepseek-v4-pro":{"draws":4,"losses":6,"wins":2},"google/gemini-3.1-flash-lite":{"draws":6,"losses":5,"wins":7},"google/gemini-3.5-flash":{"draws":2,"losses":4,"wins":4},"google/gemini-3.5-flash-lite":{"draws":0,"losses":0,"wins":2},"google/gemini-3.6-flash":{"draws":1,"losses":0,"wins":1},"google/gemma-4-31b-it":{"draws":4,"losses":2,"wins":2},"gpt-5":{"draws":1,"losses":2,"wins":1},"gpt-5.4":{"draws":5,"losses":4,"wins":1},"gpt-5.4-mini":{"draws":19,"losses":18,"wins":15},"gpt-5.4-nano":{"draws":10,"losses":17,"wins":19},"gpt-5.5":{"draws":4,"losses":5,"wins":1},"gpt-5.6-luna":{"draws":4,"losses":5,"wins":7},"gpt-5.6-sol":{"draws":8,"losses":6,"wins":2},"gpt-5.6-terra":{"draws":5,"losses":15,"wins":2},"inclusionai/ling-3.0-flash":{"draws":0,"losses":2,"wins":2},"meituan/longcat-2.0":{"draws":0,"losses":3,"wins":3},"minimax/minimax-m3":{"draws":0,"losses":7,"wins":5},"mistralai/mistral-medium-3-5":{"draws":2,"losses":5,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":8,"wins":0},"moonshotai/kimi-k3":{"draws":11,"losses":8,"wins":3},"nex-agi/nex-n2-pro":{"draws":2,"losses":2,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":6,"wins":6},"o3":{"draws":4,"losses":5,"wins":1},"openai/gpt-oss-120b":{"draws":2,"losses":3,"wins":9},"qwen/qwen3.7-max":{"draws":1,"losses":4,"wins":3},"qwen/qwen3.7-plus":{"draws":0,"losses":3,"wins":11},"stepfun/step-3.7-flash":{"draws":0,"losses":7,"wins":3},"tencent/hy3-preview":{"draws":2,"losses":5,"wins":1},"thinkingmachines/inkling":{"draws":0,"losses":4,"wins":0},"x-ai/grok-4.5":{"draws":5,"losses":20,"wins":3},"x-ai/grok-build-0.1":{"draws":5,"losses":5,"wins":4},"xiaomi/mimo-v2.5":{"draws":2,"losses":10,"wins":12},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":6,"wins":4},"z-ai/glm-5.2":{"draws":5,"losses":7,"wins":6}},"gpt-4.1":{"claude-fable-5":{"draws":0,"losses":0,"wins":2},"claude-opus-4-5":{"draws":5,"losses":2,"wins":1},"claude-opus-4-8":{"draws":1,"losses":7,"wins":2},"claude-opus-5":{"draws":6,"losses":18,"wins":0},"claude-sonnet-5":{"draws":5,"losses":6,"wins":1},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":3},"deepseek/deepseek-v4-flash":{"draws":4,"losses":7,"wins":11},"google/gemini-3.1-flash-lite":{"draws":4,"losses":3,"wins":3},"google/gemini-3.5-flash":{"draws":0,"losses":4,"wins":0},"google/gemini-3.5-flash-lite":{"draws":0,"losses":1,"wins":1},"google/gemini-3.6-flash":{"draws":1,"losses":0,"wins":3},"gpt-5":{"draws":4,"losses":3,"wins":1},"gpt-5.4":{"draws":3,"losses":0,"wins":1},"gpt-5.4-mini":{"draws":12,"losses":11,"wins":5},"gpt-5.4-nano":{"draws":2,"losses":8,"wins":4},"gpt-5.5":{"draws":3,"losses":7,"wins":2},"gpt-5.6-luna":{"draws":2,"losses":4,"wins":0},"gpt-5.6-sol":{"draws":3,"losses":6,"wins":1},"gpt-5.6-terra":{"draws":3,"losses":0,"wins":1},"inclusionai/ling-3.0-flash":{"draws":3,"losses":0,"wins":1},"meituan/longcat-2.0":{"draws":0,"losses":1,"wins":5},"minimax/minimax-m3":{"draws":0,"losses":1,"wins":7},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":1,"wins":1},"moonshotai/kimi-k3":{"draws":4,"losses":3,"wins":5},"nex-agi/nex-n2-pro":{"draws":3,"losses":1,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":2,"wins":4},"o3":{"draws":1,"losses":1,"wins":0},"openai/gpt-oss-120b":{"draws":3,"losses":3,"wins":2},"poolside/laguna-s-2.1":{"draws":4,"losses":1,"wins":1},"qwen/qwen3.7-max":{"draws":6,"losses":0,"wins":0},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":4,"losses":0,"wins":4},"thinkingmachines/inkling":{"draws":0,"losses":0,"wins":2},"x-ai/grok-4.5":{"draws":1,"losses":5,"wins":4},"xiaomi/mimo-v2.5":{"draws":0,"losses":2,"wins":6},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":5,"wins":5},"z-ai/glm-5.2":{"draws":6,"losses":15,"wins":11}},"gpt-5":{"claude-fable-5":{"draws":2,"losses":17,"wins":1},"claude-opus-4-5":{"draws":13,"losses":7,"wins":12},"claude-opus-4-8":{"draws":7,"losses":17,"wins":4},"claude-opus-5":{"draws":3,"losses":10,"wins":1},"claude-sonnet-5":{"draws":19,"losses":12,"wins":17},"cohere/north-mini-code":{"draws":5,"losses":1,"wins":12},"deepseek/deepseek-v4-flash":{"draws":9,"losses":1,"wins":16},"deepseek/deepseek-v4-pro":{"draws":0,"losses":11,"wins":5},"google/gemini-3.1-flash-lite":{"draws":6,"losses":2,"wins":8},"google/gemini-3.5-flash":{"draws":6,"losses":9,"wins":5},"google/gemini-3.5-flash-lite":{"draws":2,"losses":0,"wins":0},"google/gemini-3.6-flash":{"draws":1,"losses":1,"wins":2},"google/gemma-4-31b-it":{"draws":1,"losses":1,"wins":2},"gpt-4.1":{"draws":4,"losses":1,"wins":3},"gpt-5":{"draws":0,"losses":2,"wins":2},"gpt-5.4":{"draws":6,"losses":13,"wins":5},"gpt-5.4-mini":{"draws":24,"losses":17,"wins":11},"gpt-5.4-nano":{"draws":27,"losses":19,"wins":32},"gpt-5.5":{"draws":6,"losses":16,"wins":7},"gpt-5.6-luna":{"draws":13,"losses":3,"wins":8},"gpt-5.6-sol":{"draws":4,"losses":11,"wins":5},"gpt-5.6-terra":{"draws":9,"losses":15,"wins":6},"meituan/longcat-2.0":{"draws":3,"losses":2,"wins":1},"minimax/minimax-m3":{"draws":6,"losses":5,"wins":9},"mistralai/mistral-medium-3-5":{"draws":0,"losses":2,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":6},"moonshotai/kimi-k3":{"draws":21,"losses":10,"wins":19},"nex-agi/nex-n2-pro":{"draws":0,"losses":2,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":4,"wins":6},"o3":{"draws":2,"losses":5,"wins":13},"openai/gpt-oss-120b":{"draws":7,"losses":1,"wins":2},"poolside/laguna-s-2.1":{"draws":4,"losses":3,"wins":1},"qwen/qwen3.7-max":{"draws":6,"losses":4,"wins":6},"qwen/qwen3.7-plus":{"draws":2,"losses":1,"wins":1},"stepfun/step-3.7-flash":{"draws":4,"losses":0,"wins":8},"tencent/hy3-preview":{"draws":1,"losses":6,"wins":7},"thinkingmachines/inkling":{"draws":2,"losses":0,"wins":2},"x-ai/grok-4.5":{"draws":11,"losses":24,"wins":11},"x-ai/grok-build-0.1":{"draws":6,"losses":3,"wins":5},"xiaomi/mimo-v2.5":{"draws":18,"losses":12,"wins":8},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":3,"wins":6},"z-ai/glm-5.2":{"draws":23,"losses":32,"wins":29}},"gpt-5.4":{"claude-fable-5":{"draws":6,"losses":16,"wins":14},"claude-opus-4-5":{"draws":17,"losses":15,"wins":22},"claude-opus-4-8":{"draws":6,"losses":16,"wins":18},"claude-opus-5":{"draws":10,"losses":34,"wins":26},"claude-sonnet-5":{"draws":12,"losses":6,"wins":18},"cohere/north-mini-code":{"draws":7,"losses":7,"wins":10},"deepseek/deepseek-v4-flash":{"draws":26,"losses":10,"wins":24},"deepseek/deepseek-v4-pro":{"draws":4,"losses":5,"wins":17},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":7},"google/gemini-3.5-flash":{"draws":7,"losses":5,"wins":12},"google/gemini-3.5-flash-lite":{"draws":6,"losses":0,"wins":2},"google/gemini-3.6-flash":{"draws":4,"losses":5,"wins":11},"google/gemma-4-31b-it":{"draws":5,"losses":1,"wins":4},"gpt-4.1":{"draws":3,"losses":1,"wins":0},"gpt-5":{"draws":6,"losses":5,"wins":13},"gpt-5.4":{"draws":12,"losses":10,"wins":10},"gpt-5.4-mini":{"draws":39,"losses":19,"wins":52},"gpt-5.4-nano":{"draws":36,"losses":16,"wins":56},"gpt-5.5":{"draws":20,"losses":15,"wins":15},"gpt-5.6-luna":{"draws":24,"losses":4,"wins":22},"gpt-5.6-sol":{"draws":6,"losses":12,"wins":26},"gpt-5.6-terra":{"draws":14,"losses":13,"wins":23},"inclusionai/ling-3.0-flash":{"draws":3,"losses":1,"wins":2},"meituan/longcat-2.0":{"draws":1,"losses":0,"wins":1},"minimax/minimax-m3":{"draws":5,"losses":4,"wins":11},"mistralai/mistral-medium-3-5":{"draws":1,"losses":0,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":4,"wins":3},"moonshotai/kimi-k3":{"draws":18,"losses":16,"wins":44},"nex-agi/nex-n2-pro":{"draws":6,"losses":0,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":2,"wins":9},"o3":{"draws":5,"losses":6,"wins":9},"openai/gpt-oss-120b":{"draws":10,"losses":2,"wins":10},"poolside/laguna-s-2.1":{"draws":0,"losses":2,"wins":2},"qwen/qwen3.7-max":{"draws":4,"losses":2,"wins":10},"qwen/qwen3.7-plus":{"draws":6,"losses":0,"wins":8},"stepfun/step-3.7-flash":{"draws":4,"losses":3,"wins":3},"tencent/hy3-preview":{"draws":12,"losses":4,"wins":14},"thinkingmachines/inkling":{"draws":6,"losses":1,"wins":3},"x-ai/grok-4.5":{"draws":35,"losses":29,"wins":58},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":21,"losses":5,"wins":18},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":7,"wins":19},"z-ai/glm-5.2":{"draws":41,"losses":17,"wins":30}},"gpt-5.4-mini":{"claude-fable-5":{"draws":7,"losses":19,"wins":6},"claude-opus-4-5":{"draws":40,"losses":31,"wins":19},"claude-opus-4-8":{"draws":22,"losses":32,"wins":18},"claude-opus-5":{"draws":3,"losses":31,"wins":6},"claude-sonnet-5":{"draws":27,"losses":33,"wins":28},"cohere/north-mini-code":{"draws":17,"losses":7,"wins":22},"deepseek/deepseek-v4-flash":{"draws":78,"losses":40,"wins":62},"deepseek/deepseek-v4-pro":{"draws":22,"losses":24,"wins":10},"google/gemini-3.1-flash-lite":{"draws":23,"losses":10,"wins":33},"google/gemini-3.5-flash":{"draws":18,"losses":23,"wins":19},"google/gemini-3.5-flash-lite":{"draws":11,"losses":11,"wins":8},"google/gemini-3.6-flash":{"draws":10,"losses":10,"wins":2},"google/gemma-4-31b-it":{"draws":19,"losses":15,"wins":18},"gpt-4.1":{"draws":12,"losses":5,"wins":11},"gpt-5":{"draws":24,"losses":11,"wins":17},"gpt-5.4":{"draws":39,"losses":52,"wins":19},"gpt-5.4-mini":{"draws":100,"losses":76,"wins":76},"gpt-5.4-nano":{"draws":98,"losses":81,"wins":110},"gpt-5.5":{"draws":37,"losses":18,"wins":11},"gpt-5.6-luna":{"draws":44,"losses":31,"wins":29},"gpt-5.6-sol":{"draws":17,"losses":31,"wins":18},"gpt-5.6-terra":{"draws":52,"losses":45,"wins":27},"inclusionai/ling-3.0-flash":{"draws":4,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":7,"losses":9,"wins":12},"minimax/minimax-m3":{"draws":27,"losses":22,"wins":27},"mistralai/mistral-medium-3-5":{"draws":10,"losses":9,"wins":21},"moonshotai/kimi-k2.7-code":{"draws":9,"losses":16,"wins":5},"moonshotai/kimi-k3":{"draws":51,"losses":43,"wins":24},"nex-agi/nex-n2-pro":{"draws":19,"losses":13,"wins":24},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":45,"losses":18,"wins":23},"o3":{"draws":12,"losses":41,"wins":21},"openai/gpt-oss-120b":{"draws":30,"losses":26,"wins":24},"poolside/laguna-s-2.1":{"draws":7,"losses":6,"wins":9},"qwen/qwen3.7-max":{"draws":24,"losses":23,"wins":19},"qwen/qwen3.7-plus":{"draws":24,"losses":30,"wins":14},"stepfun/step-3.7-flash":{"draws":21,"losses":23,"wins":34},"tencent/hy3-preview":{"draws":21,"losses":12,"wins":23},"thinkingmachines/inkling":{"draws":18,"losses":14,"wins":14},"x-ai/grok-4.5":{"draws":52,"losses":92,"wins":26},"x-ai/grok-build-0.1":{"draws":3,"losses":12,"wins":9},"xiaomi/mimo-v2.5":{"draws":73,"losses":68,"wins":55},"xiaomi/mimo-v2.5-pro":{"draws":19,"losses":12,"wins":19},"z-ai/glm-5.2":{"draws":82,"losses":75,"wins":57}},"gpt-5.4-nano":{"claude-fable-5":{"draws":7,"losses":45,"wins":10},"claude-opus-4-5":{"draws":32,"losses":52,"wins":26},"claude-opus-4-8":{"draws":20,"losses":42,"wins":20},"claude-opus-5":{"draws":9,"losses":43,"wins":12},"claude-sonnet-5":{"draws":33,"losses":25,"wins":18},"cohere/north-mini-code":{"draws":22,"losses":17,"wins":25},"deepseek/deepseek-v4-flash":{"draws":74,"losses":61,"wins":41},"deepseek/deepseek-v4-pro":{"draws":23,"losses":24,"wins":17},"google/gemini-3.1-flash-lite":{"draws":17,"losses":27,"wins":36},"google/gemini-3.5-flash":{"draws":18,"losses":16,"wins":14},"google/gemini-3.5-flash-lite":{"draws":17,"losses":26,"wins":7},"google/gemini-3.6-flash":{"draws":17,"losses":21,"wins":10},"google/gemma-4-31b-it":{"draws":10,"losses":19,"wins":17},"gpt-4.1":{"draws":2,"losses":4,"wins":8},"gpt-5":{"draws":27,"losses":32,"wins":19},"gpt-5.4":{"draws":36,"losses":56,"wins":16},"gpt-5.4-mini":{"draws":98,"losses":110,"wins":81},"gpt-5.4-nano":{"draws":82,"losses":99,"wins":99},"gpt-5.5":{"draws":25,"losses":30,"wins":21},"gpt-5.6-luna":{"draws":40,"losses":32,"wins":36},"gpt-5.6-sol":{"draws":10,"losses":49,"wins":23},"gpt-5.6-terra":{"draws":34,"losses":29,"wins":33},"inclusionai/ling-3.0-flash":{"draws":17,"losses":7,"wins":0},"meituan/longcat-2.0":{"draws":13,"losses":15,"wins":16},"minimax/minimax-m3":{"draws":37,"losses":25,"wins":30},"mistralai/mistral-medium-3-5":{"draws":9,"losses":18,"wins":19},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":9,"wins":7},"moonshotai/kimi-k3":{"draws":48,"losses":68,"wins":41},"nex-agi/nex-n2-pro":{"draws":21,"losses":24,"wins":17},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":56,"losses":23,"wins":19},"o3":{"draws":20,"losses":22,"wins":28},"openai/gpt-oss-120b":{"draws":52,"losses":32,"wins":26},"poolside/laguna-s-2.1":{"draws":14,"losses":10,"wins":4},"qwen/qwen3.7-max":{"draws":36,"losses":27,"wins":15},"qwen/qwen3.7-plus":{"draws":23,"losses":40,"wins":11},"stepfun/step-3.7-flash":{"draws":20,"losses":21,"wins":23},"tencent/hy3-preview":{"draws":35,"losses":25,"wins":14},"thinkingmachines/inkling":{"draws":13,"losses":35,"wins":16},"x-ai/grok-4.5":{"draws":46,"losses":86,"wins":58},"x-ai/grok-build-0.1":{"draws":13,"losses":15,"wins":6},"xiaomi/mimo-v2.5":{"draws":80,"losses":66,"wins":50},"xiaomi/mimo-v2.5-pro":{"draws":22,"losses":27,"wins":21},"z-ai/glm-5.2":{"draws":84,"losses":87,"wins":70}},"gpt-5.5":{"claude-fable-5":{"draws":7,"losses":12,"wins":13},"claude-opus-4-5":{"draws":16,"losses":15,"wins":19},"claude-opus-4-8":{"draws":8,"losses":9,"wins":21},"claude-opus-5":{"draws":7,"losses":26,"wins":19},"claude-sonnet-5":{"draws":12,"losses":8,"wins":12},"cohere/north-mini-code":{"draws":10,"losses":1,"wins":3},"deepseek/deepseek-v4-flash":{"draws":25,"losses":2,"wins":23},"deepseek/deepseek-v4-pro":{"draws":7,"losses":2,"wins":11},"google/gemini-3.1-flash-lite":{"draws":9,"losses":2,"wins":7},"google/gemini-3.5-flash":{"draws":10,"losses":11,"wins":11},"google/gemini-3.5-flash-lite":{"draws":2,"losses":0,"wins":0},"google/gemini-3.6-flash":{"draws":4,"losses":3,"wins":7},"google/gemma-4-31b-it":{"draws":4,"losses":1,"wins":5},"gpt-4.1":{"draws":3,"losses":2,"wins":7},"gpt-5":{"draws":6,"losses":7,"wins":16},"gpt-5.4":{"draws":20,"losses":15,"wins":15},"gpt-5.4-mini":{"draws":37,"losses":11,"wins":18},"gpt-5.4-nano":{"draws":25,"losses":21,"wins":30},"gpt-5.5":{"draws":14,"losses":9,"wins":9},"gpt-5.6-luna":{"draws":13,"losses":9,"wins":12},"gpt-5.6-sol":{"draws":14,"losses":16,"wins":20},"gpt-5.6-terra":{"draws":17,"losses":13,"wins":20},"inclusionai/ling-3.0-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":0,"losses":1,"wins":1},"minimax/minimax-m3":{"draws":6,"losses":6,"wins":10},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":3,"wins":1},"moonshotai/kimi-k3":{"draws":27,"losses":18,"wins":29},"nex-agi/nex-n2-pro":{"draws":4,"losses":3,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":1,"wins":5},"o3":{"draws":5,"losses":2,"wins":11},"openai/gpt-oss-120b":{"draws":11,"losses":2,"wins":9},"poolside/laguna-s-2.1":{"draws":1,"losses":3,"wins":2},"qwen/qwen3.7-max":{"draws":7,"losses":6,"wins":7},"qwen/qwen3.7-plus":{"draws":7,"losses":0,"wins":5},"stepfun/step-3.7-flash":{"draws":5,"losses":2,"wins":9},"tencent/hy3-preview":{"draws":14,"losses":5,"wins":11},"thinkingmachines/inkling":{"draws":5,"losses":4,"wins":9},"x-ai/grok-4.5":{"draws":23,"losses":39,"wins":34},"x-ai/grok-build-0.1":{"draws":7,"losses":5,"wins":2},"xiaomi/mimo-v2.5":{"draws":25,"losses":6,"wins":9},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":7,"wins":5},"z-ai/glm-5.2":{"draws":22,"losses":20,"wins":26}},"gpt-5.6-luna":{"claude-fable-5":{"draws":2,"losses":16,"wins":2},"claude-opus-4-5":{"draws":17,"losses":12,"wins":15},"claude-opus-4-8":{"draws":10,"losses":16,"wins":14},"claude-opus-5":{"draws":1,"losses":13,"wins":4},"claude-sonnet-5":{"draws":11,"losses":7,"wins":12},"cohere/north-mini-code":{"draws":5,"losses":12,"wins":5},"deepseek/deepseek-v4-flash":{"draws":39,"losses":17,"wins":18},"deepseek/deepseek-v4-pro":{"draws":13,"losses":5,"wins":4},"google/gemini-3.1-flash-lite":{"draws":5,"losses":11,"wins":8},"google/gemini-3.5-flash":{"draws":13,"losses":8,"wins":5},"google/gemini-3.5-flash-lite":{"draws":8,"losses":4,"wins":0},"google/gemini-3.6-flash":{"draws":2,"losses":3,"wins":3},"google/gemma-4-31b-it":{"draws":4,"losses":7,"wins":5},"gpt-4.1":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":13,"losses":8,"wins":3},"gpt-5.4":{"draws":24,"losses":22,"wins":4},"gpt-5.4-mini":{"draws":44,"losses":29,"wins":31},"gpt-5.4-nano":{"draws":40,"losses":36,"wins":32},"gpt-5.5":{"draws":13,"losses":12,"wins":9},"gpt-5.6-luna":{"draws":16,"losses":14,"wins":14},"gpt-5.6-sol":{"draws":7,"losses":19,"wins":10},"gpt-5.6-terra":{"draws":15,"losses":17,"wins":10},"inclusionai/ling-3.0-flash":{"draws":5,"losses":3,"wins":0},"meituan/longcat-2.0":{"draws":2,"losses":2,"wins":2},"minimax/minimax-m3":{"draws":10,"losses":6,"wins":4},"mistralai/mistral-medium-3-5":{"draws":0,"losses":6,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":3,"wins":2},"moonshotai/kimi-k3":{"draws":15,"losses":15,"wins":18},"nex-agi/nex-n2-pro":{"draws":9,"losses":7,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":6,"wins":10},"o3":{"draws":2,"losses":8,"wins":8},"openai/gpt-oss-120b":{"draws":16,"losses":11,"wins":13},"poolside/laguna-s-2.1":{"draws":2,"losses":1,"wins":5},"qwen/qwen3.7-max":{"draws":18,"losses":3,"wins":7},"qwen/qwen3.7-plus":{"draws":9,"losses":8,"wins":5},"stepfun/step-3.7-flash":{"draws":3,"losses":12,"wins":5},"tencent/hy3-preview":{"draws":8,"losses":5,"wins":7},"thinkingmachines/inkling":{"draws":7,"losses":1,"wins":0},"x-ai/grok-4.5":{"draws":18,"losses":32,"wins":24},"x-ai/grok-build-0.1":{"draws":14,"losses":0,"wins":6},"xiaomi/mimo-v2.5":{"draws":19,"losses":24,"wins":11},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":9,"wins":4},"z-ai/glm-5.2":{"draws":36,"losses":35,"wins":25}},"gpt-5.6-sol":{"claude-fable-5":{"draws":8,"losses":26,"wins":14},"claude-opus-4-5":{"draws":10,"losses":9,"wins":33},"claude-opus-4-8":{"draws":8,"losses":11,"wins":21},"claude-opus-5":{"draws":16,"losses":40,"wins":18},"claude-sonnet-5":{"draws":6,"losses":8,"wins":28},"cohere/north-mini-code":{"draws":1,"losses":1,"wins":8},"deepseek/deepseek-v4-flash":{"draws":7,"losses":9,"wins":34},"deepseek/deepseek-v4-pro":{"draws":2,"losses":7,"wins":13},"google/gemini-3.1-flash-lite":{"draws":5,"losses":3,"wins":6},"google/gemini-3.5-flash":{"draws":6,"losses":4,"wins":10},"google/gemini-3.5-flash-lite":{"draws":5,"losses":2,"wins":3},"google/gemini-3.6-flash":{"draws":2,"losses":4,"wins":8},"google/gemma-4-31b-it":{"draws":8,"losses":2,"wins":6},"gpt-4.1":{"draws":3,"losses":1,"wins":6},"gpt-5":{"draws":4,"losses":5,"wins":11},"gpt-5.4":{"draws":6,"losses":26,"wins":12},"gpt-5.4-mini":{"draws":17,"losses":18,"wins":31},"gpt-5.4-nano":{"draws":10,"losses":23,"wins":49},"gpt-5.5":{"draws":14,"losses":20,"wins":16},"gpt-5.6-luna":{"draws":7,"losses":10,"wins":19},"gpt-5.6-sol":{"draws":4,"losses":14,"wins":14},"gpt-5.6-terra":{"draws":10,"losses":15,"wins":19},"inclusionai/ling-3.0-flash":{"draws":1,"losses":1,"wins":2},"meituan/longcat-2.0":{"draws":0,"losses":2,"wins":0},"minimax/minimax-m3":{"draws":6,"losses":0,"wins":10},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":1,"wins":7},"moonshotai/kimi-k3":{"draws":21,"losses":34,"wins":59},"nex-agi/nex-n2-pro":{"draws":0,"losses":3,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":6,"wins":20},"o3":{"draws":5,"losses":6,"wins":9},"openai/gpt-oss-120b":{"draws":8,"losses":4,"wins":8},"poolside/laguna-s-2.1":{"draws":0,"losses":2,"wins":4},"qwen/qwen3.7-max":{"draws":6,"losses":9,"wins":15},"qwen/qwen3.7-plus":{"draws":4,"losses":3,"wins":5},"stepfun/step-3.7-flash":{"draws":4,"losses":4,"wins":8},"tencent/hy3-preview":{"draws":8,"losses":9,"wins":19},"thinkingmachines/inkling":{"draws":1,"losses":2,"wins":5},"x-ai/grok-4.5":{"draws":24,"losses":46,"wins":62},"x-ai/grok-build-0.1":{"draws":4,"losses":6,"wins":6},"xiaomi/mimo-v2.5":{"draws":10,"losses":9,"wins":13},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":3,"wins":10},"z-ai/glm-5.2":{"draws":23,"losses":22,"wins":43}},"gpt-5.6-terra":{"claude-fable-5":{"draws":5,"losses":25,"wins":4},"claude-opus-4-5":{"draws":17,"losses":13,"wins":22},"claude-opus-4-8":{"draws":14,"losses":14,"wins":8},"claude-opus-5":{"draws":16,"losses":26,"wins":8},"claude-sonnet-5":{"draws":11,"losses":16,"wins":13},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":10},"deepseek/deepseek-v4-flash":{"draws":20,"losses":13,"wins":43},"deepseek/deepseek-v4-pro":{"draws":10,"losses":7,"wins":7},"google/gemini-3.1-flash-lite":{"draws":3,"losses":3,"wins":10},"google/gemini-3.5-flash":{"draws":9,"losses":13,"wins":8},"google/gemini-3.5-flash-lite":{"draws":11,"losses":0,"wins":1},"google/gemini-3.6-flash":{"draws":2,"losses":2,"wins":2},"google/gemma-4-31b-it":{"draws":5,"losses":2,"wins":15},"gpt-4.1":{"draws":3,"losses":1,"wins":0},"gpt-5":{"draws":9,"losses":6,"wins":15},"gpt-5.4":{"draws":14,"losses":23,"wins":13},"gpt-5.4-mini":{"draws":52,"losses":27,"wins":45},"gpt-5.4-nano":{"draws":34,"losses":33,"wins":29},"gpt-5.5":{"draws":17,"losses":20,"wins":13},"gpt-5.6-luna":{"draws":15,"losses":10,"wins":17},"gpt-5.6-sol":{"draws":10,"losses":19,"wins":15},"gpt-5.6-terra":{"draws":0,"losses":4,"wins":4},"inclusionai/ling-3.0-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":2,"losses":2,"wins":2},"minimax/minimax-m3":{"draws":6,"losses":6,"wins":4},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":3,"wins":4},"moonshotai/kimi-k3":{"draws":34,"losses":30,"wins":16},"nex-agi/nex-n2-pro":{"draws":9,"losses":6,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":22,"losses":4,"wins":14},"o3":{"draws":7,"losses":6,"wins":7},"openai/gpt-oss-120b":{"draws":7,"losses":3,"wins":8},"poolside/laguna-s-2.1":{"draws":2,"losses":1,"wins":1},"qwen/qwen3.7-max":{"draws":7,"losses":4,"wins":7},"qwen/qwen3.7-plus":{"draws":9,"losses":11,"wins":6},"stepfun/step-3.7-flash":{"draws":12,"losses":1,"wins":9},"tencent/hy3-preview":{"draws":10,"losses":2,"wins":2},"thinkingmachines/inkling":{"draws":8,"losses":0,"wins":2},"x-ai/grok-4.5":{"draws":25,"losses":44,"wins":25},"x-ai/grok-build-0.1":{"draws":4,"losses":0,"wins":6},"xiaomi/mimo-v2.5":{"draws":21,"losses":8,"wins":21},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":5,"wins":3},"z-ai/glm-5.2":{"draws":27,"losses":22,"wins":27}},"inclusionai/ling-3.0-flash":{"claude-opus-4-5":{"draws":3,"losses":2,"wins":1},"claude-opus-5":{"draws":5,"losses":5,"wins":0},"claude-sonnet-5":{"draws":2,"losses":4,"wins":0},"cohere/north-mini-code":{"draws":6,"losses":1,"wins":1},"deepseek/deepseek-v4-flash":{"draws":10,"losses":10,"wins":6},"deepseek/deepseek-v4-pro":{"draws":1,"losses":0,"wins":1},"google/gemini-3.1-flash-lite":{"draws":5,"losses":3,"wins":0},"google/gemini-3.5-flash":{"draws":6,"losses":0,"wins":0},"google/gemini-3.5-flash-lite":{"draws":55,"losses":59,"wins":18},"google/gemini-3.6-flash":{"draws":75,"losses":41,"wins":14},"google/gemma-4-31b-it":{"draws":0,"losses":2,"wins":2},"gpt-4.1":{"draws":3,"losses":1,"wins":0},"gpt-5.4":{"draws":3,"losses":2,"wins":1},"gpt-5.4-mini":{"draws":4,"losses":2,"wins":0},"gpt-5.4-nano":{"draws":17,"losses":0,"wins":7},"gpt-5.5":{"draws":2,"losses":0,"wins":0},"gpt-5.6-luna":{"draws":5,"losses":0,"wins":3},"gpt-5.6-sol":{"draws":1,"losses":2,"wins":1},"gpt-5.6-terra":{"draws":4,"losses":0,"wins":0},"inclusionai/ling-3.0-flash":{"draws":14,"losses":21,"wins":21},"meituan/longcat-2.0":{"draws":30,"losses":42,"wins":20},"minimax/minimax-m3":{"draws":2,"losses":1,"wins":1},"mistralai/mistral-medium-3-5":{"draws":2,"losses":4,"wins":0},"moonshotai/kimi-k3":{"draws":27,"losses":20,"wins":3},"nex-agi/nex-n2-pro":{"draws":1,"losses":5,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":3,"wins":1},"openai/gpt-oss-120b":{"draws":3,"losses":2,"wins":1},"poolside/laguna-s-2.1":{"draws":33,"losses":20,"wins":11},"qwen/qwen3.7-max":{"draws":0,"losses":2,"wins":0},"qwen/qwen3.7-plus":{"draws":0,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":4,"losses":3,"wins":1},"thinkingmachines/inkling":{"draws":29,"losses":38,"wins":27},"x-ai/grok-4.5":{"draws":17,"losses":43,"wins":6},"xiaomi/mimo-v2.5":{"draws":6,"losses":0,"wins":2},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":0,"wins":1},"z-ai/glm-5.2":{"draws":6,"losses":5,"wins":3}},"meituan/longcat-2.0":{"claude-fable-5":{"draws":0,"losses":1,"wins":1},"claude-opus-4-5":{"draws":6,"losses":5,"wins":5},"claude-opus-4-8":{"draws":2,"losses":0,"wins":0},"claude-opus-5":{"draws":4,"losses":14,"wins":6},"claude-sonnet-5":{"draws":4,"losses":6,"wins":0},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":0},"deepseek/deepseek-v4-flash":{"draws":6,"losses":5,"wins":5},"deepseek/deepseek-v4-pro":{"draws":1,"losses":0,"wins":1},"google/gemini-3.1-flash-lite":{"draws":4,"losses":8,"wins":6},"google/gemini-3.5-flash":{"draws":3,"losses":0,"wins":1},"google/gemini-3.5-flash-lite":{"draws":65,"losses":81,"wins":63},"google/gemini-3.6-flash":{"draws":64,"losses":83,"wins":47},"google/gemma-4-31b-it":{"draws":0,"losses":3,"wins":3},"gpt-4.1":{"draws":0,"losses":5,"wins":1},"gpt-5":{"draws":3,"losses":1,"wins":2},"gpt-5.4":{"draws":1,"losses":1,"wins":0},"gpt-5.4-mini":{"draws":7,"losses":12,"wins":9},"gpt-5.4-nano":{"draws":13,"losses":16,"wins":15},"gpt-5.5":{"draws":0,"losses":1,"wins":1},"gpt-5.6-luna":{"draws":2,"losses":2,"wins":2},"gpt-5.6-sol":{"draws":0,"losses":0,"wins":2},"gpt-5.6-terra":{"draws":2,"losses":2,"wins":2},"inclusionai/ling-3.0-flash":{"draws":30,"losses":20,"wins":42},"meituan/longcat-2.0":{"draws":28,"losses":40,"wins":40},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":2},"mistralai/mistral-medium-3-5":{"draws":0,"losses":2,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":3,"wins":1},"moonshotai/kimi-k3":{"draws":35,"losses":40,"wins":12},"nex-agi/nex-n2-pro":{"draws":0,"losses":2,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":3,"wins":3},"o3":{"draws":0,"losses":3,"wins":1},"openai/gpt-oss-120b":{"draws":2,"losses":0,"wins":0},"poolside/laguna-s-2.1":{"draws":45,"losses":38,"wins":33},"qwen/qwen3.7-max":{"draws":2,"losses":2,"wins":0},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":5,"losses":1,"wins":2},"thinkingmachines/inkling":{"draws":36,"losses":44,"wins":60},"x-ai/grok-4.5":{"draws":25,"losses":66,"wins":19},"x-ai/grok-build-0.1":{"draws":1,"losses":2,"wins":3},"xiaomi/mimo-v2.5":{"draws":10,"losses":6,"wins":12},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":10,"wins":0},"z-ai/glm-5.2":{"draws":13,"losses":8,"wins":3}},"minimax/minimax-m3":{"claude-fable-5":{"draws":1,"losses":5,"wins":0},"claude-opus-4-5":{"draws":7,"losses":12,"wins":3},"claude-opus-4-8":{"draws":6,"losses":8,"wins":0},"claude-opus-5":{"draws":0,"losses":11,"wins":1},"claude-sonnet-5":{"draws":8,"losses":3,"wins":1},"cohere/north-mini-code":{"draws":2,"losses":6,"wins":8},"deepseek/deepseek-v4-flash":{"draws":8,"losses":11,"wins":23},"deepseek/deepseek-v4-pro":{"draws":3,"losses":4,"wins":5},"google/gemini-3.1-flash-lite":{"draws":3,"losses":10,"wins":3},"google/gemini-3.5-flash":{"draws":2,"losses":2,"wins":0},"google/gemini-3.5-flash-lite":{"draws":3,"losses":1,"wins":2},"google/gemini-3.6-flash":{"draws":5,"losses":3,"wins":0},"google/gemma-4-31b-it":{"draws":0,"losses":5,"wins":7},"gpt-4.1":{"draws":0,"losses":7,"wins":1},"gpt-5":{"draws":6,"losses":9,"wins":5},"gpt-5.4":{"draws":5,"losses":11,"wins":4},"gpt-5.4-mini":{"draws":27,"losses":27,"wins":22},"gpt-5.4-nano":{"draws":37,"losses":30,"wins":25},"gpt-5.5":{"draws":6,"losses":10,"wins":6},"gpt-5.6-luna":{"draws":10,"losses":4,"wins":6},"gpt-5.6-sol":{"draws":6,"losses":10,"wins":0},"gpt-5.6-terra":{"draws":6,"losses":4,"wins":6},"inclusionai/ling-3.0-flash":{"draws":2,"losses":1,"wins":1},"meituan/longcat-2.0":{"draws":0,"losses":2,"wins":0},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":3,"wins":0},"moonshotai/kimi-k3":{"draws":9,"losses":16,"wins":5},"nex-agi/nex-n2-pro":{"draws":4,"losses":2,"wins":12},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":5,"wins":7},"o3":{"draws":4,"losses":8,"wins":4},"openai/gpt-oss-120b":{"draws":3,"losses":4,"wins":5},"qwen/qwen3.7-max":{"draws":4,"losses":8,"wins":6},"qwen/qwen3.7-plus":{"draws":4,"losses":5,"wins":7},"stepfun/step-3.7-flash":{"draws":2,"losses":2,"wins":6},"tencent/hy3-preview":{"draws":4,"losses":4,"wins":2},"thinkingmachines/inkling":{"draws":2,"losses":1,"wins":5},"x-ai/grok-4.5":{"draws":16,"losses":20,"wins":2},"x-ai/grok-build-0.1":{"draws":5,"losses":6,"wins":3},"xiaomi/mimo-v2.5":{"draws":15,"losses":16,"wins":15},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":9,"wins":5},"z-ai/glm-5.2":{"draws":10,"losses":7,"wins":9}},"mistralai/mistral-medium-3-5":{"claude-opus-4-5":{"draws":0,"losses":14,"wins":0},"claude-opus-4-8":{"draws":0,"losses":6,"wins":2},"claude-sonnet-5":{"draws":2,"losses":10,"wins":4},"cohere/north-mini-code":{"draws":2,"losses":4,"wins":0},"deepseek/deepseek-v4-flash":{"draws":11,"losses":18,"wins":21},"deepseek/deepseek-v4-pro":{"draws":2,"losses":7,"wins":1},"google/gemini-3.1-flash-lite":{"draws":2,"losses":11,"wins":7},"google/gemini-3.5-flash":{"draws":0,"losses":4,"wins":0},"google/gemini-3.5-flash-lite":{"draws":0,"losses":6,"wins":4},"google/gemini-3.6-flash":{"draws":2,"losses":0,"wins":0},"google/gemma-4-31b-it":{"draws":2,"losses":5,"wins":5},"gpt-5":{"draws":0,"losses":6,"wins":2},"gpt-5.4":{"draws":1,"losses":5,"wins":0},"gpt-5.4-mini":{"draws":10,"losses":21,"wins":9},"gpt-5.4-nano":{"draws":9,"losses":19,"wins":18},"gpt-5.5":{"draws":2,"losses":4,"wins":0},"gpt-5.6-luna":{"draws":0,"losses":3,"wins":6},"gpt-5.6-sol":{"draws":0,"losses":8,"wins":0},"gpt-5.6-terra":{"draws":2,"losses":12,"wins":0},"inclusionai/ling-3.0-flash":{"draws":2,"losses":0,"wins":4},"meituan/longcat-2.0":{"draws":0,"losses":2,"wins":2},"minimax/minimax-m3":{"draws":0,"losses":4,"wins":0},"mistralai/mistral-medium-3-5":{"draws":0,"losses":2,"wins":2},"moonshotai/kimi-k3":{"draws":3,"losses":21,"wins":0},"nex-agi/nex-n2-pro":{"draws":2,"losses":2,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":11,"wins":7},"o3":{"draws":0,"losses":10,"wins":0},"openai/gpt-oss-120b":{"draws":4,"losses":7,"wins":1},"poolside/laguna-s-2.1":{"draws":0,"losses":3,"wins":1},"qwen/qwen3.7-max":{"draws":2,"losses":5,"wins":3},"qwen/qwen3.7-plus":{"draws":2,"losses":3,"wins":3},"stepfun/step-3.7-flash":{"draws":0,"losses":11,"wins":7},"tencent/hy3-preview":{"draws":2,"losses":6,"wins":4},"thinkingmachines/inkling":{"draws":4,"losses":5,"wins":5},"x-ai/grok-4.5":{"draws":0,"losses":8,"wins":0},"x-ai/grok-build-0.1":{"draws":0,"losses":4,"wins":0},"xiaomi/mimo-v2.5":{"draws":3,"losses":17,"wins":8},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":4,"wins":0},"z-ai/glm-5.2":{"draws":2,"losses":20,"wins":12}},"moonshotai/kimi-k2.7-code":{"claude-fable-5":{"draws":0,"losses":8,"wins":2},"claude-opus-4-5":{"draws":4,"losses":8,"wins":6},"claude-opus-4-8":{"draws":2,"losses":3,"wins":3},"claude-opus-5":{"draws":5,"losses":8,"wins":1},"claude-sonnet-5":{"draws":3,"losses":4,"wins":1},"cohere/north-mini-code":{"draws":0,"losses":2,"wins":2},"deepseek/deepseek-v4-flash":{"draws":3,"losses":3,"wins":4},"deepseek/deepseek-v4-pro":{"draws":2,"losses":3,"wins":1},"google/gemini-3.1-flash-lite":{"draws":4,"losses":0,"wins":4},"google/gemini-3.5-flash":{"draws":0,"losses":2,"wins":4},"google/gemini-3.5-flash-lite":{"draws":0,"losses":2,"wins":0},"google/gemini-3.6-flash":{"draws":0,"losses":1,"wins":1},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":8},"gpt-4.1":{"draws":2,"losses":1,"wins":1},"gpt-5":{"draws":2,"losses":6,"wins":2},"gpt-5.4":{"draws":5,"losses":3,"wins":4},"gpt-5.4-mini":{"draws":9,"losses":5,"wins":16},"gpt-5.4-nano":{"draws":8,"losses":7,"wins":9},"gpt-5.5":{"draws":6,"losses":1,"wins":3},"gpt-5.6-luna":{"draws":3,"losses":2,"wins":3},"gpt-5.6-sol":{"draws":2,"losses":7,"wins":1},"gpt-5.6-terra":{"draws":1,"losses":4,"wins":3},"meituan/longcat-2.0":{"draws":0,"losses":1,"wins":3},"minimax/minimax-m3":{"draws":3,"losses":0,"wins":3},"moonshotai/kimi-k3":{"draws":7,"losses":8,"wins":5},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":0,"wins":0},"o3":{"draws":0,"losses":4,"wins":4},"openai/gpt-oss-120b":{"draws":2,"losses":0,"wins":0},"poolside/laguna-s-2.1":{"draws":0,"losses":1,"wins":1},"qwen/qwen3.7-plus":{"draws":5,"losses":0,"wins":5},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":0},"tencent/hy3-preview":{"draws":0,"losses":0,"wins":2},"x-ai/grok-4.5":{"draws":2,"losses":31,"wins":1},"x-ai/grok-build-0.1":{"draws":0,"losses":1,"wins":5},"xiaomi/mimo-v2.5":{"draws":8,"losses":6,"wins":10},"z-ai/glm-5.2":{"draws":3,"losses":7,"wins":8}},"moonshotai/kimi-k3":{"claude-fable-5":{"draws":12,"losses":41,"wins":7},"claude-opus-4-5":{"draws":27,"losses":19,"wins":42},"claude-opus-4-8":{"draws":21,"losses":25,"wins":28},"claude-opus-5":{"draws":22,"losses":70,"wins":14},"claude-sonnet-5":{"draws":17,"losses":11,"wins":22},"cohere/north-mini-code":{"draws":5,"losses":1,"wins":12},"deepseek/deepseek-v4-flash":{"draws":28,"losses":11,"wins":49},"deepseek/deepseek-v4-pro":{"draws":11,"losses":12,"wins":15},"google/gemini-3.1-flash-lite":{"draws":13,"losses":1,"wins":22},"google/gemini-3.5-flash":{"draws":21,"losses":16,"wins":23},"google/gemini-3.5-flash-lite":{"draws":66,"losses":28,"wins":80},"google/gemini-3.6-flash":{"draws":57,"losses":42,"wins":51},"google/gemma-4-31b-it":{"draws":11,"losses":3,"wins":8},"gpt-4.1":{"draws":4,"losses":5,"wins":3},"gpt-5":{"draws":21,"losses":19,"wins":10},"gpt-5.4":{"draws":18,"losses":44,"wins":16},"gpt-5.4-mini":{"draws":51,"losses":24,"wins":43},"gpt-5.4-nano":{"draws":48,"losses":41,"wins":68},"gpt-5.5":{"draws":27,"losses":29,"wins":18},"gpt-5.6-luna":{"draws":15,"losses":18,"wins":15},"gpt-5.6-sol":{"draws":21,"losses":59,"wins":34},"gpt-5.6-terra":{"draws":34,"losses":16,"wins":30},"inclusionai/ling-3.0-flash":{"draws":27,"losses":3,"wins":20},"meituan/longcat-2.0":{"draws":35,"losses":12,"wins":40},"minimax/minimax-m3":{"draws":9,"losses":5,"wins":16},"mistralai/mistral-medium-3-5":{"draws":3,"losses":0,"wins":21},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":5,"wins":8},"moonshotai/kimi-k3":{"draws":58,"losses":45,"wins":45},"nex-agi/nex-n2-pro":{"draws":6,"losses":4,"wins":20},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":27,"losses":6,"wins":27},"o3":{"draws":11,"losses":12,"wins":27},"openai/gpt-oss-120b":{"draws":29,"losses":2,"wins":29},"poolside/laguna-s-2.1":{"draws":45,"losses":17,"wins":28},"qwen/qwen3.7-max":{"draws":15,"losses":12,"wins":13},"qwen/qwen3.7-plus":{"draws":7,"losses":3,"wins":4},"stepfun/step-3.7-flash":{"draws":14,"losses":5,"wins":25},"tencent/hy3-preview":{"draws":12,"losses":14,"wins":20},"thinkingmachines/inkling":{"draws":36,"losses":12,"wins":44},"x-ai/grok-4.5":{"draws":72,"losses":109,"wins":95},"x-ai/grok-build-0.1":{"draws":11,"losses":0,"wins":5},"xiaomi/mimo-v2.5":{"draws":26,"losses":17,"wins":29},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":7,"wins":13},"z-ai/glm-5.2":{"draws":41,"losses":26,"wins":37}},"nex-agi/nex-n2-pro":{"claude-fable-5":{"draws":0,"losses":4,"wins":0},"claude-opus-4-5":{"draws":6,"losses":5,"wins":3},"claude-opus-4-8":{"draws":10,"losses":6,"wins":2},"claude-opus-5":{"draws":0,"losses":2,"wins":0},"claude-sonnet-5":{"draws":4,"losses":14,"wins":4},"cohere/north-mini-code":{"draws":6,"losses":6,"wins":6},"deepseek/deepseek-v4-flash":{"draws":18,"losses":10,"wins":20},"deepseek/deepseek-v4-pro":{"draws":2,"losses":3,"wins":7},"google/gemini-3.1-flash-lite":{"draws":2,"losses":8,"wins":10},"google/gemini-3.5-flash":{"draws":2,"losses":2,"wins":0},"google/gemini-3.5-flash-lite":{"draws":0,"losses":4,"wins":0},"google/gemini-3.6-flash":{"draws":0,"losses":2,"wins":0},"google/gemma-4-31b-it":{"draws":2,"losses":4,"wins":2},"gpt-4.1":{"draws":3,"losses":2,"wins":1},"gpt-5":{"draws":0,"losses":4,"wins":2},"gpt-5.4":{"draws":6,"losses":10,"wins":0},"gpt-5.4-mini":{"draws":19,"losses":24,"wins":13},"gpt-5.4-nano":{"draws":21,"losses":17,"wins":24},"gpt-5.5":{"draws":4,"losses":7,"wins":3},"gpt-5.6-luna":{"draws":9,"losses":4,"wins":7},"gpt-5.6-sol":{"draws":0,"losses":5,"wins":3},"gpt-5.6-terra":{"draws":9,"losses":9,"wins":6},"inclusionai/ling-3.0-flash":{"draws":1,"losses":2,"wins":5},"meituan/longcat-2.0":{"draws":0,"losses":0,"wins":2},"minimax/minimax-m3":{"draws":4,"losses":12,"wins":2},"mistralai/mistral-medium-3-5":{"draws":2,"losses":4,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":6,"losses":20,"wins":4},"nex-agi/nex-n2-pro":{"draws":4,"losses":0,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":6,"wins":4},"o3":{"draws":4,"losses":4,"wins":0},"openai/gpt-oss-120b":{"draws":11,"losses":6,"wins":3},"poolside/laguna-s-2.1":{"draws":0,"losses":4,"wins":0},"qwen/qwen3.7-max":{"draws":5,"losses":9,"wins":2},"qwen/qwen3.7-plus":{"draws":2,"losses":5,"wins":3},"stepfun/step-3.7-flash":{"draws":5,"losses":2,"wins":5},"tencent/hy3-preview":{"draws":9,"losses":0,"wins":3},"thinkingmachines/inkling":{"draws":0,"losses":10,"wins":4},"x-ai/grok-4.5":{"draws":5,"losses":17,"wins":4},"x-ai/grok-build-0.1":{"draws":4,"losses":4,"wins":2},"xiaomi/mimo-v2.5":{"draws":12,"losses":20,"wins":14},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":5,"wins":5},"z-ai/glm-5.2":{"draws":10,"losses":14,"wins":8}},"nvidia/nemotron-3-ultra-550b-a55b":{"claude-fable-5":{"draws":0,"losses":2,"wins":0},"claude-opus-4-5":{"draws":16,"losses":15,"wins":7},"claude-opus-4-8":{"draws":7,"losses":15,"wins":8},"claude-opus-5":{"draws":2,"losses":4,"wins":0},"claude-sonnet-5":{"draws":25,"losses":14,"wins":9},"cohere/north-mini-code":{"draws":3,"losses":7,"wins":8},"deepseek/deepseek-v4-flash":{"draws":28,"losses":20,"wins":14},"deepseek/deepseek-v4-pro":{"draws":10,"losses":7,"wins":5},"google/gemini-3.1-flash-lite":{"draws":11,"losses":11,"wins":15},"google/gemini-3.5-flash":{"draws":8,"losses":12,"wins":2},"google/gemini-3.5-flash-lite":{"draws":3,"losses":6,"wins":3},"google/gemini-3.6-flash":{"draws":7,"losses":1,"wins":2},"google/gemma-4-31b-it":{"draws":0,"losses":6,"wins":6},"gpt-4.1":{"draws":4,"losses":4,"wins":2},"gpt-5":{"draws":12,"losses":6,"wins":4},"gpt-5.4":{"draws":11,"losses":9,"wins":2},"gpt-5.4-mini":{"draws":45,"losses":23,"wins":18},"gpt-5.4-nano":{"draws":56,"losses":19,"wins":23},"gpt-5.5":{"draws":14,"losses":5,"wins":1},"gpt-5.6-luna":{"draws":12,"losses":10,"wins":6},"gpt-5.6-sol":{"draws":2,"losses":20,"wins":6},"gpt-5.6-terra":{"draws":22,"losses":14,"wins":4},"inclusionai/ling-3.0-flash":{"draws":4,"losses":1,"wins":3},"meituan/longcat-2.0":{"draws":6,"losses":3,"wins":3},"minimax/minimax-m3":{"draws":12,"losses":7,"wins":5},"mistralai/mistral-medium-3-5":{"draws":2,"losses":7,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":27,"losses":27,"wins":6},"nex-agi/nex-n2-pro":{"draws":6,"losses":4,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":7,"wins":7},"o3":{"draws":5,"losses":12,"wins":3},"openai/gpt-oss-120b":{"draws":15,"losses":5,"wins":2},"poolside/laguna-s-2.1":{"draws":4,"losses":3,"wins":1},"qwen/qwen3.7-max":{"draws":8,"losses":6,"wins":4},"qwen/qwen3.7-plus":{"draws":5,"losses":5,"wins":4},"stepfun/step-3.7-flash":{"draws":9,"losses":8,"wins":5},"tencent/hy3-preview":{"draws":12,"losses":10,"wins":4},"thinkingmachines/inkling":{"draws":4,"losses":6,"wins":4},"x-ai/grok-4.5":{"draws":13,"losses":20,"wins":11},"x-ai/grok-build-0.1":{"draws":12,"losses":4,"wins":6},"xiaomi/mimo-v2.5":{"draws":17,"losses":9,"wins":8},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":9,"wins":1},"z-ai/glm-5.2":{"draws":33,"losses":30,"wins":25}},"o3":{"claude-fable-5":{"draws":0,"losses":15,"wins":1},"claude-opus-4-5":{"draws":9,"losses":18,"wins":17},"claude-opus-4-8":{"draws":5,"losses":14,"wins":7},"claude-opus-5":{"draws":0,"losses":22,"wins":0},"claude-sonnet-5":{"draws":3,"losses":12,"wins":13},"cohere/north-mini-code":{"draws":1,"losses":4,"wins":9},"deepseek/deepseek-v4-flash":{"draws":9,"losses":12,"wins":25},"deepseek/deepseek-v4-pro":{"draws":3,"losses":7,"wins":6},"google/gemini-3.1-flash-lite":{"draws":6,"losses":4,"wins":10},"google/gemini-3.5-flash":{"draws":0,"losses":3,"wins":7},"google/gemini-3.5-flash-lite":{"draws":0,"losses":1,"wins":5},"google/gemini-3.6-flash":{"draws":1,"losses":1,"wins":0},"google/gemma-4-31b-it":{"draws":4,"losses":1,"wins":5},"gpt-4.1":{"draws":1,"losses":0,"wins":1},"gpt-5":{"draws":2,"losses":13,"wins":5},"gpt-5.4":{"draws":5,"losses":9,"wins":6},"gpt-5.4-mini":{"draws":12,"losses":21,"wins":41},"gpt-5.4-nano":{"draws":20,"losses":28,"wins":22},"gpt-5.5":{"draws":5,"losses":11,"wins":2},"gpt-5.6-luna":{"draws":2,"losses":8,"wins":8},"gpt-5.6-sol":{"draws":5,"losses":9,"wins":6},"gpt-5.6-terra":{"draws":7,"losses":7,"wins":6},"meituan/longcat-2.0":{"draws":0,"losses":1,"wins":3},"minimax/minimax-m3":{"draws":4,"losses":4,"wins":8},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":4,"wins":4},"moonshotai/kimi-k3":{"draws":11,"losses":27,"wins":12},"nex-agi/nex-n2-pro":{"draws":4,"losses":0,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":3,"wins":12},"o3":{"draws":0,"losses":2,"wins":2},"openai/gpt-oss-120b":{"draws":8,"losses":4,"wins":12},"poolside/laguna-s-2.1":{"draws":0,"losses":0,"wins":2},"qwen/qwen3.7-max":{"draws":9,"losses":4,"wins":3},"qwen/qwen3.7-plus":{"draws":0,"losses":4,"wins":6},"stepfun/step-3.7-flash":{"draws":4,"losses":5,"wins":13},"tencent/hy3-preview":{"draws":11,"losses":7,"wins":6},"thinkingmachines/inkling":{"draws":0,"losses":1,"wins":7},"x-ai/grok-4.5":{"draws":11,"losses":43,"wins":20},"x-ai/grok-build-0.1":{"draws":3,"losses":0,"wins":7},"xiaomi/mimo-v2.5":{"draws":17,"losses":7,"wins":30},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":2,"wins":6},"z-ai/glm-5.2":{"draws":7,"losses":22,"wins":17}},"openai/gpt-oss-120b":{"claude-fable-5":{"draws":1,"losses":7,"wins":0},"claude-opus-4-5":{"draws":15,"losses":10,"wins":7},"claude-opus-4-8":{"draws":8,"losses":7,"wins":5},"claude-sonnet-5":{"draws":4,"losses":12,"wins":6},"cohere/north-mini-code":{"draws":12,"losses":3,"wins":5},"deepseek/deepseek-v4-flash":{"draws":30,"losses":9,"wins":17},"deepseek/deepseek-v4-pro":{"draws":4,"losses":3,"wins":3},"google/gemini-3.1-flash-lite":{"draws":6,"losses":6,"wins":8},"google/gemini-3.5-flash":{"draws":4,"losses":3,"wins":3},"google/gemini-3.5-flash-lite":{"draws":6,"losses":0,"wins":0},"google/gemini-3.6-flash":{"draws":1,"losses":1,"wins":0},"google/gemma-4-31b-it":{"draws":2,"losses":9,"wins":3},"gpt-4.1":{"draws":3,"losses":2,"wins":3},"gpt-5":{"draws":7,"losses":2,"wins":1},"gpt-5.4":{"draws":10,"losses":10,"wins":2},"gpt-5.4-mini":{"draws":30,"losses":24,"wins":26},"gpt-5.4-nano":{"draws":52,"losses":26,"wins":32},"gpt-5.5":{"draws":11,"losses":9,"wins":2},"gpt-5.6-luna":{"draws":16,"losses":13,"wins":11},"gpt-5.6-sol":{"draws":8,"losses":8,"wins":4},"gpt-5.6-terra":{"draws":7,"losses":8,"wins":3},"inclusionai/ling-3.0-flash":{"draws":3,"losses":1,"wins":2},"meituan/longcat-2.0":{"draws":2,"losses":0,"wins":0},"minimax/minimax-m3":{"draws":3,"losses":5,"wins":4},"mistralai/mistral-medium-3-5":{"draws":4,"losses":1,"wins":7},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":29,"losses":29,"wins":2},"nex-agi/nex-n2-pro":{"draws":11,"losses":3,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":2,"wins":5},"o3":{"draws":8,"losses":12,"wins":4},"openai/gpt-oss-120b":{"draws":10,"losses":1,"wins":1},"poolside/laguna-s-2.1":{"draws":1,"losses":1,"wins":0},"qwen/qwen3.7-max":{"draws":12,"losses":1,"wins":3},"qwen/qwen3.7-plus":{"draws":8,"losses":2,"wins":8},"stepfun/step-3.7-flash":{"draws":12,"losses":15,"wins":5},"tencent/hy3-preview":{"draws":8,"losses":4,"wins":2},"thinkingmachines/inkling":{"draws":3,"losses":0,"wins":5},"x-ai/grok-4.5":{"draws":15,"losses":27,"wins":4},"x-ai/grok-build-0.1":{"draws":3,"losses":9,"wins":2},"xiaomi/mimo-v2.5":{"draws":18,"losses":13,"wins":15},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":10,"wins":1},"z-ai/glm-5.2":{"draws":25,"losses":14,"wins":15}},"poolside/laguna-s-2.1":{"claude-fable-5":{"draws":0,"losses":2,"wins":4},"claude-opus-4-5":{"draws":0,"losses":2,"wins":0},"claude-opus-4-8":{"draws":0,"losses":5,"wins":1},"claude-opus-5":{"draws":2,"losses":30,"wins":2},"claude-sonnet-5":{"draws":3,"losses":1,"wins":0},"cohere/north-mini-code":{"draws":4,"losses":4,"wins":2},"deepseek/deepseek-v4-flash":{"draws":7,"losses":3,"wins":8},"deepseek/deepseek-v4-pro":{"draws":0,"losses":2,"wins":2},"google/gemini-3.1-flash-lite":{"draws":4,"losses":1,"wins":1},"google/gemini-3.5-flash":{"draws":9,"losses":1,"wins":2},"google/gemini-3.5-flash-lite":{"draws":86,"losses":49,"wins":77},"google/gemini-3.6-flash":{"draws":66,"losses":66,"wins":26},"gpt-4.1":{"draws":4,"losses":1,"wins":1},"gpt-5":{"draws":4,"losses":1,"wins":3},"gpt-5.4":{"draws":0,"losses":2,"wins":2},"gpt-5.4-mini":{"draws":7,"losses":9,"wins":6},"gpt-5.4-nano":{"draws":14,"losses":4,"wins":10},"gpt-5.5":{"draws":1,"losses":2,"wins":3},"gpt-5.6-luna":{"draws":2,"losses":5,"wins":1},"gpt-5.6-sol":{"draws":0,"losses":4,"wins":2},"gpt-5.6-terra":{"draws":2,"losses":1,"wins":1},"inclusionai/ling-3.0-flash":{"draws":33,"losses":11,"wins":20},"meituan/longcat-2.0":{"draws":45,"losses":33,"wins":38},"mistralai/mistral-medium-3-5":{"draws":0,"losses":1,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":1},"moonshotai/kimi-k3":{"draws":45,"losses":28,"wins":17},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":1,"wins":3},"o3":{"draws":0,"losses":2,"wins":0},"openai/gpt-oss-120b":{"draws":1,"losses":0,"wins":1},"poolside/laguna-s-2.1":{"draws":44,"losses":22,"wins":22},"qwen/qwen3.7-max":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.7-plus":{"draws":1,"losses":1,"wins":0},"tencent/hy3-preview":{"draws":0,"losses":4,"wins":4},"thinkingmachines/inkling":{"draws":34,"losses":29,"wins":45},"x-ai/grok-4.5":{"draws":29,"losses":58,"wins":21},"x-ai/grok-build-0.1":{"draws":1,"losses":3,"wins":0},"xiaomi/mimo-v2.5":{"draws":4,"losses":4,"wins":2},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":2,"wins":2},"z-ai/glm-5.2":{"draws":12,"losses":10,"wins":10}},"qwen/qwen3.7-max":{"claude-fable-5":{"draws":1,"losses":7,"wins":2},"claude-opus-4-5":{"draws":11,"losses":14,"wins":7},"claude-opus-4-8":{"draws":2,"losses":11,"wins":7},"claude-opus-5":{"draws":0,"losses":17,"wins":5},"claude-sonnet-5":{"draws":5,"losses":7,"wins":4},"cohere/north-mini-code":{"draws":3,"losses":2,"wins":7},"deepseek/deepseek-v4-flash":{"draws":14,"losses":8,"wins":16},"deepseek/deepseek-v4-pro":{"draws":9,"losses":7,"wins":6},"google/gemini-3.1-flash-lite":{"draws":4,"losses":2,"wins":2},"google/gemini-3.5-flash":{"draws":3,"losses":2,"wins":7},"google/gemini-3.5-flash-lite":{"draws":2,"losses":0,"wins":0},"google/gemini-3.6-flash":{"draws":1,"losses":2,"wins":1},"google/gemma-4-31b-it":{"draws":1,"losses":3,"wins":4},"gpt-4.1":{"draws":6,"losses":0,"wins":0},"gpt-5":{"draws":6,"losses":6,"wins":4},"gpt-5.4":{"draws":4,"losses":10,"wins":2},"gpt-5.4-mini":{"draws":24,"losses":19,"wins":23},"gpt-5.4-nano":{"draws":36,"losses":15,"wins":27},"gpt-5.5":{"draws":7,"losses":7,"wins":6},"gpt-5.6-luna":{"draws":18,"losses":7,"wins":3},"gpt-5.6-sol":{"draws":6,"losses":15,"wins":9},"gpt-5.6-terra":{"draws":7,"losses":7,"wins":4},"inclusionai/ling-3.0-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":2,"losses":0,"wins":2},"minimax/minimax-m3":{"draws":4,"losses":6,"wins":8},"mistralai/mistral-medium-3-5":{"draws":2,"losses":3,"wins":5},"moonshotai/kimi-k3":{"draws":15,"losses":13,"wins":12},"nex-agi/nex-n2-pro":{"draws":5,"losses":2,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":4,"wins":6},"o3":{"draws":9,"losses":3,"wins":4},"openai/gpt-oss-120b":{"draws":12,"losses":3,"wins":1},"poolside/laguna-s-2.1":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.7-max":{"draws":4,"losses":2,"wins":2},"qwen/qwen3.7-plus":{"draws":5,"losses":5,"wins":6},"stepfun/step-3.7-flash":{"draws":4,"losses":3,"wins":9},"tencent/hy3-preview":{"draws":8,"losses":3,"wins":3},"thinkingmachines/inkling":{"draws":8,"losses":1,"wins":1},"x-ai/grok-4.5":{"draws":17,"losses":24,"wins":19},"x-ai/grok-build-0.1":{"draws":0,"losses":8,"wins":2},"xiaomi/mimo-v2.5":{"draws":10,"losses":10,"wins":12},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":3,"wins":11},"z-ai/glm-5.2":{"draws":14,"losses":11,"wins":11}},"qwen/qwen3.7-plus":{"claude-fable-5":{"draws":1,"losses":7,"wins":0},"claude-opus-4-5":{"draws":18,"losses":11,"wins":5},"claude-opus-4-8":{"draws":4,"losses":15,"wins":5},"claude-opus-5":{"draws":0,"losses":2,"wins":0},"claude-sonnet-5":{"draws":10,"losses":5,"wins":3},"cohere/north-mini-code":{"draws":7,"losses":3,"wins":8},"deepseek/deepseek-v4-flash":{"draws":17,"losses":14,"wins":15},"deepseek/deepseek-v4-pro":{"draws":2,"losses":4,"wins":0},"google/gemini-3.1-flash-lite":{"draws":1,"losses":2,"wins":11},"google/gemini-3.5-flash":{"draws":2,"losses":9,"wins":1},"google/gemini-3.5-flash-lite":{"draws":4,"losses":3,"wins":3},"google/gemini-3.6-flash":{"draws":2,"losses":0,"wins":0},"google/gemma-4-31b-it":{"draws":0,"losses":11,"wins":3},"gpt-5":{"draws":2,"losses":1,"wins":1},"gpt-5.4":{"draws":6,"losses":8,"wins":0},"gpt-5.4-mini":{"draws":24,"losses":14,"wins":30},"gpt-5.4-nano":{"draws":23,"losses":11,"wins":40},"gpt-5.5":{"draws":7,"losses":5,"wins":0},"gpt-5.6-luna":{"draws":9,"losses":5,"wins":8},"gpt-5.6-sol":{"draws":4,"losses":5,"wins":3},"gpt-5.6-terra":{"draws":9,"losses":6,"wins":11},"inclusionai/ling-3.0-flash":{"draws":0,"losses":0,"wins":2},"minimax/minimax-m3":{"draws":4,"losses":7,"wins":5},"mistralai/mistral-medium-3-5":{"draws":2,"losses":3,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":5,"wins":0},"moonshotai/kimi-k3":{"draws":7,"losses":4,"wins":3},"nex-agi/nex-n2-pro":{"draws":2,"losses":3,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":4,"wins":5},"o3":{"draws":0,"losses":6,"wins":4},"openai/gpt-oss-120b":{"draws":8,"losses":8,"wins":2},"poolside/laguna-s-2.1":{"draws":1,"losses":0,"wins":1},"qwen/qwen3.7-max":{"draws":5,"losses":6,"wins":5},"qwen/qwen3.7-plus":{"draws":4,"losses":4,"wins":4},"stepfun/step-3.7-flash":{"draws":0,"losses":7,"wins":5},"tencent/hy3-preview":{"draws":2,"losses":5,"wins":3},"thinkingmachines/inkling":{"draws":2,"losses":2,"wins":0},"x-ai/grok-4.5":{"draws":7,"losses":26,"wins":3},"x-ai/grok-build-0.1":{"draws":2,"losses":2,"wins":8},"xiaomi/mimo-v2.5":{"draws":9,"losses":11,"wins":10},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":11,"wins":1},"z-ai/glm-5.2":{"draws":17,"losses":19,"wins":10}},"stepfun/step-3.7-flash":{"claude-fable-5":{"draws":2,"losses":10,"wins":0},"claude-opus-4-5":{"draws":15,"losses":13,"wins":4},"claude-opus-4-8":{"draws":0,"losses":4,"wins":4},"claude-opus-5":{"draws":0,"losses":2,"wins":0},"claude-sonnet-5":{"draws":4,"losses":11,"wins":1},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":10},"deepseek/deepseek-v4-flash":{"draws":18,"losses":20,"wins":24},"deepseek/deepseek-v4-pro":{"draws":7,"losses":11,"wins":2},"google/gemini-3.1-flash-lite":{"draws":4,"losses":5,"wins":9},"google/gemini-3.5-flash":{"draws":2,"losses":4,"wins":2},"google/gemini-3.6-flash":{"draws":0,"losses":2,"wins":0},"google/gemma-4-31b-it":{"draws":0,"losses":3,"wins":7},"gpt-4.1":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":4,"losses":8,"wins":0},"gpt-5.4":{"draws":4,"losses":3,"wins":3},"gpt-5.4-mini":{"draws":21,"losses":34,"wins":23},"gpt-5.4-nano":{"draws":20,"losses":23,"wins":21},"gpt-5.5":{"draws":5,"losses":9,"wins":2},"gpt-5.6-luna":{"draws":3,"losses":5,"wins":12},"gpt-5.6-sol":{"draws":4,"losses":8,"wins":4},"gpt-5.6-terra":{"draws":12,"losses":9,"wins":1},"meituan/longcat-2.0":{"draws":2,"losses":2,"wins":0},"minimax/minimax-m3":{"draws":2,"losses":6,"wins":2},"mistralai/mistral-medium-3-5":{"draws":0,"losses":7,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":14,"losses":25,"wins":5},"nex-agi/nex-n2-pro":{"draws":5,"losses":5,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":5,"wins":8},"o3":{"draws":4,"losses":13,"wins":5},"openai/gpt-oss-120b":{"draws":12,"losses":5,"wins":15},"qwen/qwen3.7-max":{"draws":4,"losses":9,"wins":3},"qwen/qwen3.7-plus":{"draws":0,"losses":5,"wins":7},"tencent/hy3-preview":{"draws":5,"losses":8,"wins":9},"thinkingmachines/inkling":{"draws":2,"losses":2,"wins":10},"x-ai/grok-4.5":{"draws":9,"losses":37,"wins":8},"x-ai/grok-build-0.1":{"draws":4,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":22,"losses":16,"wins":16},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":4,"wins":1},"z-ai/glm-5.2":{"draws":2,"losses":16,"wins":6}},"tencent/hy3-preview":{"claude-fable-5":{"draws":1,"losses":6,"wins":5},"claude-opus-4-5":{"draws":12,"losses":15,"wins":5},"claude-opus-4-8":{"draws":3,"losses":11,"wins":4},"claude-opus-5":{"draws":1,"losses":7,"wins":2},"claude-sonnet-5":{"draws":7,"losses":10,"wins":7},"cohere/north-mini-code":{"draws":3,"losses":2,"wins":3},"deepseek/deepseek-v4-flash":{"draws":22,"losses":13,"wins":15},"deepseek/deepseek-v4-pro":{"draws":4,"losses":6,"wins":6},"google/gemini-3.1-flash-lite":{"draws":2,"losses":6,"wins":6},"google/gemini-3.5-flash":{"draws":2,"losses":8,"wins":2},"google/gemini-3.5-flash-lite":{"draws":4,"losses":3,"wins":1},"google/gemini-3.6-flash":{"draws":4,"losses":0,"wins":4},"google/gemma-4-31b-it":{"draws":2,"losses":1,"wins":5},"gpt-4.1":{"draws":4,"losses":4,"wins":0},"gpt-5":{"draws":1,"losses":7,"wins":6},"gpt-5.4":{"draws":12,"losses":14,"wins":4},"gpt-5.4-mini":{"draws":21,"losses":23,"wins":12},"gpt-5.4-nano":{"draws":35,"losses":14,"wins":25},"gpt-5.5":{"draws":14,"losses":11,"wins":5},"gpt-5.6-luna":{"draws":8,"losses":7,"wins":5},"gpt-5.6-sol":{"draws":8,"losses":19,"wins":9},"gpt-5.6-terra":{"draws":10,"losses":2,"wins":2},"inclusionai/ling-3.0-flash":{"draws":4,"losses":1,"wins":3},"meituan/longcat-2.0":{"draws":5,"losses":2,"wins":1},"minimax/minimax-m3":{"draws":4,"losses":2,"wins":4},"mistralai/mistral-medium-3-5":{"draws":2,"losses":4,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":12,"losses":20,"wins":14},"nex-agi/nex-n2-pro":{"draws":9,"losses":3,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":4,"wins":10},"o3":{"draws":11,"losses":6,"wins":7},"openai/gpt-oss-120b":{"draws":8,"losses":2,"wins":4},"poolside/laguna-s-2.1":{"draws":0,"losses":4,"wins":4},"qwen/qwen3.7-max":{"draws":8,"losses":3,"wins":3},"qwen/qwen3.7-plus":{"draws":2,"losses":3,"wins":5},"stepfun/step-3.7-flash":{"draws":5,"losses":9,"wins":8},"tencent/hy3-preview":{"draws":2,"losses":1,"wins":1},"thinkingmachines/inkling":{"draws":0,"losses":2,"wins":2},"x-ai/grok-4.5":{"draws":15,"losses":28,"wins":11},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":12,"losses":11,"wins":9},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":3,"wins":6},"z-ai/glm-5.2":{"draws":29,"losses":17,"wins":14}},"thinkingmachines/inkling":{"claude-fable-5":{"draws":0,"losses":2,"wins":0},"claude-opus-4-5":{"draws":6,"losses":4,"wins":6},"claude-opus-4-8":{"draws":0,"losses":7,"wins":3},"claude-opus-5":{"draws":1,"losses":30,"wins":3},"claude-sonnet-5":{"draws":4,"losses":3,"wins":1},"cohere/north-mini-code":{"draws":3,"losses":2,"wins":1},"deepseek/deepseek-v4-flash":{"draws":11,"losses":10,"wins":17},"deepseek/deepseek-v4-pro":{"draws":2,"losses":5,"wins":1},"google/gemini-3.1-flash-lite":{"draws":7,"losses":6,"wins":7},"google/gemini-3.5-flash":{"draws":0,"losses":6,"wins":0},"google/gemini-3.5-flash-lite":{"draws":71,"losses":81,"wins":82},"google/gemini-3.6-flash":{"draws":80,"losses":96,"wins":44},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":4},"gpt-4.1":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":2,"losses":2,"wins":0},"gpt-5.4":{"draws":6,"losses":3,"wins":1},"gpt-5.4-mini":{"draws":18,"losses":14,"wins":14},"gpt-5.4-nano":{"draws":13,"losses":16,"wins":35},"gpt-5.5":{"draws":5,"losses":9,"wins":4},"gpt-5.6-luna":{"draws":7,"losses":0,"wins":1},"gpt-5.6-sol":{"draws":1,"losses":5,"wins":2},"gpt-5.6-terra":{"draws":8,"losses":2,"wins":0},"inclusionai/ling-3.0-flash":{"draws":29,"losses":27,"wins":38},"meituan/longcat-2.0":{"draws":36,"losses":60,"wins":44},"minimax/minimax-m3":{"draws":2,"losses":5,"wins":1},"mistralai/mistral-medium-3-5":{"draws":4,"losses":5,"wins":5},"moonshotai/kimi-k3":{"draws":36,"losses":44,"wins":12},"nex-agi/nex-n2-pro":{"draws":0,"losses":4,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":4,"wins":6},"o3":{"draws":0,"losses":7,"wins":1},"openai/gpt-oss-120b":{"draws":3,"losses":5,"wins":0},"poolside/laguna-s-2.1":{"draws":34,"losses":45,"wins":29},"qwen/qwen3.7-max":{"draws":8,"losses":1,"wins":1},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":2},"stepfun/step-3.7-flash":{"draws":2,"losses":10,"wins":2},"tencent/hy3-preview":{"draws":0,"losses":2,"wins":2},"thinkingmachines/inkling":{"draws":38,"losses":43,"wins":43},"x-ai/grok-4.5":{"draws":29,"losses":63,"wins":16},"x-ai/grok-build-0.1":{"draws":2,"losses":2,"wins":2},"xiaomi/mimo-v2.5":{"draws":22,"losses":15,"wins":9},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":4,"wins":4},"z-ai/glm-5.2":{"draws":7,"losses":17,"wins":10}},"x-ai/grok-4.5":{"claude-fable-5":{"draws":15,"losses":50,"wins":23},"claude-opus-4-5":{"draws":31,"losses":32,"wins":67},"claude-opus-4-8":{"draws":18,"losses":29,"wins":37},"claude-opus-5":{"draws":25,"losses":130,"wins":39},"claude-sonnet-5":{"draws":23,"losses":15,"wins":34},"cohere/north-mini-code":{"draws":5,"losses":0,"wins":13},"deepseek/deepseek-v4-flash":{"draws":27,"losses":14,"wins":55},"deepseek/deepseek-v4-pro":{"draws":9,"losses":14,"wins":31},"google/gemini-3.1-flash-lite":{"draws":6,"losses":1,"wins":17},"google/gemini-3.5-flash":{"draws":13,"losses":19,"wins":8},"google/gemini-3.5-flash-lite":{"draws":59,"losses":34,"wins":109},"google/gemini-3.6-flash":{"draws":37,"losses":79,"wins":66},"google/gemma-4-31b-it":{"draws":5,"losses":3,"wins":20},"gpt-4.1":{"draws":1,"losses":4,"wins":5},"gpt-5":{"draws":11,"losses":11,"wins":24},"gpt-5.4":{"draws":35,"losses":58,"wins":29},"gpt-5.4-mini":{"draws":52,"losses":26,"wins":92},"gpt-5.4-nano":{"draws":46,"losses":58,"wins":86},"gpt-5.5":{"draws":23,"losses":34,"wins":39},"gpt-5.6-luna":{"draws":18,"losses":24,"wins":32},"gpt-5.6-sol":{"draws":24,"losses":62,"wins":46},"gpt-5.6-terra":{"draws":25,"losses":25,"wins":44},"inclusionai/ling-3.0-flash":{"draws":17,"losses":6,"wins":43},"meituan/longcat-2.0":{"draws":25,"losses":19,"wins":66},"minimax/minimax-m3":{"draws":16,"losses":2,"wins":20},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":1,"wins":31},"moonshotai/kimi-k3":{"draws":72,"losses":95,"wins":109},"nex-agi/nex-n2-pro":{"draws":5,"losses":4,"wins":17},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":11,"wins":20},"o3":{"draws":11,"losses":20,"wins":43},"openai/gpt-oss-120b":{"draws":15,"losses":4,"wins":27},"poolside/laguna-s-2.1":{"draws":29,"losses":21,"wins":58},"qwen/qwen3.7-max":{"draws":17,"losses":19,"wins":24},"qwen/qwen3.7-plus":{"draws":7,"losses":3,"wins":26},"stepfun/step-3.7-flash":{"draws":9,"losses":8,"wins":37},"tencent/hy3-preview":{"draws":15,"losses":11,"wins":28},"thinkingmachines/inkling":{"draws":29,"losses":16,"wins":63},"x-ai/grok-4.5":{"draws":70,"losses":107,"wins":107},"x-ai/grok-build-0.1":{"draws":8,"losses":4,"wins":14},"xiaomi/mimo-v2.5":{"draws":21,"losses":12,"wins":55},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":12,"wins":24},"z-ai/glm-5.2":{"draws":16,"losses":46,"wins":72}},"x-ai/grok-build-0.1":{"claude-fable-5":{"draws":0,"losses":0,"wins":2},"claude-opus-4-5":{"draws":9,"losses":9,"wins":2},"claude-opus-4-8":{"draws":5,"losses":4,"wins":5},"claude-opus-5":{"draws":4,"losses":0,"wins":2},"claude-sonnet-5":{"draws":1,"losses":10,"wins":1},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":4},"deepseek/deepseek-v4-flash":{"draws":8,"losses":4,"wins":10},"deepseek/deepseek-v4-pro":{"draws":8,"losses":1,"wins":1},"google/gemini-3.1-flash-lite":{"draws":7,"losses":1,"wins":10},"google/gemini-3.5-flash":{"draws":4,"losses":4,"wins":0},"google/gemini-3.5-flash-lite":{"draws":0,"losses":2,"wins":2},"google/gemini-3.6-flash":{"draws":0,"losses":2,"wins":0},"google/gemma-4-31b-it":{"draws":5,"losses":4,"wins":5},"gpt-5":{"draws":6,"losses":5,"wins":3},"gpt-5.4":{"draws":2,"losses":2,"wins":0},"gpt-5.4-mini":{"draws":3,"losses":9,"wins":12},"gpt-5.4-nano":{"draws":13,"losses":6,"wins":15},"gpt-5.5":{"draws":7,"losses":2,"wins":5},"gpt-5.6-luna":{"draws":14,"losses":6,"wins":0},"gpt-5.6-sol":{"draws":4,"losses":6,"wins":6},"gpt-5.6-terra":{"draws":4,"losses":6,"wins":0},"meituan/longcat-2.0":{"draws":1,"losses":3,"wins":2},"minimax/minimax-m3":{"draws":5,"losses":3,"wins":6},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":5,"wins":1},"moonshotai/kimi-k3":{"draws":11,"losses":5,"wins":0},"nex-agi/nex-n2-pro":{"draws":4,"losses":2,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":6,"wins":4},"o3":{"draws":3,"losses":7,"wins":0},"openai/gpt-oss-120b":{"draws":3,"losses":2,"wins":9},"poolside/laguna-s-2.1":{"draws":1,"losses":0,"wins":3},"qwen/qwen3.7-max":{"draws":0,"losses":2,"wins":8},"qwen/qwen3.7-plus":{"draws":2,"losses":8,"wins":2},"stepfun/step-3.7-flash":{"draws":4,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":0,"losses":2,"wins":0},"thinkingmachines/inkling":{"draws":2,"losses":2,"wins":2},"x-ai/grok-4.5":{"draws":8,"losses":14,"wins":4},"xiaomi/mimo-v2.5":{"draws":12,"losses":5,"wins":11},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":4,"wins":0},"z-ai/glm-5.2":{"draws":4,"losses":6,"wins":4}},"xiaomi/mimo-v2.5":{"claude-fable-5":{"draws":2,"losses":12,"wins":0},"claude-opus-4-5":{"draws":33,"losses":24,"wins":19},"claude-opus-4-8":{"draws":17,"losses":24,"wins":3},"claude-opus-5":{"draws":3,"losses":6,"wins":1},"claude-sonnet-5":{"draws":35,"losses":20,"wins":13},"cohere/north-mini-code":{"draws":19,"losses":13,"wins":14},"deepseek/deepseek-v4-flash":{"draws":36,"losses":34,"wins":40},"deepseek/deepseek-v4-pro":{"draws":9,"losses":11,"wins":8},"google/gemini-3.1-flash-lite":{"draws":14,"losses":10,"wins":14},"google/gemini-3.5-flash":{"draws":13,"losses":7,"wins":6},"google/gemini-3.5-flash-lite":{"draws":6,"losses":3,"wins":1},"google/gemini-3.6-flash":{"draws":13,"losses":8,"wins":3},"google/gemma-4-31b-it":{"draws":2,"losses":12,"wins":10},"gpt-4.1":{"draws":0,"losses":6,"wins":2},"gpt-5":{"draws":18,"losses":8,"wins":12},"gpt-5.4":{"draws":21,"losses":18,"wins":5},"gpt-5.4-mini":{"draws":73,"losses":55,"wins":68},"gpt-5.4-nano":{"draws":80,"losses":50,"wins":66},"gpt-5.5":{"draws":25,"losses":9,"wins":6},"gpt-5.6-luna":{"draws":19,"losses":11,"wins":24},"gpt-5.6-sol":{"draws":10,"losses":13,"wins":9},"gpt-5.6-terra":{"draws":21,"losses":21,"wins":8},"inclusionai/ling-3.0-flash":{"draws":6,"losses":2,"wins":0},"meituan/longcat-2.0":{"draws":10,"losses":12,"wins":6},"minimax/minimax-m3":{"draws":15,"losses":15,"wins":16},"mistralai/mistral-medium-3-5":{"draws":3,"losses":8,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":10,"wins":6},"moonshotai/kimi-k3":{"draws":26,"losses":29,"wins":17},"nex-agi/nex-n2-pro":{"draws":12,"losses":14,"wins":20},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":17,"losses":8,"wins":9},"o3":{"draws":17,"losses":30,"wins":7},"openai/gpt-oss-120b":{"draws":18,"losses":15,"wins":13},"poolside/laguna-s-2.1":{"draws":4,"losses":2,"wins":4},"qwen/qwen3.7-max":{"draws":10,"losses":12,"wins":10},"qwen/qwen3.7-plus":{"draws":9,"losses":10,"wins":11},"stepfun/step-3.7-flash":{"draws":22,"losses":16,"wins":16},"tencent/hy3-preview":{"draws":12,"losses":9,"wins":11},"thinkingmachines/inkling":{"draws":22,"losses":9,"wins":15},"x-ai/grok-4.5":{"draws":21,"losses":55,"wins":12},"x-ai/grok-build-0.1":{"draws":12,"losses":11,"wins":5},"xiaomi/mimo-v2.5":{"draws":48,"losses":22,"wins":22},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":12,"wins":11},"z-ai/glm-5.2":{"draws":54,"losses":52,"wins":22}},"xiaomi/mimo-v2.5-pro":{"claude-fable-5":{"draws":0,"losses":16,"wins":0},"claude-opus-4-5":{"draws":3,"losses":10,"wins":13},"claude-opus-4-8":{"draws":8,"losses":15,"wins":7},"claude-opus-5":{"draws":6,"losses":11,"wins":1},"claude-sonnet-5":{"draws":2,"losses":7,"wins":1},"cohere/north-mini-code":{"draws":4,"losses":6,"wins":4},"deepseek/deepseek-v4-flash":{"draws":14,"losses":15,"wins":15},"deepseek/deepseek-v4-pro":{"draws":3,"losses":4,"wins":5},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":12},"google/gemini-3.5-flash":{"draws":3,"losses":3,"wins":2},"google/gemini-3.5-flash-lite":{"draws":2,"losses":5,"wins":1},"google/gemini-3.6-flash":{"draws":1,"losses":3,"wins":0},"google/gemma-4-31b-it":{"draws":0,"losses":4,"wins":6},"gpt-4.1":{"draws":0,"losses":5,"wins":5},"gpt-5":{"draws":5,"losses":6,"wins":3},"gpt-5.4":{"draws":8,"losses":19,"wins":7},"gpt-5.4-mini":{"draws":19,"losses":19,"wins":12},"gpt-5.4-nano":{"draws":22,"losses":21,"wins":27},"gpt-5.5":{"draws":6,"losses":5,"wins":7},"gpt-5.6-luna":{"draws":9,"losses":4,"wins":9},"gpt-5.6-sol":{"draws":3,"losses":10,"wins":3},"gpt-5.6-terra":{"draws":4,"losses":3,"wins":5},"inclusionai/ling-3.0-flash":{"draws":1,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":2,"losses":0,"wins":10},"minimax/minimax-m3":{"draws":4,"losses":5,"wins":9},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":4},"moonshotai/kimi-k3":{"draws":6,"losses":13,"wins":7},"nex-agi/nex-n2-pro":{"draws":4,"losses":5,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":1,"wins":9},"o3":{"draws":4,"losses":6,"wins":2},"openai/gpt-oss-120b":{"draws":7,"losses":1,"wins":10},"poolside/laguna-s-2.1":{"draws":2,"losses":2,"wins":2},"qwen/qwen3.7-max":{"draws":6,"losses":11,"wins":3},"qwen/qwen3.7-plus":{"draws":6,"losses":1,"wins":11},"stepfun/step-3.7-flash":{"draws":1,"losses":1,"wins":4},"tencent/hy3-preview":{"draws":3,"losses":6,"wins":3},"thinkingmachines/inkling":{"draws":0,"losses":4,"wins":4},"x-ai/grok-4.5":{"draws":4,"losses":24,"wins":12},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":4},"xiaomi/mimo-v2.5":{"draws":7,"losses":11,"wins":12},"z-ai/glm-5.2":{"draws":9,"losses":13,"wins":4}},"z-ai/glm-5.2":{"claude-fable-5":{"draws":1,"losses":33,"wins":8},"claude-opus-4-5":{"draws":41,"losses":46,"wins":37},"claude-opus-4-8":{"draws":23,"losses":34,"wins":23},"claude-opus-5":{"draws":14,"losses":58,"wins":10},"claude-sonnet-5":{"draws":37,"losses":33,"wins":34},"cohere/north-mini-code":{"draws":14,"losses":2,"wins":4},"deepseek/deepseek-v4-flash":{"draws":45,"losses":40,"wins":55},"deepseek/deepseek-v4-pro":{"draws":14,"losses":26,"wins":14},"google/gemini-3.1-flash-lite":{"draws":16,"losses":6,"wins":22},"google/gemini-3.5-flash":{"draws":17,"losses":21,"wins":16},"google/gemini-3.5-flash-lite":{"draws":9,"losses":6,"wins":9},"google/gemini-3.6-flash":{"draws":13,"losses":8,"wins":5},"google/gemma-4-31b-it":{"draws":5,"losses":6,"wins":7},"gpt-4.1":{"draws":6,"losses":11,"wins":15},"gpt-5":{"draws":23,"losses":29,"wins":32},"gpt-5.4":{"draws":41,"losses":30,"wins":17},"gpt-5.4-mini":{"draws":82,"losses":57,"wins":75},"gpt-5.4-nano":{"draws":84,"losses":70,"wins":87},"gpt-5.5":{"draws":22,"losses":26,"wins":20},"gpt-5.6-luna":{"draws":36,"losses":25,"wins":35},"gpt-5.6-sol":{"draws":23,"losses":43,"wins":22},"gpt-5.6-terra":{"draws":27,"losses":27,"wins":22},"inclusionai/ling-3.0-flash":{"draws":6,"losses":3,"wins":5},"meituan/longcat-2.0":{"draws":13,"losses":3,"wins":8},"minimax/minimax-m3":{"draws":10,"losses":9,"wins":7},"mistralai/mistral-medium-3-5":{"draws":2,"losses":12,"wins":20},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":8,"wins":7},"moonshotai/kimi-k3":{"draws":41,"losses":37,"wins":26},"nex-agi/nex-n2-pro":{"draws":10,"losses":8,"wins":14},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":33,"losses":25,"wins":30},"o3":{"draws":7,"losses":17,"wins":22},"openai/gpt-oss-120b":{"draws":25,"losses":15,"wins":14},"poolside/laguna-s-2.1":{"draws":12,"losses":10,"wins":10},"qwen/qwen3.7-max":{"draws":14,"losses":11,"wins":11},"qwen/qwen3.7-plus":{"draws":17,"losses":10,"wins":19},"stepfun/step-3.7-flash":{"draws":2,"losses":6,"wins":16},"tencent/hy3-preview":{"draws":29,"losses":14,"wins":17},"thinkingmachines/inkling":{"draws":7,"losses":10,"wins":17},"x-ai/grok-4.5":{"draws":16,"losses":72,"wins":46},"x-ai/grok-build-0.1":{"draws":4,"losses":4,"wins":6},"xiaomi/mimo-v2.5":{"draws":54,"losses":22,"wins":52},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":4,"wins":13},"z-ai/glm-5.2":{"draws":94,"losses":67,"wins":67}}},"versus_totals_tracks":{"highest":{"claude-fable-5":{"claude-fable-5":{"draws":1,"losses":0,"wins":5},"claude-opus-4-5":{"draws":1,"losses":1,"wins":8},"claude-opus-4-8":{"draws":1,"losses":5,"wins":10},"claude-opus-5":{"draws":11,"losses":10,"wins":21},"claude-sonnet-5":{"draws":6,"losses":0,"wins":14},"deepseek/deepseek-v4-flash":{"draws":2,"losses":2,"wins":12},"deepseek/deepseek-v4-pro":{"draws":1,"losses":0,"wins":11},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":2},"google/gemini-3.5-flash":{"draws":2,"losses":2,"wins":12},"google/gemini-3.6-flash":{"draws":2,"losses":1,"wins":3},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":2},"gpt-4.1":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":1,"losses":0,"wins":11},"gpt-5.4":{"draws":2,"losses":8,"wins":8},"gpt-5.4-mini":{"draws":2,"losses":4,"wins":8},"gpt-5.4-nano":{"draws":5,"losses":4,"wins":27},"gpt-5.5":{"draws":5,"losses":6,"wins":5},"gpt-5.6-luna":{"draws":2,"losses":2,"wins":10},"gpt-5.6-sol":{"draws":6,"losses":6,"wins":14},"gpt-5.6-terra":{"draws":3,"losses":1,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":1},"moonshotai/kimi-k3":{"draws":5,"losses":4,"wins":29},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":4},"o3":{"draws":0,"losses":0,"wins":8},"openai/gpt-oss-120b":{"draws":1,"losses":0,"wins":7},"poolside/laguna-s-2.1":{"draws":0,"losses":2,"wins":2},"qwen/qwen3.7-max":{"draws":0,"losses":2,"wins":0},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":2},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":0,"losses":3,"wins":5},"x-ai/grok-4.5":{"draws":4,"losses":8,"wins":30},"xiaomi/mimo-v2.5":{"draws":1,"losses":0,"wins":5},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":6},"z-ai/glm-5.2":{"draws":1,"losses":4,"wins":23}},"claude-opus-4-8":{"claude-fable-5":{"draws":2,"losses":8,"wins":8},"claude-opus-4-5":{"draws":1,"losses":3,"wins":10},"claude-opus-4-8":{"draws":0,"losses":2,"wins":2},"claude-opus-5":{"draws":8,"losses":14,"wins":8},"claude-sonnet-5":{"draws":3,"losses":3,"wins":12},"deepseek/deepseek-v4-flash":{"draws":0,"losses":3,"wins":13},"deepseek/deepseek-v4-pro":{"draws":2,"losses":0,"wins":2},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":5},"google/gemini-3.5-flash":{"draws":2,"losses":4,"wins":4},"google/gemini-3.5-flash-lite":{"draws":0,"losses":0,"wins":2},"google/gemini-3.6-flash":{"draws":1,"losses":1,"wins":0},"gpt-4.1":{"draws":0,"losses":0,"wins":4},"gpt-5":{"draws":2,"losses":2,"wins":10},"gpt-5.4":{"draws":3,"losses":9,"wins":6},"gpt-5.4-mini":{"draws":2,"losses":6,"wins":10},"gpt-5.4-nano":{"draws":2,"losses":5,"wins":15},"gpt-5.5":{"draws":1,"losses":7,"wins":2},"gpt-5.6-luna":{"draws":2,"losses":4,"wins":10},"gpt-5.6-sol":{"draws":1,"losses":9,"wins":4},"gpt-5.6-terra":{"draws":1,"losses":2,"wins":9},"meituan/longcat-2.0":{"draws":2,"losses":0,"wins":0},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":2},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":7,"losses":9,"wins":14},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":1,"losses":2,"wins":9},"o3":{"draws":0,"losses":1,"wins":5},"openai/gpt-oss-120b":{"draws":1,"losses":0,"wins":5},"qwen/qwen3.7-max":{"draws":0,"losses":0,"wins":2},"qwen/qwen3.7-plus":{"draws":0,"losses":1,"wins":5},"stepfun/step-3.7-flash":{"draws":0,"losses":1,"wins":1},"tencent/hy3-preview":{"draws":1,"losses":0,"wins":5},"thinkingmachines/inkling":{"draws":0,"losses":0,"wins":4},"x-ai/grok-4.5":{"draws":6,"losses":14,"wins":22},"x-ai/grok-build-0.1":{"draws":0,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":1,"losses":0,"wins":3},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":2,"wins":2},"z-ai/glm-5.2":{"draws":6,"losses":9,"wins":19}},"claude-opus-5":{"claude-fable-5":{"draws":5,"losses":8,"wins":15},"claude-opus-4-5":{"draws":3,"losses":4,"wins":39},"claude-opus-4-8":{"draws":2,"losses":5,"wins":5},"claude-opus-5":{"draws":10,"losses":41,"wins":71},"claude-sonnet-5":{"draws":0,"losses":0,"wins":12},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":3},"deepseek/deepseek-v4-pro":{"draws":0,"losses":1,"wins":3},"google/gemini-3.1-flash-lite":{"draws":0,"losses":1,"wins":3},"google/gemini-3.5-flash":{"draws":0,"losses":1,"wins":9},"google/gemini-3.5-flash-lite":{"draws":0,"losses":1,"wins":7},"google/gemini-3.6-flash":{"draws":3,"losses":1,"wins":22},"gpt-4.1":{"draws":1,"losses":0,"wins":7},"gpt-5.4":{"draws":0,"losses":4,"wins":14},"gpt-5.4-mini":{"draws":0,"losses":0,"wins":6},"gpt-5.4-nano":{"draws":1,"losses":3,"wins":6},"gpt-5.5":{"draws":0,"losses":3,"wins":7},"gpt-5.6-luna":{"draws":0,"losses":0,"wins":2},"gpt-5.6-sol":{"draws":4,"losses":6,"wins":10},"gpt-5.6-terra":{"draws":2,"losses":1,"wins":7},"meituan/longcat-2.0":{"draws":0,"losses":3,"wins":5},"minimax/minimax-m3":{"draws":0,"losses":1,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":1,"wins":4},"moonshotai/kimi-k3":{"draws":2,"losses":4,"wins":28},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":0,"wins":2},"o3":{"draws":0,"losses":0,"wins":10},"poolside/laguna-s-2.1":{"draws":0,"losses":0,"wins":8},"qwen/qwen3.7-max":{"draws":0,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":0,"losses":0,"wins":2},"thinkingmachines/inkling":{"draws":0,"losses":2,"wins":10},"x-ai/grok-4.5":{"draws":2,"losses":5,"wins":37},"xiaomi/mimo-v2.5":{"draws":0,"losses":1,"wins":3},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":1,"wins":4},"z-ai/glm-5.2":{"draws":3,"losses":1,"wins":12}},"claude-sonnet-5":{"claude-fable-5":{"draws":6,"losses":12,"wins":0},"claude-opus-4-5":{"draws":9,"losses":6,"wins":9},"claude-opus-4-8":{"draws":3,"losses":14,"wins":5},"claude-opus-5":{"draws":10,"losses":21,"wins":3},"claude-sonnet-5":{"draws":3,"losses":5,"wins":6},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":4},"deepseek/deepseek-v4-flash":{"draws":4,"losses":2,"wins":20},"deepseek/deepseek-v4-pro":{"draws":5,"losses":5,"wins":6},"google/gemini-3.1-flash-lite":{"draws":3,"losses":1,"wins":10},"google/gemini-3.5-flash":{"draws":3,"losses":3,"wins":4},"google/gemini-3.5-flash-lite":{"draws":0,"losses":1,"wins":3},"google/gemini-3.6-flash":{"draws":1,"losses":0,"wins":1},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":2},"gpt-4.1":{"draws":2,"losses":1,"wins":3},"gpt-5":{"draws":10,"losses":8,"wins":6},"gpt-5.4":{"draws":6,"losses":12,"wins":2},"gpt-5.4-mini":{"draws":13,"losses":9,"wins":14},"gpt-5.4-nano":{"draws":9,"losses":11,"wins":6},"gpt-5.5":{"draws":8,"losses":6,"wins":2},"gpt-5.6-luna":{"draws":4,"losses":7,"wins":1},"gpt-5.6-sol":{"draws":4,"losses":17,"wins":5},"gpt-5.6-terra":{"draws":6,"losses":7,"wins":9},"inclusionai/ling-3.0-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":2,"losses":0,"wins":2},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":2},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":8},"moonshotai/kimi-k3":{"draws":9,"losses":11,"wins":8},"nex-agi/nex-n2-pro":{"draws":1,"losses":3,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":2,"wins":10},"o3":{"draws":0,"losses":8,"wins":4},"openai/gpt-oss-120b":{"draws":4,"losses":4,"wins":4},"qwen/qwen3.7-max":{"draws":0,"losses":0,"wins":2},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":0},"stepfun/step-3.7-flash":{"draws":4,"losses":0,"wins":6},"tencent/hy3-preview":{"draws":3,"losses":3,"wins":8},"x-ai/grok-4.5":{"draws":18,"losses":17,"wins":9},"x-ai/grok-build-0.1":{"draws":1,"losses":1,"wins":2},"xiaomi/mimo-v2.5":{"draws":6,"losses":1,"wins":3},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":2},"z-ai/glm-5.2":{"draws":25,"losses":19,"wins":16}},"deepseek/deepseek-v4-flash":{"claude-fable-5":{"draws":1,"losses":4,"wins":1},"claude-opus-4-5":{"draws":12,"losses":9,"wins":5},"claude-opus-4-8":{"draws":0,"losses":11,"wins":7},"claude-opus-5":{"draws":1,"losses":1,"wins":0},"claude-sonnet-5":{"draws":5,"losses":14,"wins":3},"cohere/north-mini-code":{"draws":4,"losses":2,"wins":2},"deepseek/deepseek-v4-flash":{"draws":1,"losses":12,"wins":17},"deepseek/deepseek-v4-pro":{"draws":6,"losses":11,"wins":1},"google/gemini-3.1-flash-lite":{"draws":4,"losses":7,"wins":9},"google/gemini-3.5-flash":{"draws":2,"losses":9,"wins":3},"google/gemini-3.5-flash-lite":{"draws":2,"losses":2,"wins":2},"google/gemini-3.6-flash":{"draws":3,"losses":1,"wins":2},"google/gemma-4-31b-it":{"draws":1,"losses":7,"wins":2},"gpt-4.1":{"draws":0,"losses":1,"wins":1},"gpt-5":{"draws":5,"losses":15,"wins":0},"gpt-5.4":{"draws":6,"losses":4,"wins":2},"gpt-5.4-mini":{"draws":12,"losses":13,"wins":7},"gpt-5.4-nano":{"draws":22,"losses":13,"wins":19},"gpt-5.5":{"draws":2,"losses":4,"wins":0},"gpt-5.6-luna":{"draws":8,"losses":3,"wins":5},"gpt-5.6-sol":{"draws":0,"losses":10,"wins":4},"gpt-5.6-terra":{"draws":4,"losses":12,"wins":6},"inclusionai/ling-3.0-flash":{"draws":6,"losses":2,"wins":4},"meituan/longcat-2.0":{"draws":2,"losses":0,"wins":2},"minimax/minimax-m3":{"draws":0,"losses":4,"wins":0},"mistralai/mistral-medium-3-5":{"draws":0,"losses":7,"wins":13},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":1,"wins":1},"moonshotai/kimi-k3":{"draws":12,"losses":15,"wins":7},"nex-agi/nex-n2-pro":{"draws":0,"losses":2,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":6,"wins":12},"o3":{"draws":1,"losses":11,"wins":4},"openai/gpt-oss-120b":{"draws":6,"losses":6,"wins":0},"poolside/laguna-s-2.1":{"draws":0,"losses":4,"wins":2},"qwen/qwen3.7-max":{"draws":0,"losses":1,"wins":1},"qwen/qwen3.7-plus":{"draws":0,"losses":2,"wins":0},"stepfun/step-3.7-flash":{"draws":4,"losses":11,"wins":11},"tencent/hy3-preview":{"draws":6,"losses":7,"wins":5},"thinkingmachines/inkling":{"draws":2,"losses":6,"wins":2},"x-ai/grok-4.5":{"draws":2,"losses":29,"wins":7},"x-ai/grok-build-0.1":{"draws":2,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":4,"losses":2,"wins":4},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":2,"wins":6},"z-ai/glm-5.2":{"draws":18,"losses":25,"wins":23}},"deepseek/deepseek-v4-pro":{"claude-fable-5":{"draws":0,"losses":8,"wins":0},"claude-opus-4-5":{"draws":3,"losses":6,"wins":3},"claude-opus-4-8":{"draws":3,"losses":5,"wins":4},"claude-opus-5":{"draws":1,"losses":11,"wins":0},"claude-sonnet-5":{"draws":6,"losses":4,"wins":4},"deepseek/deepseek-v4-flash":{"draws":4,"losses":1,"wins":15},"deepseek/deepseek-v4-pro":{"draws":0,"losses":0,"wins":4},"google/gemini-3.1-flash-lite":{"draws":2,"losses":2,"wins":2},"google/gemini-3.5-flash":{"draws":1,"losses":2,"wins":1},"google/gemini-3.5-flash-lite":{"draws":0,"losses":0,"wins":2},"google/gemini-3.6-flash":{"draws":0,"losses":2,"wins":0},"google/gemma-4-31b-it":{"draws":2,"losses":1,"wins":3},"gpt-5":{"draws":0,"losses":3,"wins":9},"gpt-5.4":{"draws":1,"losses":11,"wins":2},"gpt-5.4-mini":{"draws":5,"losses":6,"wins":9},"gpt-5.4-nano":{"draws":8,"losses":6,"wins":12},"gpt-5.5":{"draws":3,"losses":6,"wins":1},"gpt-5.6-luna":{"draws":6,"losses":2,"wins":2},"gpt-5.6-sol":{"draws":0,"losses":8,"wins":2},"gpt-5.6-terra":{"draws":6,"losses":5,"wins":3},"minimax/minimax-m3":{"draws":0,"losses":1,"wins":1},"mistralai/mistral-medium-3-5":{"draws":0,"losses":1,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":5,"losses":10,"wins":9},"nex-agi/nex-n2-pro":{"draws":0,"losses":2,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":3,"wins":5},"o3":{"draws":1,"losses":2,"wins":5},"openai/gpt-oss-120b":{"draws":2,"losses":2,"wins":0},"poolside/laguna-s-2.1":{"draws":0,"losses":2,"wins":2},"qwen/qwen3.7-max":{"draws":0,"losses":3,"wins":1},"stepfun/step-3.7-flash":{"draws":2,"losses":1,"wins":7},"tencent/hy3-preview":{"draws":0,"losses":2,"wins":6},"thinkingmachines/inkling":{"draws":0,"losses":0,"wins":2},"x-ai/grok-4.5":{"draws":3,"losses":18,"wins":5},"x-ai/grok-build-0.1":{"draws":4,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":6,"losses":2,"wins":2},"z-ai/glm-5.2":{"draws":8,"losses":6,"wins":20}},"google/gemini-3.1-flash-lite":{"claude-opus-4-5":{"draws":3,"losses":13,"wins":0},"claude-opus-4-8":{"draws":3,"losses":7,"wins":2},"claude-opus-5":{"draws":0,"losses":8,"wins":0},"claude-sonnet-5":{"draws":4,"losses":5,"wins":1},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":6},"deepseek/deepseek-v4-flash":{"draws":6,"losses":7,"wins":5},"deepseek/deepseek-v4-pro":{"draws":2,"losses":1,"wins":1},"google/gemini-3.1-flash-lite":{"draws":0,"losses":2,"wins":0},"google/gemini-3.5-flash":{"draws":2,"losses":2,"wins":0},"google/gemini-3.5-flash-lite":{"draws":2,"losses":1,"wins":1},"google/gemini-3.6-flash":{"draws":2,"losses":2,"wins":0},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":0},"gpt-4.1":{"draws":2,"losses":1,"wins":1},"gpt-5":{"draws":2,"losses":6,"wins":0},"gpt-5.4":{"draws":1,"losses":1,"wins":0},"gpt-5.4-mini":{"draws":7,"losses":10,"wins":3},"gpt-5.4-nano":{"draws":9,"losses":13,"wins":4},"gpt-5.5":{"draws":4,"losses":4,"wins":0},"gpt-5.6-luna":{"draws":2,"losses":4,"wins":2},"gpt-5.6-sol":{"draws":0,"losses":4,"wins":2},"gpt-5.6-terra":{"draws":2,"losses":4,"wins":0},"inclusionai/ling-3.0-flash":{"draws":4,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":4,"losses":0,"wins":2},"mistralai/mistral-medium-3-5":{"draws":0,"losses":3,"wins":5},"moonshotai/kimi-k3":{"draws":4,"losses":14,"wins":0},"nex-agi/nex-n2-pro":{"draws":0,"losses":4,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":7,"wins":3},"o3":{"draws":0,"losses":4,"wins":4},"openai/gpt-oss-120b":{"draws":4,"losses":4,"wins":2},"poolside/laguna-s-2.1":{"draws":4,"losses":1,"wins":1},"qwen/qwen3.7-plus":{"draws":0,"losses":2,"wins":0},"stepfun/step-3.7-flash":{"draws":2,"losses":5,"wins":3},"tencent/hy3-preview":{"draws":1,"losses":5,"wins":4},"thinkingmachines/inkling":{"draws":0,"losses":1,"wins":1},"x-ai/grok-4.5":{"draws":2,"losses":10,"wins":0},"x-ai/grok-build-0.1":{"draws":3,"losses":0,"wins":1},"xiaomi/mimo-v2.5":{"draws":8,"losses":0,"wins":0},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":4,"wins":0},"z-ai/glm-5.2":{"draws":2,"losses":10,"wins":4}},"google/gemini-3.5-flash":{"claude-fable-5":{"draws":1,"losses":11,"wins":4},"claude-opus-4-5":{"draws":5,"losses":3,"wins":6},"claude-opus-4-8":{"draws":1,"losses":3,"wins":4},"claude-opus-5":{"draws":0,"losses":2,"wins":0},"claude-sonnet-5":{"draws":2,"losses":3,"wins":1},"deepseek/deepseek-v4-flash":{"draws":11,"losses":4,"wins":11},"deepseek/deepseek-v4-pro":{"draws":1,"losses":1,"wins":0},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":2},"google/gemini-3.5-flash":{"draws":2,"losses":1,"wins":1},"google/gemini-3.6-flash":{"draws":2,"losses":0,"wins":0},"google/gemma-4-31b-it":{"draws":0,"losses":2,"wins":2},"gpt-4.1":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":2,"losses":2,"wins":6},"gpt-5.4":{"draws":2,"losses":4,"wins":2},"gpt-5.4-mini":{"draws":8,"losses":13,"wins":9},"gpt-5.4-nano":{"draws":8,"losses":11,"wins":5},"gpt-5.5":{"draws":8,"losses":8,"wins":2},"gpt-5.6-luna":{"draws":5,"losses":3,"wins":2},"gpt-5.6-sol":{"draws":1,"losses":6,"wins":1},"gpt-5.6-terra":{"draws":3,"losses":6,"wins":1},"inclusionai/ling-3.0-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":1,"losses":1,"wins":0},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":2},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":4},"moonshotai/kimi-k3":{"draws":9,"losses":15,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":2,"wins":10},"o3":{"draws":0,"losses":3,"wins":1},"openai/gpt-oss-120b":{"draws":2,"losses":2,"wins":2},"poolside/laguna-s-2.1":{"draws":5,"losses":2,"wins":1},"stepfun/step-3.7-flash":{"draws":2,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":2,"losses":2,"wins":4},"x-ai/grok-4.5":{"draws":4,"losses":3,"wins":9},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":5,"losses":5,"wins":2},"z-ai/glm-5.2":{"draws":11,"losses":10,"wins":13}},"google/gemini-3.5-flash-lite":{"claude-opus-5":{"draws":1,"losses":8,"wins":1},"google/gemini-3.5-flash-lite":{"draws":37,"losses":32,"wins":39},"google/gemini-3.6-flash":{"draws":48,"losses":43,"wins":25},"inclusionai/ling-3.0-flash":{"draws":19,"losses":5,"wins":24},"meituan/longcat-2.0":{"draws":26,"losses":21,"wins":27},"moonshotai/kimi-k3":{"draws":21,"losses":32,"wins":9},"poolside/laguna-s-2.1":{"draws":30,"losses":26,"wins":18},"thinkingmachines/inkling":{"draws":28,"losses":26,"wins":34},"x-ai/grok-4.5":{"draws":22,"losses":36,"wins":10},"z-ai/glm-5.2":{"draws":0,"losses":1,"wins":1}},"google/gemini-3.6-flash":{"claude-fable-5":{"draws":1,"losses":1,"wins":0},"claude-opus-5":{"draws":4,"losses":8,"wins":6},"google/gemini-3.5-flash-lite":{"draws":17,"losses":6,"wins":29},"google/gemini-3.6-flash":{"draws":14,"losses":13,"wins":27},"inclusionai/ling-3.0-flash":{"draws":14,"losses":0,"wins":6},"meituan/longcat-2.0":{"draws":17,"losses":5,"wins":20},"moonshotai/kimi-k3":{"draws":9,"losses":6,"wins":15},"poolside/laguna-s-2.1":{"draws":18,"losses":2,"wins":20},"thinkingmachines/inkling":{"draws":10,"losses":3,"wins":27},"x-ai/grok-4.5":{"draws":2,"losses":15,"wins":23}},"gpt-5":{"claude-fable-5":{"draws":1,"losses":12,"wins":1},"claude-opus-4-5":{"draws":10,"losses":5,"wins":5},"claude-opus-4-8":{"draws":2,"losses":10,"wins":0},"claude-opus-5":{"draws":0,"losses":6,"wins":0},"claude-sonnet-5":{"draws":13,"losses":6,"wins":9},"cohere/north-mini-code":{"draws":1,"losses":1,"wins":4},"deepseek/deepseek-v4-flash":{"draws":9,"losses":0,"wins":13},"deepseek/deepseek-v4-pro":{"draws":0,"losses":8,"wins":4},"google/gemini-3.1-flash-lite":{"draws":2,"losses":2,"wins":4},"google/gemini-3.5-flash":{"draws":4,"losses":7,"wins":3},"google/gemini-3.6-flash":{"draws":0,"losses":0,"wins":2},"gpt-4.1":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":0,"losses":0,"wins":2},"gpt-5.4":{"draws":4,"losses":11,"wins":3},"gpt-5.4-mini":{"draws":11,"losses":14,"wins":7},"gpt-5.4-nano":{"draws":12,"losses":4,"wins":24},"gpt-5.5":{"draws":6,"losses":10,"wins":3},"gpt-5.6-luna":{"draws":8,"losses":1,"wins":7},"gpt-5.6-sol":{"draws":4,"losses":9,"wins":3},"gpt-5.6-terra":{"draws":4,"losses":10,"wins":4},"meituan/longcat-2.0":{"draws":0,"losses":1,"wins":1},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":4},"mistralai/mistral-medium-3-5":{"draws":0,"losses":2,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":16,"losses":6,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":0,"wins":3},"o3":{"draws":0,"losses":2,"wins":8},"openai/gpt-oss-120b":{"draws":2,"losses":0,"wins":2},"poolside/laguna-s-2.1":{"draws":0,"losses":2,"wins":0},"qwen/qwen3.7-max":{"draws":2,"losses":1,"wins":3},"qwen/qwen3.7-plus":{"draws":0,"losses":1,"wins":1},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":6},"tencent/hy3-preview":{"draws":1,"losses":4,"wins":5},"x-ai/grok-4.5":{"draws":7,"losses":10,"wins":7},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":8,"losses":1,"wins":5},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":3,"wins":3},"z-ai/glm-5.2":{"draws":20,"losses":23,"wins":19}},"gpt-5.4":{"claude-fable-5":{"draws":4,"losses":7,"wins":9},"claude-opus-4-5":{"draws":7,"losses":2,"wins":9},"claude-opus-4-8":{"draws":3,"losses":5,"wins":8},"claude-opus-5":{"draws":6,"losses":20,"wins":20},"claude-sonnet-5":{"draws":3,"losses":2,"wins":7},"cohere/north-mini-code":{"draws":1,"losses":1,"wins":4},"deepseek/deepseek-v4-flash":{"draws":2,"losses":2,"wins":8},"deepseek/deepseek-v4-pro":{"draws":0,"losses":0,"wins":8},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":1},"google/gemini-3.5-flash":{"draws":3,"losses":0,"wins":7},"google/gemini-3.6-flash":{"draws":0,"losses":1,"wins":5},"gpt-5":{"draws":2,"losses":3,"wins":7},"gpt-5.4":{"draws":3,"losses":1,"wins":6},"gpt-5.4-mini":{"draws":6,"losses":6,"wins":18},"gpt-5.4-nano":{"draws":8,"losses":3,"wins":19},"gpt-5.5":{"draws":10,"losses":3,"wins":7},"gpt-5.6-luna":{"draws":7,"losses":2,"wins":13},"gpt-5.6-sol":{"draws":2,"losses":2,"wins":10},"gpt-5.6-terra":{"draws":3,"losses":4,"wins":11},"meituan/longcat-2.0":{"draws":1,"losses":0,"wins":1},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":2},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":0,"wins":1},"moonshotai/kimi-k3":{"draws":4,"losses":4,"wins":26},"nex-agi/nex-n2-pro":{"draws":1,"losses":0,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":0,"wins":5},"o3":{"draws":0,"losses":2,"wins":2},"openai/gpt-oss-120b":{"draws":0,"losses":0,"wins":6},"qwen/qwen3.7-max":{"draws":0,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":1,"losses":0,"wins":9},"x-ai/grok-4.5":{"draws":11,"losses":8,"wins":33},"xiaomi/mimo-v2.5":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":6},"z-ai/glm-5.2":{"draws":6,"losses":9,"wins":21}},"gpt-5.4-mini":{"claude-fable-5":{"draws":2,"losses":10,"wins":4},"claude-opus-4-5":{"draws":11,"losses":3,"wins":8},"claude-opus-4-8":{"draws":1,"losses":10,"wins":7},"claude-opus-5":{"draws":0,"losses":24,"wins":2},"claude-sonnet-5":{"draws":5,"losses":8,"wins":11},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":2},"deepseek/deepseek-v4-flash":{"draws":13,"losses":6,"wins":21},"deepseek/deepseek-v4-pro":{"draws":2,"losses":3,"wins":5},"google/gemini-3.1-flash-lite":{"draws":7,"losses":1,"wins":8},"google/gemini-3.5-flash":{"draws":1,"losses":5,"wins":10},"google/gemini-3.5-flash-lite":{"draws":4,"losses":0,"wins":0},"google/gemini-3.6-flash":{"draws":3,"losses":1,"wins":0},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":2},"gpt-4.1":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":9,"losses":4,"wins":11},"gpt-5.4":{"draws":1,"losses":15,"wins":6},"gpt-5.4-mini":{"draws":13,"losses":11,"wins":22},"gpt-5.4-nano":{"draws":16,"losses":13,"wins":15},"gpt-5.5":{"draws":2,"losses":7,"wins":3},"gpt-5.6-luna":{"draws":10,"losses":11,"wins":3},"gpt-5.6-sol":{"draws":0,"losses":5,"wins":9},"gpt-5.6-terra":{"draws":8,"losses":12,"wins":8},"inclusionai/ling-3.0-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":2,"losses":1,"wins":1},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":0},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":6},"moonshotai/kimi-k3":{"draws":10,"losses":14,"wins":8},"nex-agi/nex-n2-pro":{"draws":2,"losses":1,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":7,"wins":11},"o3":{"draws":0,"losses":15,"wins":5},"openai/gpt-oss-120b":{"draws":11,"losses":4,"wins":7},"poolside/laguna-s-2.1":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.7-max":{"draws":6,"losses":1,"wins":5},"qwen/qwen3.7-plus":{"draws":6,"losses":2,"wins":0},"stepfun/step-3.7-flash":{"draws":3,"losses":2,"wins":9},"tencent/hy3-preview":{"draws":5,"losses":1,"wins":12},"thinkingmachines/inkling":{"draws":0,"losses":3,"wins":1},"x-ai/grok-4.5":{"draws":7,"losses":34,"wins":11},"xiaomi/mimo-v2.5":{"draws":5,"losses":2,"wins":11},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":2,"wins":6},"z-ai/glm-5.2":{"draws":24,"losses":33,"wins":29}},"gpt-5.4-nano":{"claude-fable-5":{"draws":3,"losses":18,"wins":5},"claude-opus-4-5":{"draws":11,"losses":13,"wins":12},"claude-opus-4-8":{"draws":2,"losses":11,"wins":7},"claude-opus-5":{"draws":4,"losses":15,"wins":3},"claude-sonnet-5":{"draws":15,"losses":6,"wins":9},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":6},"deepseek/deepseek-v4-flash":{"draws":23,"losses":11,"wins":12},"deepseek/deepseek-v4-pro":{"draws":7,"losses":13,"wins":4},"google/gemini-3.1-flash-lite":{"draws":5,"losses":1,"wins":4},"google/gemini-3.5-flash":{"draws":6,"losses":5,"wins":9},"google/gemini-3.5-flash-lite":{"draws":5,"losses":1,"wins":0},"google/gemini-3.6-flash":{"draws":6,"losses":6,"wins":4},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":2},"gpt-4.1":{"draws":0,"losses":1,"wins":1},"gpt-5":{"draws":10,"losses":20,"wins":6},"gpt-5.4":{"draws":13,"losses":17,"wins":8},"gpt-5.4-mini":{"draws":24,"losses":15,"wins":15},"gpt-5.4-nano":{"draws":16,"losses":7,"wins":21},"gpt-5.5":{"draws":5,"losses":13,"wins":4},"gpt-5.6-luna":{"draws":11,"losses":7,"wins":8},"gpt-5.6-sol":{"draws":3,"losses":16,"wins":5},"gpt-5.6-terra":{"draws":6,"losses":10,"wins":14},"inclusionai/ling-3.0-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":1,"losses":2,"wins":1},"minimax/minimax-m3":{"draws":9,"losses":2,"wins":5},"mistralai/mistral-medium-3-5":{"draws":1,"losses":5,"wins":4},"moonshotai/kimi-k3":{"draws":16,"losses":25,"wins":20},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":28,"losses":2,"wins":4},"o3":{"draws":0,"losses":3,"wins":11},"openai/gpt-oss-120b":{"draws":7,"losses":9,"wins":4},"poolside/laguna-s-2.1":{"draws":0,"losses":2,"wins":2},"qwen/qwen3.7-max":{"draws":1,"losses":3,"wins":2},"qwen/qwen3.7-plus":{"draws":0,"losses":2,"wins":0},"stepfun/step-3.7-flash":{"draws":7,"losses":2,"wins":11},"tencent/hy3-preview":{"draws":6,"losses":7,"wins":11},"thinkingmachines/inkling":{"draws":5,"losses":6,"wins":3},"x-ai/grok-4.5":{"draws":10,"losses":27,"wins":25},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":6,"losses":0,"wins":8},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":2,"wins":0},"z-ai/glm-5.2":{"draws":34,"losses":31,"wins":27}},"gpt-5.5":{"claude-fable-5":{"draws":3,"losses":6,"wins":9},"claude-opus-4-5":{"draws":3,"losses":3,"wins":8},"claude-opus-4-8":{"draws":2,"losses":1,"wins":13},"claude-opus-5":{"draws":0,"losses":16,"wins":18},"claude-sonnet-5":{"draws":4,"losses":2,"wins":6},"deepseek/deepseek-v4-flash":{"draws":2,"losses":0,"wins":6},"deepseek/deepseek-v4-pro":{"draws":1,"losses":0,"wins":5},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":4},"google/gemini-3.5-flash":{"draws":7,"losses":6,"wins":9},"google/gemini-3.6-flash":{"draws":2,"losses":2,"wins":4},"gpt-4.1":{"draws":1,"losses":0,"wins":3},"gpt-5":{"draws":4,"losses":3,"wins":12},"gpt-5.4":{"draws":7,"losses":5,"wins":10},"gpt-5.4-mini":{"draws":4,"losses":4,"wins":6},"gpt-5.4-nano":{"draws":1,"losses":3,"wins":18},"gpt-5.5":{"draws":5,"losses":1,"wins":4},"gpt-5.6-luna":{"draws":3,"losses":4,"wins":7},"gpt-5.6-sol":{"draws":0,"losses":4,"wins":10},"gpt-5.6-terra":{"draws":2,"losses":4,"wins":8},"minimax/minimax-m3":{"draws":1,"losses":1,"wins":4},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":9,"losses":4,"wins":13},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":0,"wins":1},"o3":{"draws":0,"losses":0,"wins":6},"openai/gpt-oss-120b":{"draws":2,"losses":0,"wins":4},"poolside/laguna-s-2.1":{"draws":1,"losses":0,"wins":1},"qwen/qwen3.7-max":{"draws":0,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":5,"losses":0,"wins":5},"thinkingmachines/inkling":{"draws":1,"losses":0,"wins":5},"x-ai/grok-4.5":{"draws":9,"losses":16,"wins":19},"xiaomi/mimo-v2.5":{"draws":2,"losses":2,"wins":0},"z-ai/glm-5.2":{"draws":5,"losses":7,"wins":16}},"gpt-5.6-luna":{"claude-fable-5":{"draws":2,"losses":10,"wins":2},"claude-opus-4-5":{"draws":5,"losses":5,"wins":12},"claude-opus-4-8":{"draws":2,"losses":8,"wins":10},"claude-opus-5":{"draws":0,"losses":9,"wins":3},"claude-sonnet-5":{"draws":4,"losses":3,"wins":7},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":1},"deepseek/deepseek-v4-flash":{"draws":7,"losses":5,"wins":6},"deepseek/deepseek-v4-pro":{"draws":2,"losses":1,"wins":3},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":4},"google/gemini-3.5-flash":{"draws":7,"losses":3,"wins":4},"google/gemini-3.5-flash-lite":{"draws":2,"losses":0,"wins":0},"google/gemini-3.6-flash":{"draws":2,"losses":0,"wins":2},"gpt-4.1":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":6,"losses":5,"wins":1},"gpt-5.4":{"draws":7,"losses":10,"wins":3},"gpt-5.4-mini":{"draws":13,"losses":3,"wins":16},"gpt-5.4-nano":{"draws":10,"losses":14,"wins":10},"gpt-5.5":{"draws":2,"losses":7,"wins":5},"gpt-5.6-luna":{"draws":2,"losses":1,"wins":7},"gpt-5.6-sol":{"draws":0,"losses":10,"wins":4},"gpt-5.6-terra":{"draws":4,"losses":7,"wins":9},"inclusionai/ling-3.0-flash":{"draws":5,"losses":1,"wins":0},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":0,"wins":1},"moonshotai/kimi-k3":{"draws":4,"losses":6,"wins":12},"nex-agi/nex-n2-pro":{"draws":1,"losses":2,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":1,"wins":5},"o3":{"draws":0,"losses":3,"wins":5},"openai/gpt-oss-120b":{"draws":2,"losses":1,"wins":5},"poolside/laguna-s-2.1":{"draws":2,"losses":0,"wins":2},"qwen/qwen3.7-max":{"draws":1,"losses":1,"wins":0},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":0},"stepfun/step-3.7-flash":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":4,"losses":0,"wins":4},"thinkingmachines/inkling":{"draws":4,"losses":0,"wins":0},"x-ai/grok-4.5":{"draws":6,"losses":17,"wins":15},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":2,"losses":0,"wins":2},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":3,"wins":0},"z-ai/glm-5.2":{"draws":10,"losses":15,"wins":17}},"gpt-5.6-sol":{"claude-fable-5":{"draws":5,"losses":8,"wins":9},"claude-opus-4-5":{"draws":2,"losses":2,"wins":12},"claude-opus-4-8":{"draws":1,"losses":3,"wins":10},"claude-opus-5":{"draws":6,"losses":22,"wins":14},"claude-sonnet-5":{"draws":1,"losses":4,"wins":17},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":3},"deepseek/deepseek-v4-flash":{"draws":0,"losses":2,"wins":12},"deepseek/deepseek-v4-pro":{"draws":0,"losses":2,"wins":8},"google/gemini-3.1-flash-lite":{"draws":0,"losses":2,"wins":6},"google/gemini-3.5-flash":{"draws":3,"losses":1,"wins":8},"google/gemini-3.5-flash-lite":{"draws":0,"losses":1,"wins":1},"google/gemini-3.6-flash":{"draws":0,"losses":4,"wins":4},"gpt-4.1":{"draws":0,"losses":0,"wins":4},"gpt-5":{"draws":0,"losses":3,"wins":9},"gpt-5.4":{"draws":2,"losses":10,"wins":4},"gpt-5.4-mini":{"draws":2,"losses":7,"wins":7},"gpt-5.4-nano":{"draws":5,"losses":7,"wins":20},"gpt-5.5":{"draws":3,"losses":8,"wins":7},"gpt-5.6-luna":{"draws":0,"losses":5,"wins":9},"gpt-5.6-sol":{"draws":2,"losses":5,"wins":5},"gpt-5.6-terra":{"draws":3,"losses":6,"wins":7},"meituan/longcat-2.0":{"draws":0,"losses":2,"wins":0},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":9,"losses":6,"wins":27},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":4,"wins":8},"o3":{"draws":1,"losses":1,"wins":4},"openai/gpt-oss-120b":{"draws":3,"losses":3,"wins":2},"poolside/laguna-s-2.1":{"draws":0,"losses":0,"wins":4},"qwen/qwen3.7-max":{"draws":0,"losses":0,"wins":2},"stepfun/step-3.7-flash":{"draws":0,"losses":1,"wins":3},"tencent/hy3-preview":{"draws":0,"losses":2,"wins":8},"x-ai/grok-4.5":{"draws":2,"losses":9,"wins":29},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":0,"losses":1,"wins":1},"z-ai/glm-5.2":{"draws":7,"losses":6,"wins":21}},"gpt-5.6-terra":{"claude-fable-5":{"draws":3,"losses":18,"wins":3},"claude-opus-4-5":{"draws":2,"losses":2,"wins":10},"claude-opus-4-8":{"draws":1,"losses":11,"wins":2},"claude-opus-5":{"draws":10,"losses":18,"wins":6},"claude-sonnet-5":{"draws":5,"losses":6,"wins":9},"deepseek/deepseek-v4-flash":{"draws":4,"losses":3,"wins":11},"deepseek/deepseek-v4-pro":{"draws":2,"losses":2,"wins":4},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":6},"google/gemini-3.5-flash":{"draws":4,"losses":2,"wins":8},"google/gemini-3.5-flash-lite":{"draws":3,"losses":0,"wins":1},"google/gemini-3.6-flash":{"draws":0,"losses":2,"wins":2},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":4,"losses":5,"wins":11},"gpt-5.4":{"draws":3,"losses":6,"wins":5},"gpt-5.4-mini":{"draws":7,"losses":10,"wins":23},"gpt-5.4-nano":{"draws":2,"losses":13,"wins":9},"gpt-5.5":{"draws":4,"losses":9,"wins":7},"gpt-5.6-luna":{"draws":2,"losses":5,"wins":7},"gpt-5.6-sol":{"draws":0,"losses":7,"wins":9},"gpt-5.6-terra":{"draws":0,"losses":2,"wins":2},"meituan/longcat-2.0":{"draws":2,"losses":0,"wins":0},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":2},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":10,"losses":12,"wins":8},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":0,"wins":7},"o3":{"draws":0,"losses":1,"wins":3},"openai/gpt-oss-120b":{"draws":1,"losses":1,"wins":6},"qwen/qwen3.7-max":{"draws":0,"losses":0,"wins":2},"qwen/qwen3.7-plus":{"draws":0,"losses":2,"wins":4},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":2,"losses":0,"wins":2},"thinkingmachines/inkling":{"draws":0,"losses":0,"wins":2},"x-ai/grok-4.5":{"draws":2,"losses":20,"wins":18},"xiaomi/mimo-v2.5":{"draws":2,"losses":0,"wins":2},"z-ai/glm-5.2":{"draws":12,"losses":10,"wins":20}},"mistralai/mistral-medium-3-5":{"claude-opus-4-5":{"draws":0,"losses":6,"wins":0},"claude-opus-4-8":{"draws":0,"losses":4,"wins":0},"claude-sonnet-5":{"draws":0,"losses":10,"wins":2},"cohere/north-mini-code":{"draws":0,"losses":2,"wins":0},"deepseek/deepseek-v4-flash":{"draws":2,"losses":10,"wins":8},"deepseek/deepseek-v4-pro":{"draws":0,"losses":5,"wins":1},"google/gemini-3.1-flash-lite":{"draws":2,"losses":10,"wins":6},"google/gemini-3.5-flash":{"draws":0,"losses":4,"wins":0},"google/gemini-3.5-flash-lite":{"draws":0,"losses":5,"wins":3},"google/gemini-3.6-flash":{"draws":2,"losses":0,"wins":0},"google/gemma-4-31b-it":{"draws":0,"losses":3,"wins":3},"gpt-5":{"draws":0,"losses":6,"wins":0},"gpt-5.4":{"draws":0,"losses":4,"wins":0},"gpt-5.4-mini":{"draws":4,"losses":8,"wins":4},"gpt-5.4-nano":{"draws":1,"losses":12,"wins":13},"gpt-5.5":{"draws":0,"losses":2,"wins":0},"gpt-5.6-luna":{"draws":0,"losses":2,"wins":2},"gpt-5.6-sol":{"draws":0,"losses":4,"wins":0},"gpt-5.6-terra":{"draws":0,"losses":6,"wins":0},"inclusionai/ling-3.0-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":0,"losses":2,"wins":2},"mistralai/mistral-medium-3-5":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":1,"losses":17,"wins":0},"nex-agi/nex-n2-pro":{"draws":0,"losses":2,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":8,"wins":4},"o3":{"draws":0,"losses":6,"wins":0},"openai/gpt-oss-120b":{"draws":0,"losses":4,"wins":0},"poolside/laguna-s-2.1":{"draws":0,"losses":1,"wins":1},"qwen/qwen3.7-max":{"draws":0,"losses":2,"wins":2},"stepfun/step-3.7-flash":{"draws":0,"losses":6,"wins":2},"tencent/hy3-preview":{"draws":0,"losses":6,"wins":2},"thinkingmachines/inkling":{"draws":4,"losses":3,"wins":3},"x-ai/grok-4.5":{"draws":0,"losses":8,"wins":0},"x-ai/grok-build-0.1":{"draws":0,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":1,"losses":7,"wins":2},"z-ai/glm-5.2":{"draws":2,"losses":16,"wins":2}},"moonshotai/kimi-k3":{"claude-fable-5":{"draws":7,"losses":34,"wins":5},"claude-opus-4-5":{"draws":11,"losses":11,"wins":22},"claude-opus-4-8":{"draws":11,"losses":16,"wins":11},"claude-opus-5":{"draws":11,"losses":23,"wins":6},"claude-sonnet-5":{"draws":11,"losses":11,"wins":16},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":1},"deepseek/deepseek-v4-flash":{"draws":15,"losses":8,"wins":23},"deepseek/deepseek-v4-pro":{"draws":5,"losses":9,"wins":10},"google/gemini-3.1-flash-lite":{"draws":6,"losses":0,"wins":18},"google/gemini-3.5-flash":{"draws":13,"losses":10,"wins":21},"google/gemini-3.5-flash-lite":{"draws":13,"losses":2,"wins":23},"google/gemini-3.6-flash":{"draws":11,"losses":8,"wins":13},"google/gemma-4-31b-it":{"draws":2,"losses":1,"wins":3},"gpt-4.1":{"draws":4,"losses":5,"wins":3},"gpt-5":{"draws":16,"losses":12,"wins":6},"gpt-5.4":{"draws":8,"losses":30,"wins":4},"gpt-5.4-mini":{"draws":15,"losses":11,"wins":16},"gpt-5.4-nano":{"draws":25,"losses":22,"wins":34},"gpt-5.5":{"draws":11,"losses":20,"wins":7},"gpt-5.6-luna":{"draws":6,"losses":13,"wins":7},"gpt-5.6-sol":{"draws":13,"losses":33,"wins":16},"gpt-5.6-terra":{"draws":16,"losses":8,"wins":16},"inclusionai/ling-3.0-flash":{"draws":4,"losses":1,"wins":7},"meituan/longcat-2.0":{"draws":9,"losses":1,"wins":12},"minimax/minimax-m3":{"draws":1,"losses":1,"wins":2},"mistralai/mistral-medium-3-5":{"draws":1,"losses":0,"wins":17},"moonshotai/kimi-k3":{"draws":21,"losses":20,"wins":27},"nex-agi/nex-n2-pro":{"draws":4,"losses":0,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":24,"losses":2,"wins":22},"o3":{"draws":2,"losses":4,"wins":12},"openai/gpt-oss-120b":{"draws":19,"losses":0,"wins":13},"poolside/laguna-s-2.1":{"draws":10,"losses":4,"wins":10},"qwen/qwen3.7-plus":{"draws":0,"losses":3,"wins":1},"stepfun/step-3.7-flash":{"draws":4,"losses":1,"wins":11},"tencent/hy3-preview":{"draws":9,"losses":11,"wins":14},"thinkingmachines/inkling":{"draws":7,"losses":1,"wins":14},"x-ai/grok-4.5":{"draws":19,"losses":43,"wins":36},"xiaomi/mimo-v2.5":{"draws":7,"losses":1,"wins":0},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":2},"z-ai/glm-5.2":{"draws":41,"losses":26,"wins":37}},"nvidia/nemotron-3-ultra-550b-a55b":{"claude-opus-4-5":{"draws":14,"losses":9,"wins":1},"claude-opus-4-8":{"draws":3,"losses":8,"wins":3},"claude-sonnet-5":{"draws":18,"losses":10,"wins":0},"cohere/north-mini-code":{"draws":0,"losses":2,"wins":2},"deepseek/deepseek-v4-flash":{"draws":20,"losses":14,"wins":12},"deepseek/deepseek-v4-pro":{"draws":6,"losses":3,"wins":3},"google/gemini-3.1-flash-lite":{"draws":7,"losses":4,"wins":10},"google/gemini-3.5-flash":{"draws":2,"losses":6,"wins":2},"google/gemini-3.5-flash-lite":{"draws":0,"losses":1,"wins":1},"google/gemini-3.6-flash":{"draws":3,"losses":0,"wins":1},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":2},"gpt-4.1":{"draws":4,"losses":2,"wins":2},"gpt-5":{"draws":8,"losses":3,"wins":1},"gpt-5.4":{"draws":3,"losses":5,"wins":0},"gpt-5.4-mini":{"draws":26,"losses":8,"wins":6},"gpt-5.4-nano":{"draws":29,"losses":8,"wins":7},"gpt-5.5":{"draws":4,"losses":2,"wins":0},"gpt-5.6-luna":{"draws":6,"losses":3,"wins":1},"gpt-5.6-sol":{"draws":2,"losses":8,"wins":4},"gpt-5.6-terra":{"draws":12,"losses":11,"wins":1},"inclusionai/ling-3.0-flash":{"draws":4,"losses":1,"wins":1},"meituan/longcat-2.0":{"draws":1,"losses":0,"wins":1},"minimax/minimax-m3":{"draws":6,"losses":2,"wins":0},"mistralai/mistral-medium-3-5":{"draws":2,"losses":2,"wins":8},"moonshotai/kimi-k3":{"draws":21,"losses":12,"wins":1},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":5,"wins":3},"o3":{"draws":2,"losses":9,"wins":1},"openai/gpt-oss-120b":{"draws":10,"losses":2,"wins":0},"poolside/laguna-s-2.1":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.7-max":{"draws":6,"losses":0,"wins":0},"qwen/qwen3.7-plus":{"draws":3,"losses":1,"wins":0},"stepfun/step-3.7-flash":{"draws":6,"losses":5,"wins":5},"tencent/hy3-preview":{"draws":9,"losses":7,"wins":2},"thinkingmachines/inkling":{"draws":4,"losses":3,"wins":1},"x-ai/grok-4.5":{"draws":10,"losses":13,"wins":5},"x-ai/grok-build-0.1":{"draws":4,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":6,"losses":2,"wins":2},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":1,"wins":1},"z-ai/glm-5.2":{"draws":23,"losses":19,"wins":16}},"o3":{"claude-fable-5":{"draws":0,"losses":7,"wins":1},"claude-opus-4-5":{"draws":4,"losses":6,"wins":8},"claude-opus-4-8":{"draws":0,"losses":8,"wins":4},"claude-opus-5":{"draws":0,"losses":6,"wins":0},"claude-sonnet-5":{"draws":0,"losses":5,"wins":9},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":2},"deepseek/deepseek-v4-flash":{"draws":0,"losses":4,"wins":12},"deepseek/deepseek-v4-pro":{"draws":1,"losses":4,"wins":3},"google/gemini-3.1-flash-lite":{"draws":0,"losses":4,"wins":6},"google/gemini-3.5-flash":{"draws":0,"losses":3,"wins":3},"google/gemini-3.5-flash-lite":{"draws":0,"losses":0,"wins":2},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":2},"gpt-4.1":{"draws":1,"losses":0,"wins":1},"gpt-5":{"draws":0,"losses":6,"wins":2},"gpt-5.4":{"draws":0,"losses":2,"wins":2},"gpt-5.4-mini":{"draws":1,"losses":7,"wins":12},"gpt-5.4-nano":{"draws":1,"losses":11,"wins":4},"gpt-5.5":{"draws":0,"losses":2,"wins":0},"gpt-5.6-luna":{"draws":0,"losses":4,"wins":2},"gpt-5.6-sol":{"draws":0,"losses":1,"wins":1},"gpt-5.6-terra":{"draws":0,"losses":3,"wins":1},"meituan/longcat-2.0":{"draws":0,"losses":0,"wins":2},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":1},"moonshotai/kimi-k3":{"draws":0,"losses":12,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":1,"wins":11},"o3":{"draws":0,"losses":1,"wins":1},"openai/gpt-oss-120b":{"draws":1,"losses":2,"wins":1},"stepfun/step-3.7-flash":{"draws":0,"losses":1,"wins":3},"tencent/hy3-preview":{"draws":0,"losses":6,"wins":4},"thinkingmachines/inkling":{"draws":0,"losses":0,"wins":6},"x-ai/grok-4.5":{"draws":1,"losses":16,"wins":5},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":4},"xiaomi/mimo-v2.5":{"draws":2,"losses":0,"wins":4},"z-ai/glm-5.2":{"draws":0,"losses":13,"wins":11}},"openai/gpt-oss-120b":{"claude-fable-5":{"draws":1,"losses":7,"wins":0},"claude-opus-4-5":{"draws":7,"losses":2,"wins":5},"claude-opus-4-8":{"draws":3,"losses":5,"wins":0},"claude-sonnet-5":{"draws":4,"losses":6,"wins":2},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":0},"deepseek/deepseek-v4-flash":{"draws":11,"losses":0,"wins":11},"deepseek/deepseek-v4-pro":{"draws":2,"losses":0,"wins":2},"google/gemini-3.1-flash-lite":{"draws":4,"losses":2,"wins":4},"google/gemini-3.5-flash":{"draws":4,"losses":3,"wins":3},"google/gemini-3.5-flash-lite":{"draws":2,"losses":0,"wins":0},"google/gemini-3.6-flash":{"draws":1,"losses":1,"wins":0},"gpt-4.1":{"draws":2,"losses":2,"wins":2},"gpt-5":{"draws":2,"losses":2,"wins":0},"gpt-5.4":{"draws":0,"losses":6,"wins":2},"gpt-5.4-mini":{"draws":10,"losses":1,"wins":5},"gpt-5.4-nano":{"draws":10,"losses":6,"wins":10},"gpt-5.5":{"draws":4,"losses":2,"wins":2},"gpt-5.6-luna":{"draws":3,"losses":6,"wins":1},"gpt-5.6-sol":{"draws":5,"losses":2,"wins":3},"gpt-5.6-terra":{"draws":1,"losses":6,"wins":1},"meituan/longcat-2.0":{"draws":2,"losses":0,"wins":0},"minimax/minimax-m3":{"draws":1,"losses":1,"wins":0},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":4},"moonshotai/kimi-k3":{"draws":17,"losses":13,"wins":0},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":0,"wins":2},"o3":{"draws":1,"losses":1,"wins":2},"openai/gpt-oss-120b":{"draws":5,"losses":0,"wins":1},"qwen/qwen3.7-max":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":0},"stepfun/step-3.7-flash":{"draws":4,"losses":1,"wins":3},"tencent/hy3-preview":{"draws":3,"losses":3,"wins":2},"x-ai/grok-4.5":{"draws":2,"losses":8,"wins":4},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":6,"losses":0,"wins":0},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":4,"wins":1},"z-ai/glm-5.2":{"draws":10,"losses":12,"wins":8}},"stepfun/step-3.7-flash":{"claude-fable-5":{"draws":0,"losses":4,"wins":0},"claude-opus-4-5":{"draws":2,"losses":9,"wins":3},"claude-opus-4-8":{"draws":0,"losses":2,"wins":2},"claude-sonnet-5":{"draws":2,"losses":7,"wins":1},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":3},"deepseek/deepseek-v4-flash":{"draws":4,"losses":11,"wins":11},"deepseek/deepseek-v4-pro":{"draws":2,"losses":7,"wins":1},"google/gemini-3.1-flash-lite":{"draws":2,"losses":3,"wins":7},"google/gemini-3.5-flash":{"draws":2,"losses":2,"wins":0},"google/gemini-3.6-flash":{"draws":0,"losses":2,"wins":0},"gpt-4.1":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":2,"losses":6,"wins":0},"gpt-5.4-mini":{"draws":4,"losses":15,"wins":5},"gpt-5.4-nano":{"draws":6,"losses":16,"wins":8},"gpt-5.6-luna":{"draws":0,"losses":1,"wins":3},"gpt-5.6-sol":{"draws":0,"losses":3,"wins":1},"gpt-5.6-terra":{"draws":2,"losses":4,"wins":0},"meituan/longcat-2.0":{"draws":2,"losses":2,"wins":0},"minimax/minimax-m3":{"draws":0,"losses":2,"wins":0},"mistralai/mistral-medium-3-5":{"draws":0,"losses":4,"wins":8},"moonshotai/kimi-k3":{"draws":4,"losses":11,"wins":1},"nex-agi/nex-n2-pro":{"draws":1,"losses":1,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":5,"wins":7},"o3":{"draws":0,"losses":3,"wins":1},"openai/gpt-oss-120b":{"draws":6,"losses":3,"wins":1},"qwen/qwen3.7-max":{"draws":0,"losses":5,"wins":1},"qwen/qwen3.7-plus":{"draws":0,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":0,"losses":5,"wins":5},"thinkingmachines/inkling":{"draws":0,"losses":2,"wins":10},"x-ai/grok-4.5":{"draws":0,"losses":19,"wins":3},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":6,"losses":3,"wins":3},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":3,"wins":1},"z-ai/glm-5.2":{"draws":2,"losses":12,"wins":6}},"tencent/hy3-preview":{"claude-fable-5":{"draws":0,"losses":5,"wins":1},"claude-opus-4-5":{"draws":9,"losses":9,"wins":2},"claude-opus-4-8":{"draws":2,"losses":5,"wins":3},"claude-opus-5":{"draws":0,"losses":2,"wins":0},"claude-sonnet-5":{"draws":2,"losses":8,"wins":4},"cohere/north-mini-code":{"draws":1,"losses":2,"wins":1},"deepseek/deepseek-v4-flash":{"draws":8,"losses":8,"wins":8},"deepseek/deepseek-v4-pro":{"draws":0,"losses":6,"wins":2},"google/gemini-3.1-flash-lite":{"draws":2,"losses":6,"wins":6},"google/gemini-3.5-flash":{"draws":2,"losses":6,"wins":2},"google/gemini-3.5-flash-lite":{"draws":2,"losses":2,"wins":0},"google/gemini-3.6-flash":{"draws":2,"losses":0,"wins":2},"google/gemma-4-31b-it":{"draws":0,"losses":1,"wins":3},"gpt-4.1":{"draws":2,"losses":4,"wins":0},"gpt-5":{"draws":1,"losses":7,"wins":6},"gpt-5.4":{"draws":3,"losses":7,"wins":2},"gpt-5.4-mini":{"draws":9,"losses":13,"wins":6},"gpt-5.4-nano":{"draws":14,"losses":11,"wins":7},"gpt-5.5":{"draws":8,"losses":5,"wins":1},"gpt-5.6-luna":{"draws":4,"losses":4,"wins":2},"gpt-5.6-sol":{"draws":2,"losses":13,"wins":7},"gpt-5.6-terra":{"draws":2,"losses":2,"wins":0},"inclusionai/ling-3.0-flash":{"draws":2,"losses":1,"wins":3},"meituan/longcat-2.0":{"draws":2,"losses":1,"wins":1},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":2},"mistralai/mistral-medium-3-5":{"draws":0,"losses":2,"wins":6},"moonshotai/kimi-k3":{"draws":7,"losses":14,"wins":11},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":4,"wins":10},"o3":{"draws":2,"losses":6,"wins":6},"openai/gpt-oss-120b":{"draws":4,"losses":2,"wins":4},"poolside/laguna-s-2.1":{"draws":0,"losses":1,"wins":1},"qwen/qwen3.7-max":{"draws":4,"losses":3,"wins":1},"qwen/qwen3.7-plus":{"draws":0,"losses":2,"wins":4},"stepfun/step-3.7-flash":{"draws":0,"losses":5,"wins":5},"tencent/hy3-preview":{"draws":1,"losses":0,"wins":1},"thinkingmachines/inkling":{"draws":0,"losses":1,"wins":1},"x-ai/grok-4.5":{"draws":4,"losses":23,"wins":3},"xiaomi/mimo-v2.5":{"draws":3,"losses":5,"wins":6},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":1,"wins":1},"z-ai/glm-5.2":{"draws":14,"losses":11,"wins":13}},"thinkingmachines/inkling":{"google/gemini-3.5-flash-lite":{"draws":16,"losses":14,"wins":12},"google/gemini-3.6-flash":{"draws":17,"losses":23,"wins":6},"gpt-5.6-terra":{"draws":2,"losses":0,"wins":0},"inclusionai/ling-3.0-flash":{"draws":6,"losses":3,"wins":3},"meituan/longcat-2.0":{"draws":7,"losses":6,"wins":11},"moonshotai/kimi-k3":{"draws":7,"losses":9,"wins":4},"poolside/laguna-s-2.1":{"draws":12,"losses":9,"wins":1},"thinkingmachines/inkling":{"draws":4,"losses":7,"wins":7},"x-ai/grok-4.5":{"draws":2,"losses":9,"wins":3}},"x-ai/grok-4.5":{"claude-fable-5":{"draws":4,"losses":33,"wins":9},"claude-opus-4-5":{"draws":16,"losses":10,"wins":28},"claude-opus-4-8":{"draws":8,"losses":19,"wins":13},"claude-opus-5":{"draws":9,"losses":27,"wins":16},"claude-sonnet-5":{"draws":16,"losses":12,"wins":18},"deepseek/deepseek-v4-flash":{"draws":4,"losses":7,"wins":29},"deepseek/deepseek-v4-pro":{"draws":6,"losses":7,"wins":21},"google/gemini-3.1-flash-lite":{"draws":4,"losses":1,"wins":11},"google/gemini-3.5-flash":{"draws":2,"losses":10,"wins":2},"google/gemini-3.5-flash-lite":{"draws":10,"losses":14,"wins":34},"google/gemini-3.6-flash":{"draws":9,"losses":20,"wins":19},"gpt-4.1":{"draws":0,"losses":1,"wins":1},"gpt-5":{"draws":5,"losses":9,"wins":10},"gpt-5.4":{"draws":15,"losses":27,"wins":10},"gpt-5.4-mini":{"draws":7,"losses":10,"wins":39},"gpt-5.4-nano":{"draws":17,"losses":23,"wins":24},"gpt-5.5":{"draws":8,"losses":16,"wins":16},"gpt-5.6-luna":{"draws":5,"losses":16,"wins":19},"gpt-5.6-sol":{"draws":4,"losses":32,"wins":14},"gpt-5.6-terra":{"draws":1,"losses":17,"wins":16},"inclusionai/ling-3.0-flash":{"draws":2,"losses":2,"wins":14},"meituan/longcat-2.0":{"draws":10,"losses":3,"wins":25},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":4},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":19,"losses":36,"wins":45},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":7,"wins":18},"o3":{"draws":1,"losses":7,"wins":16},"openai/gpt-oss-120b":{"draws":1,"losses":4,"wins":7},"poolside/laguna-s-2.1":{"draws":9,"losses":4,"wins":27},"qwen/qwen3.7-max":{"draws":0,"losses":3,"wins":3},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":10},"stepfun/step-3.7-flash":{"draws":2,"losses":4,"wins":18},"tencent/hy3-preview":{"draws":5,"losses":5,"wins":18},"thinkingmachines/inkling":{"draws":9,"losses":6,"wins":17},"x-ai/grok-4.5":{"draws":22,"losses":47,"wins":55},"x-ai/grok-build-0.1":{"draws":2,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":4,"losses":1,"wins":9},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":4,"wins":7},"z-ai/glm-5.2":{"draws":7,"losses":26,"wins":43}},"xiaomi/mimo-v2.5":{"claude-fable-5":{"draws":0,"losses":2,"wins":0},"claude-opus-4-5":{"draws":0,"losses":4,"wins":2},"claude-opus-4-8":{"draws":2,"losses":2,"wins":0},"claude-sonnet-5":{"draws":5,"losses":4,"wins":1},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":0},"deepseek/deepseek-v4-flash":{"draws":4,"losses":0,"wins":0},"deepseek/deepseek-v4-pro":{"draws":2,"losses":2,"wins":0},"google/gemini-3.1-flash-lite":{"draws":6,"losses":0,"wins":0},"google/gemini-3.5-flash":{"draws":1,"losses":0,"wins":1},"google/gemini-3.5-flash-lite":{"draws":4,"losses":0,"wins":0},"google/gemini-3.6-flash":{"draws":5,"losses":1,"wins":0},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":0},"gpt-4.1":{"draws":0,"losses":1,"wins":1},"gpt-5":{"draws":0,"losses":0,"wins":2},"gpt-5.4":{"draws":2,"losses":0,"wins":0},"gpt-5.4-mini":{"draws":12,"losses":3,"wins":3},"gpt-5.4-nano":{"draws":18,"losses":2,"wins":2},"gpt-5.5":{"draws":0,"losses":0,"wins":2},"gpt-5.6-luna":{"draws":2,"losses":4,"wins":0},"inclusionai/ling-3.0-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":6,"losses":2,"wins":0},"minimax/minimax-m3":{"draws":1,"losses":3,"wins":0},"mistralai/mistral-medium-3-5":{"draws":1,"losses":1,"wins":0},"moonshotai/kimi-k3":{"draws":3,"losses":0,"wins":1},"nex-agi/nex-n2-pro":{"draws":3,"losses":0,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":0,"wins":0},"o3":{"draws":3,"losses":1,"wins":0},"openai/gpt-oss-120b":{"draws":2,"losses":0,"wins":2},"poolside/laguna-s-2.1":{"draws":4,"losses":0,"wins":0},"qwen/qwen3.7-max":{"draws":3,"losses":3,"wins":0},"stepfun/step-3.7-flash":{"draws":4,"losses":0,"wins":2},"thinkingmachines/inkling":{"draws":8,"losses":0,"wins":0},"x-ai/grok-4.5":{"draws":0,"losses":1,"wins":1},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":4,"losses":2,"wins":0},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":2,"wins":0},"z-ai/glm-5.2":{"draws":14,"losses":3,"wins":1}},"z-ai/glm-5.2":{"claude-fable-5":{"draws":1,"losses":19,"wins":2},"claude-opus-4-5":{"draws":17,"losses":17,"wins":20},"claude-opus-4-8":{"draws":5,"losses":17,"wins":6},"claude-opus-5":{"draws":10,"losses":26,"wins":6},"claude-sonnet-5":{"draws":16,"losses":12,"wins":20},"cohere/north-mini-code":{"draws":7,"losses":0,"wins":3},"deepseek/deepseek-v4-flash":{"draws":21,"losses":12,"wins":19},"deepseek/deepseek-v4-pro":{"draws":8,"losses":13,"wins":3},"google/gemini-3.1-flash-lite":{"draws":6,"losses":2,"wins":14},"google/gemini-3.5-flash":{"draws":9,"losses":9,"wins":8},"google/gemini-3.5-flash-lite":{"draws":6,"losses":1,"wins":3},"google/gemini-3.6-flash":{"draws":7,"losses":1,"wins":0},"google/gemma-4-31b-it":{"draws":3,"losses":2,"wins":1},"gpt-4.1":{"draws":1,"losses":4,"wins":3},"gpt-5":{"draws":18,"losses":14,"wins":12},"gpt-5.4":{"draws":12,"losses":23,"wins":9},"gpt-5.4-mini":{"draws":29,"losses":21,"wins":24},"gpt-5.4-nano":{"draws":37,"losses":15,"wins":23},"gpt-5.5":{"draws":9,"losses":13,"wins":8},"gpt-5.6-luna":{"draws":11,"losses":10,"wins":11},"gpt-5.6-sol":{"draws":9,"losses":20,"wins":9},"gpt-5.6-terra":{"draws":6,"losses":6,"wins":6},"inclusionai/ling-3.0-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":8,"losses":0,"wins":0},"minimax/minimax-m3":{"draws":4,"losses":0,"wins":0},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":14},"moonshotai/kimi-k3":{"draws":32,"losses":19,"wins":17},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":21,"losses":6,"wins":15},"o3":{"draws":2,"losses":6,"wins":12},"openai/gpt-oss-120b":{"draws":10,"losses":9,"wins":7},"poolside/laguna-s-2.1":{"draws":9,"losses":3,"wins":2},"qwen/qwen3.7-max":{"draws":7,"losses":1,"wins":0},"qwen/qwen3.7-plus":{"draws":4,"losses":1,"wins":3},"stepfun/step-3.7-flash":{"draws":2,"losses":5,"wins":9},"tencent/hy3-preview":{"draws":11,"losses":10,"wins":5},"thinkingmachines/inkling":{"draws":4,"losses":2,"wins":6},"x-ai/grok-4.5":{"draws":8,"losses":41,"wins":25},"x-ai/grok-build-0.1":{"draws":4,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":14,"losses":3,"wins":17},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":1,"wins":4},"z-ai/glm-5.2":{"draws":31,"losses":28,"wins":27}}},"medium":{"claude-fable-5":{"claude-fable-5":{"draws":1,"losses":5,"wins":0},"claude-opus-4-5":{"draws":2,"losses":1,"wins":11},"claude-opus-4-8":{"draws":1,"losses":8,"wins":5},"claude-opus-5":{"draws":8,"losses":20,"wins":12},"claude-sonnet-5":{"draws":0,"losses":0,"wins":2},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":2},"google/gemini-3.5-flash":{"draws":3,"losses":7,"wins":4},"google/gemini-3.6-flash":{"draws":0,"losses":2,"wins":0},"google/gemma-4-31b-it":{"draws":1,"losses":1,"wins":0},"gpt-5":{"draws":1,"losses":1,"wins":6},"gpt-5.4":{"draws":4,"losses":6,"wins":8},"gpt-5.4-mini":{"draws":5,"losses":2,"wins":11},"gpt-5.4-nano":{"draws":2,"losses":6,"wins":18},"gpt-5.5":{"draws":2,"losses":7,"wins":7},"gpt-5.6-luna":{"draws":0,"losses":0,"wins":6},"gpt-5.6-sol":{"draws":2,"losses":8,"wins":12},"gpt-5.6-terra":{"draws":2,"losses":3,"wins":13},"meituan/longcat-2.0":{"draws":0,"losses":1,"wins":1},"minimax/minimax-m3":{"draws":1,"losses":0,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":7},"moonshotai/kimi-k3":{"draws":7,"losses":3,"wins":12},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":0,"wins":2},"o3":{"draws":0,"losses":1,"wins":7},"poolside/laguna-s-2.1":{"draws":0,"losses":2,"wins":0},"qwen/qwen3.7-max":{"draws":1,"losses":0,"wins":7},"qwen/qwen3.7-plus":{"draws":1,"losses":0,"wins":5},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":8},"tencent/hy3-preview":{"draws":1,"losses":2,"wins":1},"thinkingmachines/inkling":{"draws":0,"losses":0,"wins":2},"x-ai/grok-4.5":{"draws":11,"losses":15,"wins":20},"x-ai/grok-build-0.1":{"draws":0,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":1,"losses":0,"wins":7},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":10},"z-ai/glm-5.2":{"draws":0,"losses":4,"wins":10}},"claude-opus-4-8":{"claude-fable-5":{"draws":0,"losses":3,"wins":5},"claude-opus-4-5":{"draws":2,"losses":2,"wins":6},"claude-opus-4-8":{"draws":2,"losses":4,"wins":2},"claude-opus-5":{"draws":2,"losses":4,"wins":0},"claude-sonnet-5":{"draws":8,"losses":2,"wins":6},"cohere/north-mini-code":{"draws":3,"losses":2,"wins":1},"deepseek/deepseek-v4-flash":{"draws":8,"losses":2,"wins":2},"deepseek/deepseek-v4-pro":{"draws":3,"losses":4,"wins":3},"google/gemini-3.1-flash-lite":{"draws":6,"losses":0,"wins":6},"google/gemini-3.5-flash":{"draws":4,"losses":4,"wins":0},"google/gemini-3.5-flash-lite":{"draws":0,"losses":0,"wins":2},"google/gemini-3.6-flash":{"draws":1,"losses":1,"wins":0},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":0},"gpt-4.1":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":3,"losses":1,"wins":6},"gpt-5.4":{"draws":3,"losses":3,"wins":6},"gpt-5.4-mini":{"draws":10,"losses":6,"wins":4},"gpt-5.4-nano":{"draws":10,"losses":6,"wins":8},"gpt-5.5":{"draws":6,"losses":4,"wins":4},"gpt-5.6-luna":{"draws":5,"losses":5,"wins":4},"gpt-5.6-sol":{"draws":3,"losses":7,"wins":4},"gpt-5.6-terra":{"draws":6,"losses":2,"wins":2},"minimax/minimax-m3":{"draws":6,"losses":0,"wins":0},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":3,"wins":1},"moonshotai/kimi-k3":{"draws":5,"losses":11,"wins":6},"nex-agi/nex-n2-pro":{"draws":8,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":5,"wins":5},"o3":{"draws":4,"losses":2,"wins":4},"openai/gpt-oss-120b":{"draws":3,"losses":1,"wins":2},"qwen/qwen3.7-max":{"draws":0,"losses":2,"wins":6},"qwen/qwen3.7-plus":{"draws":4,"losses":2,"wins":8},"stepfun/step-3.7-flash":{"draws":0,"losses":3,"wins":1},"tencent/hy3-preview":{"draws":2,"losses":3,"wins":1},"thinkingmachines/inkling":{"draws":0,"losses":1,"wins":1},"x-ai/grok-4.5":{"draws":2,"losses":13,"wins":1},"x-ai/grok-build-0.1":{"draws":3,"losses":3,"wins":4},"xiaomi/mimo-v2.5":{"draws":12,"losses":0,"wins":8},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":1,"wins":7},"z-ai/glm-5.2":{"draws":9,"losses":3,"wins":12}},"claude-opus-5":{"claude-fable-5":{"draws":8,"losses":16,"wins":8},"claude-opus-4-5":{"draws":6,"losses":3,"wins":39},"claude-opus-4-8":{"draws":3,"losses":2,"wins":7},"claude-opus-5":{"draws":15,"losses":59,"wins":54},"claude-sonnet-5":{"draws":5,"losses":2,"wins":25},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":3},"deepseek/deepseek-v4-flash":{"draws":1,"losses":0,"wins":1},"deepseek/deepseek-v4-pro":{"draws":1,"losses":0,"wins":5},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":4},"google/gemini-3.5-flash":{"draws":1,"losses":5,"wins":6},"google/gemini-3.5-flash-lite":{"draws":3,"losses":2,"wins":11},"google/gemini-3.6-flash":{"draws":0,"losses":8,"wins":18},"gpt-4.1":{"draws":2,"losses":0,"wins":8},"gpt-5":{"draws":1,"losses":1,"wins":2},"gpt-5.4":{"draws":3,"losses":7,"wins":12},"gpt-5.4-mini":{"draws":0,"losses":3,"wins":11},"gpt-5.4-nano":{"draws":4,"losses":6,"wins":18},"gpt-5.5":{"draws":2,"losses":10,"wins":8},"gpt-5.6-luna":{"draws":0,"losses":3,"wins":5},"gpt-5.6-sol":{"draws":3,"losses":10,"wins":15},"gpt-5.6-terra":{"draws":8,"losses":1,"wins":7},"inclusionai/ling-3.0-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":1,"losses":1,"wins":6},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":10,"losses":2,"wins":22},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":0,"wins":2},"o3":{"draws":0,"losses":0,"wins":8},"poolside/laguna-s-2.1":{"draws":0,"losses":0,"wins":10},"qwen/qwen3.7-max":{"draws":0,"losses":2,"wins":10},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":0,"losses":2,"wins":4},"thinkingmachines/inkling":{"draws":0,"losses":0,"wins":16},"x-ai/grok-4.5":{"draws":9,"losses":28,"wins":47},"x-ai/grok-build-0.1":{"draws":1,"losses":1,"wins":0},"xiaomi/mimo-v2.5":{"draws":1,"losses":0,"wins":3},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":0,"wins":3},"z-ai/glm-5.2":{"draws":6,"losses":5,"wins":23}},"claude-sonnet-5":{"claude-fable-5":{"draws":0,"losses":2,"wins":0},"claude-opus-4-5":{"draws":6,"losses":7,"wins":5},"claude-opus-4-8":{"draws":6,"losses":2,"wins":4},"claude-opus-5":{"draws":0,"losses":12,"wins":0},"claude-sonnet-5":{"draws":2,"losses":4,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":6},"deepseek/deepseek-v4-flash":{"draws":10,"losses":5,"wins":1},"deepseek/deepseek-v4-pro":{"draws":2,"losses":1,"wins":1},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":2},"google/gemini-3.5-flash":{"draws":3,"losses":5,"wins":2},"google/gemini-3.5-flash-lite":{"draws":0,"losses":0,"wins":4},"google/gemini-3.6-flash":{"draws":2,"losses":0,"wins":0},"google/gemma-4-31b-it":{"draws":0,"losses":2,"wins":4},"gpt-4.1":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":4,"losses":6,"wins":2},"gpt-5.4":{"draws":2,"losses":4,"wins":2},"gpt-5.4-mini":{"draws":8,"losses":11,"wins":11},"gpt-5.4-nano":{"draws":9,"losses":2,"wins":13},"gpt-5.5":{"draws":2,"losses":4,"wins":2},"gpt-5.6-luna":{"draws":2,"losses":2,"wins":2},"gpt-5.6-sol":{"draws":2,"losses":9,"wins":1},"gpt-5.6-terra":{"draws":2,"losses":4,"wins":4},"meituan/longcat-2.0":{"draws":2,"losses":0,"wins":4},"minimax/minimax-m3":{"draws":4,"losses":1,"wins":1},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":1,"wins":4},"moonshotai/kimi-k3":{"draws":6,"losses":9,"wins":1},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":5,"wins":0},"o3":{"draws":3,"losses":4,"wins":7},"openai/gpt-oss-120b":{"draws":0,"losses":0,"wins":4},"poolside/laguna-s-2.1":{"draws":1,"losses":0,"wins":1},"qwen/qwen3.7-max":{"draws":2,"losses":4,"wins":4},"qwen/qwen3.7-plus":{"draws":6,"losses":3,"wins":1},"stepfun/step-3.7-flash":{"draws":0,"losses":1,"wins":3},"tencent/hy3-preview":{"draws":2,"losses":2,"wins":2},"thinkingmachines/inkling":{"draws":4,"losses":0,"wins":2},"x-ai/grok-4.5":{"draws":3,"losses":13,"wins":6},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":8},"xiaomi/mimo-v2.5":{"draws":19,"losses":3,"wins":12},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":1,"wins":3},"z-ai/glm-5.2":{"draws":5,"losses":3,"wins":6}},"cohere/north-mini-code":{"claude-opus-4-5":{"draws":3,"losses":3,"wins":2},"claude-opus-4-8":{"draws":3,"losses":1,"wins":2},"claude-sonnet-5":{"draws":3,"losses":11,"wins":2},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":2},"deepseek/deepseek-v4-flash":{"draws":4,"losses":1,"wins":7},"google/gemini-3.1-flash-lite":{"draws":0,"losses":7,"wins":5},"google/gemini-3.5-flash":{"draws":3,"losses":4,"wins":1},"google/gemini-3.5-flash-lite":{"draws":2,"losses":0,"wins":0},"google/gemini-3.6-flash":{"draws":2,"losses":2,"wins":0},"google/gemma-4-31b-it":{"draws":0,"losses":3,"wins":3},"gpt-4.1":{"draws":1,"losses":1,"wins":0},"gpt-5":{"draws":5,"losses":10,"wins":1},"gpt-5.4":{"draws":3,"losses":6,"wins":5},"gpt-5.4-mini":{"draws":3,"losses":9,"wins":2},"gpt-5.4-nano":{"draws":12,"losses":9,"wins":7},"gpt-5.5":{"draws":4,"losses":1,"wins":1},"gpt-5.6-luna":{"draws":3,"losses":3,"wins":8},"gpt-5.6-sol":{"draws":1,"losses":5,"wins":0},"gpt-5.6-terra":{"draws":0,"losses":6,"wins":2},"inclusionai/ling-3.0-flash":{"draws":4,"losses":1,"wins":1},"meituan/longcat-2.0":{"draws":2,"losses":0,"wins":0},"minimax/minimax-m3":{"draws":2,"losses":3,"wins":3},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":5,"losses":8,"wins":1},"nex-agi/nex-n2-pro":{"draws":6,"losses":4,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":1,"losses":6,"wins":5},"o3":{"draws":1,"losses":1,"wins":2},"openai/gpt-oss-120b":{"draws":6,"losses":1,"wins":3},"poolside/laguna-s-2.1":{"draws":4,"losses":2,"wins":2},"qwen/qwen3.7-max":{"draws":2,"losses":3,"wins":1},"qwen/qwen3.7-plus":{"draws":2,"losses":4,"wins":2},"stepfun/step-3.7-flash":{"draws":0,"losses":3,"wins":1},"tencent/hy3-preview":{"draws":1,"losses":3,"wins":2},"thinkingmachines/inkling":{"draws":0,"losses":0,"wins":2},"x-ai/grok-4.5":{"draws":4,"losses":6,"wins":0},"x-ai/grok-build-0.1":{"draws":2,"losses":4,"wins":2},"xiaomi/mimo-v2.5":{"draws":7,"losses":5,"wins":8},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":0,"wins":4},"z-ai/glm-5.2":{"draws":7,"losses":4,"wins":1}},"deepseek/deepseek-v4-flash":{"claude-fable-5":{"draws":0,"losses":5,"wins":1},"claude-opus-4-5":{"draws":5,"losses":0,"wins":1},"claude-opus-4-8":{"draws":7,"losses":3,"wins":0},"claude-sonnet-5":{"draws":8,"losses":4,"wins":0},"cohere/north-mini-code":{"draws":0,"losses":3,"wins":1},"deepseek/deepseek-v4-flash":{"draws":12,"losses":12,"wins":12},"deepseek/deepseek-v4-pro":{"draws":2,"losses":6,"wins":2},"google/gemini-3.1-flash-lite":{"draws":4,"losses":4,"wins":8},"google/gemini-3.5-flash":{"draws":6,"losses":1,"wins":1},"google/gemini-3.5-flash-lite":{"draws":5,"losses":6,"wins":1},"google/gemini-3.6-flash":{"draws":1,"losses":1,"wins":2},"google/gemma-4-31b-it":{"draws":2,"losses":4,"wins":4},"gpt-4.1":{"draws":2,"losses":6,"wins":4},"gpt-5":{"draws":2,"losses":1,"wins":1},"gpt-5.4":{"draws":6,"losses":9,"wins":5},"gpt-5.4-mini":{"draws":18,"losses":19,"wins":9},"gpt-5.4-nano":{"draws":20,"losses":11,"wins":15},"gpt-5.5":{"draws":7,"losses":7,"wins":0},"gpt-5.6-luna":{"draws":8,"losses":2,"wins":2},"gpt-5.6-sol":{"draws":3,"losses":7,"wins":2},"gpt-5.6-terra":{"draws":6,"losses":7,"wins":3},"inclusionai/ling-3.0-flash":{"draws":0,"losses":3,"wins":3},"meituan/longcat-2.0":{"draws":1,"losses":4,"wins":3},"minimax/minimax-m3":{"draws":4,"losses":7,"wins":3},"mistralai/mistral-medium-3-5":{"draws":7,"losses":6,"wins":1},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":1,"wins":2},"moonshotai/kimi-k3":{"draws":1,"losses":5,"wins":0},"nex-agi/nex-n2-pro":{"draws":4,"losses":5,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":5,"wins":3},"o3":{"draws":3,"losses":5,"wins":2},"openai/gpt-oss-120b":{"draws":8,"losses":4,"wins":0},"poolside/laguna-s-2.1":{"draws":0,"losses":3,"wins":1},"qwen/qwen3.7-max":{"draws":4,"losses":2,"wins":4},"qwen/qwen3.7-plus":{"draws":5,"losses":6,"wins":3},"stepfun/step-3.7-flash":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":4,"losses":3,"wins":3},"thinkingmachines/inkling":{"draws":1,"losses":6,"wins":3},"x-ai/grok-4.5":{"draws":2,"losses":4,"wins":2},"x-ai/grok-build-0.1":{"draws":2,"losses":4,"wins":2},"xiaomi/mimo-v2.5":{"draws":14,"losses":12,"wins":8},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":5,"wins":5},"z-ai/glm-5.2":{"draws":15,"losses":18,"wins":7}},"google/gemini-3.1-flash-lite":{"claude-fable-5":{"draws":0,"losses":4,"wins":0},"claude-opus-4-5":{"draws":4,"losses":4,"wins":0},"claude-opus-4-8":{"draws":4,"losses":5,"wins":1},"claude-opus-5":{"draws":0,"losses":3,"wins":1},"claude-sonnet-5":{"draws":3,"losses":5,"wins":2},"cohere/north-mini-code":{"draws":0,"losses":5,"wins":3},"deepseek/deepseek-v4-flash":{"draws":2,"losses":7,"wins":3},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":6},"google/gemini-3.5-flash-lite":{"draws":0,"losses":4,"wins":2},"google/gemma-4-31b-it":{"draws":4,"losses":4,"wins":2},"gpt-4.1":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":4,"losses":0,"wins":2},"gpt-5.4":{"draws":0,"losses":6,"wins":0},"gpt-5.4-mini":{"draws":7,"losses":14,"wins":5},"gpt-5.4-nano":{"draws":6,"losses":15,"wins":13},"gpt-5.5":{"draws":3,"losses":1,"wins":2},"gpt-5.6-luna":{"draws":2,"losses":1,"wins":7},"gpt-5.6-sol":{"draws":3,"losses":0,"wins":1},"gpt-5.6-terra":{"draws":1,"losses":2,"wins":3},"inclusionai/ling-3.0-flash":{"draws":1,"losses":0,"wins":1},"meituan/longcat-2.0":{"draws":0,"losses":3,"wins":5},"minimax/minimax-m3":{"draws":3,"losses":3,"wins":6},"mistralai/mistral-medium-3-5":{"draws":0,"losses":2,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":4,"wins":0},"moonshotai/kimi-k3":{"draws":9,"losses":6,"wins":1},"nex-agi/nex-n2-pro":{"draws":2,"losses":4,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":1,"wins":7},"o3":{"draws":6,"losses":4,"wins":0},"openai/gpt-oss-120b":{"draws":2,"losses":4,"wins":2},"qwen/qwen3.7-max":{"draws":2,"losses":1,"wins":1},"qwen/qwen3.7-plus":{"draws":0,"losses":4,"wins":2},"stepfun/step-3.7-flash":{"draws":0,"losses":3,"wins":1},"tencent/hy3-preview":{"draws":1,"losses":0,"wins":1},"thinkingmachines/inkling":{"draws":2,"losses":3,"wins":3},"x-ai/grok-4.5":{"draws":2,"losses":6,"wins":0},"x-ai/grok-build-0.1":{"draws":2,"losses":6,"wins":0},"xiaomi/mimo-v2.5":{"draws":2,"losses":12,"wins":6},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":2,"wins":0},"z-ai/glm-5.2":{"draws":11,"losses":6,"wins":1}},"google/gemini-3.5-flash":{"claude-fable-5":{"draws":4,"losses":5,"wins":5},"claude-opus-4-5":{"draws":6,"losses":6,"wins":8},"claude-opus-4-8":{"draws":6,"losses":1,"wins":5},"claude-opus-5":{"draws":2,"losses":21,"wins":9},"claude-sonnet-5":{"draws":6,"losses":3,"wins":9},"cohere/north-mini-code":{"draws":3,"losses":1,"wins":4},"deepseek/deepseek-v4-flash":{"draws":8,"losses":1,"wins":1},"deepseek/deepseek-v4-pro":{"draws":0,"losses":0,"wins":2},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":1},"google/gemini-3.5-flash":{"draws":2,"losses":1,"wins":1},"google/gemini-3.5-flash-lite":{"draws":2,"losses":0,"wins":0},"google/gemini-3.6-flash":{"draws":2,"losses":1,"wins":3},"google/gemma-4-31b-it":{"draws":2,"losses":2,"wins":2},"gpt-4.1":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":4,"losses":3,"wins":3},"gpt-5.4":{"draws":5,"losses":8,"wins":3},"gpt-5.4-mini":{"draws":10,"losses":6,"wins":14},"gpt-5.4-nano":{"draws":10,"losses":3,"wins":11},"gpt-5.5":{"draws":2,"losses":3,"wins":9},"gpt-5.6-luna":{"draws":8,"losses":2,"wins":6},"gpt-5.6-sol":{"draws":5,"losses":4,"wins":3},"gpt-5.6-terra":{"draws":6,"losses":2,"wins":12},"inclusionai/ling-3.0-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":2,"losses":0,"wins":0},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":4,"wins":2},"moonshotai/kimi-k3":{"draws":12,"losses":8,"wins":8},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":0,"wins":2},"o3":{"draws":0,"losses":4,"wins":2},"openai/gpt-oss-120b":{"draws":2,"losses":1,"wins":1},"poolside/laguna-s-2.1":{"draws":4,"losses":0,"wins":0},"qwen/qwen3.7-max":{"draws":3,"losses":7,"wins":2},"qwen/qwen3.7-plus":{"draws":2,"losses":1,"wins":9},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":0,"losses":0,"wins":4},"thinkingmachines/inkling":{"draws":0,"losses":0,"wins":6},"x-ai/grok-4.5":{"draws":9,"losses":5,"wins":10},"x-ai/grok-build-0.1":{"draws":4,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":8,"losses":1,"wins":5},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":2,"wins":3},"z-ai/glm-5.2":{"draws":6,"losses":6,"wins":8}},"google/gemini-3.5-flash-lite":{"claude-opus-4-5":{"draws":3,"losses":0,"wins":3},"claude-opus-4-8":{"draws":1,"losses":6,"wins":1},"claude-opus-5":{"draws":3,"losses":4,"wins":1},"claude-sonnet-5":{"draws":4,"losses":9,"wins":1},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":2},"deepseek/deepseek-v4-flash":{"draws":12,"losses":3,"wins":11},"deepseek/deepseek-v4-pro":{"draws":1,"losses":2,"wins":1},"google/gemini-3.1-flash-lite":{"draws":2,"losses":3,"wins":9},"google/gemini-3.5-flash":{"draws":2,"losses":0,"wins":0},"google/gemini-3.5-flash-lite":{"draws":35,"losses":45,"wins":32},"google/gemini-3.6-flash":{"draws":50,"losses":35,"wins":23},"google/gemma-4-31b-it":{"draws":0,"losses":2,"wins":0},"gpt-4.1":{"draws":0,"losses":1,"wins":1},"gpt-5":{"draws":2,"losses":0,"wins":0},"gpt-5.4":{"draws":6,"losses":2,"wins":0},"gpt-5.4-mini":{"draws":11,"losses":8,"wins":11},"gpt-5.4-nano":{"draws":17,"losses":7,"wins":26},"gpt-5.5":{"draws":2,"losses":0,"wins":0},"gpt-5.6-luna":{"draws":8,"losses":0,"wins":4},"gpt-5.6-sol":{"draws":5,"losses":3,"wins":2},"gpt-5.6-terra":{"draws":11,"losses":1,"wins":0},"inclusionai/ling-3.0-flash":{"draws":16,"losses":12,"wins":18},"meituan/longcat-2.0":{"draws":21,"losses":25,"wins":18},"minimax/minimax-m3":{"draws":3,"losses":2,"wins":1},"mistralai/mistral-medium-3-5":{"draws":0,"losses":4,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":22,"losses":27,"wins":7},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":3,"wins":6},"o3":{"draws":0,"losses":5,"wins":1},"openai/gpt-oss-120b":{"draws":6,"losses":0,"wins":0},"poolside/laguna-s-2.1":{"draws":28,"losses":34,"wins":14},"qwen/qwen3.7-max":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.7-plus":{"draws":4,"losses":3,"wins":3},"tencent/hy3-preview":{"draws":4,"losses":1,"wins":3},"thinkingmachines/inkling":{"draws":18,"losses":34,"wins":24},"x-ai/grok-4.5":{"draws":23,"losses":38,"wins":5},"x-ai/grok-build-0.1":{"draws":0,"losses":2,"wins":2},"xiaomi/mimo-v2.5":{"draws":6,"losses":1,"wins":3},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":1,"wins":5},"z-ai/glm-5.2":{"draws":9,"losses":8,"wins":5}},"google/gemini-3.6-flash":{"claude-fable-5":{"draws":1,"losses":2,"wins":3},"claude-opus-4-5":{"draws":3,"losses":3,"wins":4},"claude-opus-4-8":{"draws":2,"losses":0,"wins":2},"claude-opus-5":{"draws":4,"losses":23,"wins":15},"claude-sonnet-5":{"draws":5,"losses":1,"wins":2},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":2},"deepseek/deepseek-v4-flash":{"draws":13,"losses":5,"wins":6},"deepseek/deepseek-v4-pro":{"draws":0,"losses":0,"wins":2},"google/gemini-3.1-flash-lite":{"draws":4,"losses":0,"wins":2},"google/gemini-3.5-flash":{"draws":4,"losses":3,"wins":1},"google/gemini-3.5-flash-lite":{"draws":57,"losses":30,"wins":55},"google/gemini-3.6-flash":{"draws":39,"losses":36,"wins":27},"google/gemma-4-31b-it":{"draws":1,"losses":1,"wins":0},"gpt-4.1":{"draws":1,"losses":3,"wins":0},"gpt-5":{"draws":1,"losses":2,"wins":1},"gpt-5.4":{"draws":4,"losses":11,"wins":5},"gpt-5.4-mini":{"draws":10,"losses":2,"wins":10},"gpt-5.4-nano":{"draws":17,"losses":10,"wins":21},"gpt-5.5":{"draws":4,"losses":7,"wins":3},"gpt-5.6-luna":{"draws":2,"losses":3,"wins":3},"gpt-5.6-sol":{"draws":2,"losses":8,"wins":4},"gpt-5.6-terra":{"draws":2,"losses":2,"wins":2},"inclusionai/ling-3.0-flash":{"draws":31,"losses":3,"wins":18},"meituan/longcat-2.0":{"draws":22,"losses":21,"wins":39},"minimax/minimax-m3":{"draws":5,"losses":0,"wins":3},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":1},"moonshotai/kimi-k3":{"draws":22,"losses":23,"wins":21},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":2,"wins":1},"o3":{"draws":1,"losses":0,"wins":1},"openai/gpt-oss-120b":{"draws":1,"losses":0,"wins":1},"poolside/laguna-s-2.1":{"draws":20,"losses":6,"wins":28},"qwen/qwen3.7-max":{"draws":1,"losses":1,"wins":2},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":0},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":4,"losses":4,"wins":0},"thinkingmachines/inkling":{"draws":36,"losses":15,"wins":37},"x-ai/grok-4.5":{"draws":20,"losses":23,"wins":37},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":13,"losses":3,"wins":8},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":0,"wins":3},"z-ai/glm-5.2":{"draws":13,"losses":5,"wins":8}},"google/gemma-4-31b-it":{"claude-fable-5":{"draws":1,"losses":0,"wins":1},"claude-opus-4-5":{"draws":2,"losses":4,"wins":4},"claude-opus-4-8":{"draws":2,"losses":0,"wins":0},"claude-sonnet-5":{"draws":2,"losses":6,"wins":2},"cohere/north-mini-code":{"draws":0,"losses":3,"wins":3},"deepseek/deepseek-v4-flash":{"draws":0,"losses":1,"wins":5},"deepseek/deepseek-v4-pro":{"draws":0,"losses":2,"wins":0},"google/gemini-3.1-flash-lite":{"draws":2,"losses":4,"wins":4},"google/gemini-3.5-flash":{"draws":0,"losses":4,"wins":4},"google/gemma-4-31b-it":{"draws":2,"losses":1,"wins":1},"gpt-5":{"draws":1,"losses":2,"wins":1},"gpt-5.4":{"draws":1,"losses":1,"wins":0},"gpt-5.4-mini":{"draws":7,"losses":8,"wins":3},"gpt-5.4-nano":{"draws":5,"losses":6,"wins":7},"gpt-5.5":{"draws":0,"losses":3,"wins":1},"gpt-5.6-luna":{"draws":2,"losses":4,"wins":0},"gpt-5.6-sol":{"draws":4,"losses":2,"wins":2},"gpt-5.6-terra":{"draws":1,"losses":5,"wins":2},"inclusionai/ling-3.0-flash":{"draws":0,"losses":1,"wins":1},"minimax/minimax-m3":{"draws":0,"losses":1,"wins":3},"mistralai/mistral-medium-3-5":{"draws":0,"losses":1,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":4,"losses":7,"wins":3},"nex-agi/nex-n2-pro":{"draws":0,"losses":2,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":6,"wins":4},"o3":{"draws":2,"losses":4,"wins":0},"openai/gpt-oss-120b":{"draws":2,"losses":1,"wins":3},"qwen/qwen3.7-max":{"draws":0,"losses":3,"wins":1},"qwen/qwen3.7-plus":{"draws":0,"losses":1,"wins":5},"stepfun/step-3.7-flash":{"draws":0,"losses":4,"wins":0},"x-ai/grok-4.5":{"draws":4,"losses":11,"wins":3},"x-ai/grok-build-0.1":{"draws":0,"losses":3,"wins":3},"xiaomi/mimo-v2.5":{"draws":0,"losses":0,"wins":6},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":2,"wins":2},"z-ai/glm-5.2":{"draws":3,"losses":3,"wins":4}},"gpt-5":{"claude-fable-5":{"draws":1,"losses":5,"wins":0},"claude-opus-4-5":{"draws":3,"losses":2,"wins":7},"claude-opus-4-8":{"draws":5,"losses":7,"wins":4},"claude-opus-5":{"draws":3,"losses":4,"wins":1},"claude-sonnet-5":{"draws":6,"losses":6,"wins":8},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":8},"deepseek/deepseek-v4-flash":{"draws":0,"losses":1,"wins":3},"deepseek/deepseek-v4-pro":{"draws":0,"losses":3,"wins":1},"google/gemini-3.1-flash-lite":{"draws":4,"losses":0,"wins":4},"google/gemini-3.5-flash":{"draws":2,"losses":2,"wins":2},"google/gemini-3.5-flash-lite":{"draws":2,"losses":0,"wins":0},"google/gemini-3.6-flash":{"draws":1,"losses":1,"wins":0},"google/gemma-4-31b-it":{"draws":1,"losses":1,"wins":2},"gpt-4.1":{"draws":2,"losses":1,"wins":1},"gpt-5":{"draws":0,"losses":2,"wins":0},"gpt-5.4":{"draws":2,"losses":2,"wins":2},"gpt-5.4-mini":{"draws":13,"losses":3,"wins":4},"gpt-5.4-nano":{"draws":15,"losses":15,"wins":8},"gpt-5.5":{"draws":0,"losses":6,"wins":4},"gpt-5.6-luna":{"draws":5,"losses":2,"wins":1},"gpt-5.6-sol":{"draws":0,"losses":2,"wins":2},"gpt-5.6-terra":{"draws":5,"losses":5,"wins":2},"meituan/longcat-2.0":{"draws":3,"losses":1,"wins":0},"minimax/minimax-m3":{"draws":4,"losses":5,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":4},"moonshotai/kimi-k3":{"draws":5,"losses":4,"wins":11},"nex-agi/nex-n2-pro":{"draws":0,"losses":2,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":4,"wins":3},"o3":{"draws":2,"losses":3,"wins":5},"openai/gpt-oss-120b":{"draws":5,"losses":1,"wins":0},"poolside/laguna-s-2.1":{"draws":4,"losses":1,"wins":1},"qwen/qwen3.7-max":{"draws":4,"losses":3,"wins":3},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":0},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":0,"losses":2,"wins":2},"thinkingmachines/inkling":{"draws":2,"losses":0,"wins":2},"x-ai/grok-4.5":{"draws":4,"losses":14,"wins":4},"x-ai/grok-build-0.1":{"draws":4,"losses":3,"wins":5},"xiaomi/mimo-v2.5":{"draws":10,"losses":11,"wins":3},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":0,"wins":3},"z-ai/glm-5.2":{"draws":3,"losses":9,"wins":10}},"gpt-5.4":{"claude-fable-5":{"draws":2,"losses":5,"wins":3},"claude-opus-4-5":{"draws":2,"losses":5,"wins":9},"claude-opus-4-8":{"draws":3,"losses":7,"wins":6},"claude-opus-5":{"draws":2,"losses":6,"wins":2},"claude-sonnet-5":{"draws":8,"losses":4,"wins":8},"cohere/north-mini-code":{"draws":4,"losses":4,"wins":4},"deepseek/deepseek-v4-flash":{"draws":7,"losses":4,"wins":5},"deepseek/deepseek-v4-pro":{"draws":1,"losses":1,"wins":2},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":4},"google/gemini-3.5-flash":{"draws":4,"losses":2,"wins":4},"google/gemini-3.5-flash-lite":{"draws":2,"losses":0,"wins":0},"google/gemini-3.6-flash":{"draws":2,"losses":0,"wins":2},"google/gemma-4-31b-it":{"draws":1,"losses":0,"wins":1},"gpt-4.1":{"draws":3,"losses":1,"wins":0},"gpt-5":{"draws":4,"losses":2,"wins":0},"gpt-5.4":{"draws":5,"losses":6,"wins":1},"gpt-5.4-mini":{"draws":11,"losses":9,"wins":18},"gpt-5.4-nano":{"draws":13,"losses":6,"wins":21},"gpt-5.5":{"draws":6,"losses":6,"wins":4},"gpt-5.6-luna":{"draws":7,"losses":1,"wins":2},"gpt-5.6-sol":{"draws":0,"losses":5,"wins":7},"gpt-5.6-terra":{"draws":9,"losses":6,"wins":5},"inclusionai/ling-3.0-flash":{"draws":3,"losses":1,"wins":2},"minimax/minimax-m3":{"draws":3,"losses":0,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":4,"wins":2},"moonshotai/kimi-k3":{"draws":8,"losses":7,"wins":7},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":2,"wins":3},"o3":{"draws":1,"losses":3,"wins":2},"openai/gpt-oss-120b":{"draws":4,"losses":0,"wins":2},"poolside/laguna-s-2.1":{"draws":0,"losses":0,"wins":2},"qwen/qwen3.7-max":{"draws":2,"losses":2,"wins":2},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":6},"stepfun/step-3.7-flash":{"draws":1,"losses":3,"wins":0},"tencent/hy3-preview":{"draws":6,"losses":1,"wins":1},"thinkingmachines/inkling":{"draws":4,"losses":0,"wins":0},"x-ai/grok-4.5":{"draws":14,"losses":16,"wins":6},"xiaomi/mimo-v2.5":{"draws":7,"losses":2,"wins":5},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":3,"wins":7},"z-ai/glm-5.2":{"draws":17,"losses":5,"wins":6}},"gpt-5.4-mini":{"claude-fable-5":{"draws":5,"losses":7,"wins":2},"claude-opus-4-5":{"draws":14,"losses":13,"wins":5},"claude-opus-4-8":{"draws":6,"losses":10,"wins":8},"claude-opus-5":{"draws":2,"losses":6,"wins":4},"claude-sonnet-5":{"draws":7,"losses":14,"wins":17},"cohere/north-mini-code":{"draws":5,"losses":2,"wins":11},"deepseek/deepseek-v4-flash":{"draws":16,"losses":10,"wins":10},"deepseek/deepseek-v4-pro":{"draws":4,"losses":7,"wins":3},"google/gemini-3.1-flash-lite":{"draws":9,"losses":4,"wins":11},"google/gemini-3.5-flash":{"draws":9,"losses":16,"wins":7},"google/gemini-3.5-flash-lite":{"draws":2,"losses":3,"wins":3},"google/gemini-3.6-flash":{"draws":3,"losses":7,"wins":2},"google/gemma-4-31b-it":{"draws":8,"losses":3,"wins":7},"gpt-4.1":{"draws":7,"losses":3,"wins":4},"gpt-5":{"draws":9,"losses":3,"wins":6},"gpt-5.4":{"draws":14,"losses":22,"wins":10},"gpt-5.4-mini":{"draws":44,"losses":24,"wins":24},"gpt-5.4-nano":{"draws":33,"losses":26,"wins":56},"gpt-5.5":{"draws":11,"losses":8,"wins":3},"gpt-5.6-luna":{"draws":16,"losses":12,"wins":8},"gpt-5.6-sol":{"draws":9,"losses":12,"wins":5},"gpt-5.6-terra":{"draws":24,"losses":13,"wins":13},"inclusionai/ling-3.0-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":3,"losses":2,"wins":7},"minimax/minimax-m3":{"draws":18,"losses":10,"wins":18},"mistralai/mistral-medium-3-5":{"draws":2,"losses":4,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":16,"wins":5},"moonshotai/kimi-k3":{"draws":19,"losses":11,"wins":8},"nex-agi/nex-n2-pro":{"draws":7,"losses":2,"wins":13},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":20,"losses":5,"wins":7},"o3":{"draws":5,"losses":10,"wins":13},"openai/gpt-oss-120b":{"draws":11,"losses":6,"wins":3},"poolside/laguna-s-2.1":{"draws":2,"losses":3,"wins":5},"qwen/qwen3.7-max":{"draws":10,"losses":14,"wins":10},"qwen/qwen3.7-plus":{"draws":8,"losses":13,"wins":7},"stepfun/step-3.7-flash":{"draws":9,"losses":5,"wins":10},"tencent/hy3-preview":{"draws":5,"losses":1,"wins":2},"thinkingmachines/inkling":{"draws":8,"losses":3,"wins":3},"x-ai/grok-4.5":{"draws":19,"losses":35,"wins":14},"x-ai/grok-build-0.1":{"draws":3,"losses":9,"wins":8},"xiaomi/mimo-v2.5":{"draws":27,"losses":27,"wins":20},"xiaomi/mimo-v2.5-pro":{"draws":12,"losses":7,"wins":7},"z-ai/glm-5.2":{"draws":33,"losses":25,"wins":16}},"gpt-5.4-nano":{"claude-fable-5":{"draws":2,"losses":23,"wins":5},"claude-opus-4-5":{"draws":9,"losses":23,"wins":10},"claude-opus-4-8":{"draws":7,"losses":14,"wins":1},"claude-opus-5":{"draws":4,"losses":18,"wins":8},"claude-sonnet-5":{"draws":12,"losses":15,"wins":5},"cohere/north-mini-code":{"draws":11,"losses":10,"wins":9},"deepseek/deepseek-v4-flash":{"draws":11,"losses":17,"wins":6},"deepseek/deepseek-v4-pro":{"draws":1,"losses":1,"wins":6},"google/gemini-3.1-flash-lite":{"draws":3,"losses":15,"wins":26},"google/gemini-3.5-flash":{"draws":7,"losses":8,"wins":3},"google/gemini-3.5-flash-lite":{"draws":3,"losses":16,"wins":5},"google/gemini-3.6-flash":{"draws":6,"losses":8,"wins":4},"google/gemma-4-31b-it":{"draws":3,"losses":7,"wins":6},"gpt-4.1":{"draws":0,"losses":2,"wins":4},"gpt-5":{"draws":10,"losses":10,"wins":10},"gpt-5.4":{"draws":13,"losses":27,"wins":6},"gpt-5.4-mini":{"draws":30,"losses":58,"wins":25},"gpt-5.4-nano":{"draws":27,"losses":46,"wins":41},"gpt-5.5":{"draws":2,"losses":8,"wins":10},"gpt-5.6-luna":{"draws":14,"losses":15,"wins":15},"gpt-5.6-sol":{"draws":1,"losses":13,"wins":6},"gpt-5.6-terra":{"draws":13,"losses":16,"wins":7},"inclusionai/ling-3.0-flash":{"draws":5,"losses":5,"wins":0},"meituan/longcat-2.0":{"draws":5,"losses":7,"wins":10},"minimax/minimax-m3":{"draws":15,"losses":16,"wins":17},"mistralai/mistral-medium-3-5":{"draws":1,"losses":7,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":9,"wins":4},"moonshotai/kimi-k3":{"draws":13,"losses":18,"wins":9},"nex-agi/nex-n2-pro":{"draws":5,"losses":14,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":18,"wins":10},"o3":{"draws":4,"losses":8,"wins":4},"openai/gpt-oss-120b":{"draws":12,"losses":13,"wins":7},"poolside/laguna-s-2.1":{"draws":6,"losses":4,"wins":2},"qwen/qwen3.7-max":{"draws":16,"losses":15,"wins":7},"qwen/qwen3.7-plus":{"draws":13,"losses":27,"wins":4},"stepfun/step-3.7-flash":{"draws":6,"losses":5,"wins":9},"tencent/hy3-preview":{"draws":8,"losses":3,"wins":1},"thinkingmachines/inkling":{"draws":5,"losses":13,"wins":8},"x-ai/grok-4.5":{"draws":14,"losses":33,"wins":19},"x-ai/grok-build-0.1":{"draws":10,"losses":14,"wins":4},"xiaomi/mimo-v2.5":{"draws":31,"losses":33,"wins":20},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":14,"wins":11},"z-ai/glm-5.2":{"draws":23,"losses":23,"wins":25}},"gpt-5.5":{"claude-fable-5":{"draws":4,"losses":6,"wins":4},"claude-opus-4-5":{"draws":6,"losses":7,"wins":7},"claude-opus-4-8":{"draws":4,"losses":4,"wins":6},"claude-opus-5":{"draws":5,"losses":10,"wins":1},"claude-sonnet-5":{"draws":8,"losses":4,"wins":4},"cohere/north-mini-code":{"draws":4,"losses":1,"wins":1},"deepseek/deepseek-v4-flash":{"draws":6,"losses":0,"wins":6},"deepseek/deepseek-v4-pro":{"draws":0,"losses":1,"wins":1},"google/gemini-3.1-flash-lite":{"draws":7,"losses":2,"wins":3},"google/gemini-3.5-flash":{"draws":2,"losses":5,"wins":1},"google/gemini-3.6-flash":{"draws":0,"losses":1,"wins":3},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":2},"gpt-4.1":{"draws":1,"losses":0,"wins":3},"gpt-5":{"draws":0,"losses":4,"wins":4},"gpt-5.4":{"draws":7,"losses":5,"wins":2},"gpt-5.4-mini":{"draws":10,"losses":3,"wins":9},"gpt-5.4-nano":{"draws":4,"losses":16,"wins":6},"gpt-5.5":{"draws":4,"losses":4,"wins":4},"gpt-5.6-luna":{"draws":3,"losses":3,"wins":2},"gpt-5.6-sol":{"draws":8,"losses":5,"wins":7},"gpt-5.6-terra":{"draws":6,"losses":6,"wins":8},"inclusionai/ling-3.0-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":0,"losses":1,"wins":1},"minimax/minimax-m3":{"draws":3,"losses":2,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":1,"wins":1},"moonshotai/kimi-k3":{"draws":8,"losses":8,"wins":10},"nex-agi/nex-n2-pro":{"draws":0,"losses":1,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":0,"wins":4},"o3":{"draws":2,"losses":0,"wins":4},"openai/gpt-oss-120b":{"draws":0,"losses":2,"wins":4},"poolside/laguna-s-2.1":{"draws":0,"losses":3,"wins":1},"qwen/qwen3.7-max":{"draws":4,"losses":2,"wins":4},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":2},"stepfun/step-3.7-flash":{"draws":3,"losses":0,"wins":3},"tencent/hy3-preview":{"draws":3,"losses":0,"wins":3},"thinkingmachines/inkling":{"draws":1,"losses":3,"wins":4},"x-ai/grok-4.5":{"draws":7,"losses":12,"wins":13},"x-ai/grok-build-0.1":{"draws":3,"losses":5,"wins":2},"xiaomi/mimo-v2.5":{"draws":9,"losses":3,"wins":4},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":4,"wins":3},"z-ai/glm-5.2":{"draws":7,"losses":8,"wins":3}},"gpt-5.6-luna":{"claude-fable-5":{"draws":0,"losses":6,"wins":0},"claude-opus-4-5":{"draws":6,"losses":5,"wins":3},"claude-opus-4-8":{"draws":3,"losses":6,"wins":3},"claude-opus-5":{"draws":1,"losses":4,"wins":1},"claude-sonnet-5":{"draws":3,"losses":4,"wins":5},"cohere/north-mini-code":{"draws":3,"losses":3,"wins":2},"deepseek/deepseek-v4-flash":{"draws":7,"losses":1,"wins":4},"deepseek/deepseek-v4-pro":{"draws":4,"losses":2,"wins":0},"google/gemini-3.1-flash-lite":{"draws":2,"losses":2,"wins":0},"google/gemini-3.5-flash":{"draws":6,"losses":5,"wins":1},"google/gemini-3.5-flash-lite":{"draws":4,"losses":0,"wins":0},"google/gemini-3.6-flash":{"draws":0,"losses":1,"wins":1},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":4},"gpt-4.1":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":5,"losses":1,"wins":2},"gpt-5.4":{"draws":10,"losses":4,"wins":0},"gpt-5.4-mini":{"draws":20,"losses":7,"wins":9},"gpt-5.4-nano":{"draws":12,"losses":2,"wins":14},"gpt-5.5":{"draws":3,"losses":3,"wins":2},"gpt-5.6-luna":{"draws":6,"losses":3,"wins":7},"gpt-5.6-sol":{"draws":5,"losses":5,"wins":6},"gpt-5.6-terra":{"draws":6,"losses":5,"wins":1},"meituan/longcat-2.0":{"draws":0,"losses":0,"wins":2},"minimax/minimax-m3":{"draws":4,"losses":1,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":3,"wins":1},"moonshotai/kimi-k3":{"draws":8,"losses":7,"wins":5},"nex-agi/nex-n2-pro":{"draws":4,"losses":1,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":2,"wins":4},"o3":{"draws":2,"losses":0,"wins":2},"openai/gpt-oss-120b":{"draws":8,"losses":2,"wins":4},"poolside/laguna-s-2.1":{"draws":0,"losses":1,"wins":3},"qwen/qwen3.7-max":{"draws":11,"losses":0,"wins":7},"qwen/qwen3.7-plus":{"draws":2,"losses":3,"wins":3},"stepfun/step-3.7-flash":{"draws":2,"losses":1,"wins":1},"tencent/hy3-preview":{"draws":2,"losses":2,"wins":0},"thinkingmachines/inkling":{"draws":2,"losses":0,"wins":0},"x-ai/grok-4.5":{"draws":6,"losses":14,"wins":6},"x-ai/grok-build-0.1":{"draws":8,"losses":0,"wins":6},"xiaomi/mimo-v2.5":{"draws":9,"losses":4,"wins":5},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":3,"wins":4},"z-ai/glm-5.2":{"draws":19,"losses":12,"wins":3}},"gpt-5.6-sol":{"claude-fable-5":{"draws":3,"losses":16,"wins":5},"claude-opus-4-5":{"draws":2,"losses":2,"wins":12},"claude-opus-4-8":{"draws":1,"losses":3,"wins":6},"claude-opus-5":{"draws":5,"losses":13,"wins":4},"claude-sonnet-5":{"draws":3,"losses":1,"wins":10},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":4},"deepseek/deepseek-v4-flash":{"draws":1,"losses":0,"wins":7},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":0},"google/gemini-3.5-flash":{"draws":3,"losses":3,"wins":2},"google/gemini-3.5-flash-lite":{"draws":2,"losses":0,"wins":2},"google/gemini-3.6-flash":{"draws":2,"losses":0,"wins":2},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":4,"losses":2,"wins":2},"gpt-5.4":{"draws":0,"losses":9,"wins":3},"gpt-5.4-mini":{"draws":8,"losses":5,"wins":15},"gpt-5.4-nano":{"draws":2,"losses":6,"wins":16},"gpt-5.5":{"draws":4,"losses":9,"wins":5},"gpt-5.6-luna":{"draws":3,"losses":2,"wins":5},"gpt-5.6-sol":{"draws":2,"losses":4,"wins":6},"gpt-5.6-terra":{"draws":2,"losses":1,"wins":5},"inclusionai/ling-3.0-flash":{"draws":1,"losses":0,"wins":1},"minimax/minimax-m3":{"draws":4,"losses":0,"wins":2},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":1,"wins":5},"moonshotai/kimi-k3":{"draws":4,"losses":9,"wins":17},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":0,"wins":8},"o3":{"draws":2,"losses":1,"wins":3},"openai/gpt-oss-120b":{"draws":5,"losses":0,"wins":5},"qwen/qwen3.7-max":{"draws":3,"losses":2,"wins":7},"qwen/qwen3.7-plus":{"draws":4,"losses":2,"wins":0},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":1,"losses":2,"wins":3},"thinkingmachines/inkling":{"draws":1,"losses":2,"wins":5},"x-ai/grok-4.5":{"draws":9,"losses":22,"wins":19},"x-ai/grok-build-0.1":{"draws":2,"losses":2,"wins":2},"xiaomi/mimo-v2.5":{"draws":4,"losses":0,"wins":0},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":6},"z-ai/glm-5.2":{"draws":6,"losses":3,"wins":15}},"gpt-5.6-terra":{"claude-fable-5":{"draws":2,"losses":5,"wins":1},"claude-opus-4-5":{"draws":10,"losses":6,"wins":8},"claude-opus-4-8":{"draws":3,"losses":0,"wins":3},"claude-opus-5":{"draws":3,"losses":8,"wins":1},"claude-sonnet-5":{"draws":1,"losses":5,"wins":4},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":6},"deepseek/deepseek-v4-flash":{"draws":1,"losses":2,"wins":7},"deepseek/deepseek-v4-pro":{"draws":2,"losses":1,"wins":1},"google/gemini-3.1-flash-lite":{"draws":1,"losses":1,"wins":4},"google/gemini-3.5-flash":{"draws":3,"losses":9,"wins":0},"google/gemini-3.5-flash-lite":{"draws":6,"losses":0,"wins":0},"google/gemma-4-31b-it":{"draws":1,"losses":2,"wins":5},"gpt-4.1":{"draws":1,"losses":1,"wins":0},"gpt-5":{"draws":5,"losses":1,"wins":4},"gpt-5.4":{"draws":9,"losses":6,"wins":3},"gpt-5.4-mini":{"draws":21,"losses":6,"wins":9},"gpt-5.4-nano":{"draws":16,"losses":14,"wins":16},"gpt-5.5":{"draws":6,"losses":5,"wins":3},"gpt-5.6-luna":{"draws":6,"losses":3,"wins":3},"gpt-5.6-sol":{"draws":3,"losses":4,"wins":3},"gpt-5.6-terra":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":0,"losses":2,"wins":2},"minimax/minimax-m3":{"draws":4,"losses":0,"wins":2},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":1},"moonshotai/kimi-k3":{"draws":12,"losses":5,"wins":3},"nex-agi/nex-n2-pro":{"draws":3,"losses":2,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":1,"wins":5},"o3":{"draws":3,"losses":2,"wins":1},"openai/gpt-oss-120b":{"draws":4,"losses":0,"wins":2},"poolside/laguna-s-2.1":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.7-max":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.7-plus":{"draws":5,"losses":7,"wins":2},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":2,"losses":0,"wins":0},"thinkingmachines/inkling":{"draws":4,"losses":0,"wins":0},"x-ai/grok-4.5":{"draws":9,"losses":11,"wins":4},"x-ai/grok-build-0.1":{"draws":4,"losses":0,"wins":6},"xiaomi/mimo-v2.5":{"draws":8,"losses":2,"wins":12},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":0,"wins":0},"z-ai/glm-5.2":{"draws":9,"losses":7,"wins":2}},"inclusionai/ling-3.0-flash":{"claude-opus-5":{"draws":2,"losses":0,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":0},"deepseek/deepseek-v4-flash":{"draws":0,"losses":0,"wins":2},"google/gemini-3.5-flash-lite":{"draws":16,"losses":27,"wins":11},"google/gemini-3.6-flash":{"draws":20,"losses":20,"wins":10},"inclusionai/ling-3.0-flash":{"draws":4,"losses":9,"wins":11},"meituan/longcat-2.0":{"draws":6,"losses":22,"wins":10},"moonshotai/kimi-k3":{"draws":11,"losses":9,"wins":2},"poolside/laguna-s-2.1":{"draws":7,"losses":8,"wins":5},"thinkingmachines/inkling":{"draws":8,"losses":18,"wins":14},"x-ai/grok-4.5":{"draws":8,"losses":17,"wins":3}},"meituan/longcat-2.0":{"claude-fable-5":{"draws":0,"losses":1,"wins":1},"claude-opus-4-5":{"draws":2,"losses":0,"wins":0},"claude-opus-5":{"draws":0,"losses":8,"wins":2},"google/gemini-3.5-flash-lite":{"draws":20,"losses":36,"wins":27},"google/gemini-3.6-flash":{"draws":25,"losses":42,"wins":23},"inclusionai/ling-3.0-flash":{"draws":11,"losses":6,"wins":21},"meituan/longcat-2.0":{"draws":13,"losses":16,"wins":23},"moonshotai/kimi-k3":{"draws":11,"losses":21,"wins":5},"poolside/laguna-s-2.1":{"draws":12,"losses":17,"wins":21},"thinkingmachines/inkling":{"draws":17,"losses":15,"wins":32},"x-ai/grok-4.5":{"draws":15,"losses":36,"wins":7}},"minimax/minimax-m3":{"claude-fable-5":{"draws":1,"losses":3,"wins":0},"claude-opus-4-5":{"draws":3,"losses":4,"wins":1},"claude-opus-4-8":{"draws":6,"losses":2,"wins":0},"claude-opus-5":{"draws":0,"losses":2,"wins":0},"claude-sonnet-5":{"draws":8,"losses":3,"wins":1},"cohere/north-mini-code":{"draws":2,"losses":4,"wins":4},"deepseek/deepseek-v4-flash":{"draws":6,"losses":3,"wins":5},"deepseek/deepseek-v4-pro":{"draws":0,"losses":1,"wins":1},"google/gemini-3.1-flash-lite":{"draws":1,"losses":10,"wins":3},"google/gemini-3.5-flash":{"draws":2,"losses":2,"wins":0},"google/gemini-3.6-flash":{"draws":5,"losses":1,"wins":0},"google/gemma-4-31b-it":{"draws":0,"losses":5,"wins":1},"gpt-4.1":{"draws":0,"losses":3,"wins":1},"gpt-5":{"draws":5,"losses":7,"wins":2},"gpt-5.4":{"draws":3,"losses":3,"wins":0},"gpt-5.4-mini":{"draws":14,"losses":21,"wins":9},"gpt-5.4-nano":{"draws":22,"losses":23,"wins":19},"gpt-5.5":{"draws":2,"losses":5,"wins":1},"gpt-5.6-luna":{"draws":8,"losses":3,"wins":1},"gpt-5.6-sol":{"draws":6,"losses":4,"wins":0},"gpt-5.6-terra":{"draws":2,"losses":0,"wins":2},"inclusionai/ling-3.0-flash":{"draws":2,"losses":1,"wins":1},"meituan/longcat-2.0":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":1,"wins":0},"moonshotai/kimi-k3":{"draws":5,"losses":5,"wins":2},"nex-agi/nex-n2-pro":{"draws":2,"losses":2,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":5,"wins":3},"o3":{"draws":0,"losses":3,"wins":1},"openai/gpt-oss-120b":{"draws":1,"losses":3,"wins":4},"qwen/qwen3.7-max":{"draws":2,"losses":5,"wins":5},"qwen/qwen3.7-plus":{"draws":3,"losses":4,"wins":3},"stepfun/step-3.7-flash":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":2,"losses":2,"wins":0},"x-ai/grok-4.5":{"draws":10,"losses":8,"wins":0},"x-ai/grok-build-0.1":{"draws":5,"losses":5,"wins":0},"xiaomi/mimo-v2.5":{"draws":8,"losses":11,"wins":7},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":5,"wins":1},"z-ai/glm-5.2":{"draws":4,"losses":4,"wins":0}},"moonshotai/kimi-k2.7-code":{"claude-fable-5":{"draws":0,"losses":8,"wins":2},"claude-opus-4-5":{"draws":4,"losses":8,"wins":6},"claude-opus-4-8":{"draws":2,"losses":3,"wins":3},"claude-opus-5":{"draws":5,"losses":8,"wins":1},"claude-sonnet-5":{"draws":3,"losses":4,"wins":1},"cohere/north-mini-code":{"draws":0,"losses":2,"wins":2},"deepseek/deepseek-v4-flash":{"draws":3,"losses":3,"wins":4},"deepseek/deepseek-v4-pro":{"draws":2,"losses":3,"wins":1},"google/gemini-3.1-flash-lite":{"draws":4,"losses":0,"wins":4},"google/gemini-3.5-flash":{"draws":0,"losses":2,"wins":4},"google/gemini-3.5-flash-lite":{"draws":0,"losses":2,"wins":0},"google/gemini-3.6-flash":{"draws":0,"losses":1,"wins":1},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":8},"gpt-4.1":{"draws":2,"losses":1,"wins":1},"gpt-5":{"draws":2,"losses":6,"wins":2},"gpt-5.4":{"draws":5,"losses":3,"wins":4},"gpt-5.4-mini":{"draws":9,"losses":5,"wins":16},"gpt-5.4-nano":{"draws":8,"losses":7,"wins":9},"gpt-5.5":{"draws":6,"losses":1,"wins":3},"gpt-5.6-luna":{"draws":3,"losses":2,"wins":3},"gpt-5.6-sol":{"draws":2,"losses":7,"wins":1},"gpt-5.6-terra":{"draws":1,"losses":4,"wins":3},"meituan/longcat-2.0":{"draws":0,"losses":1,"wins":3},"minimax/minimax-m3":{"draws":3,"losses":0,"wins":3},"moonshotai/kimi-k3":{"draws":7,"losses":8,"wins":5},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":0,"wins":0},"o3":{"draws":0,"losses":4,"wins":4},"openai/gpt-oss-120b":{"draws":2,"losses":0,"wins":0},"poolside/laguna-s-2.1":{"draws":0,"losses":1,"wins":1},"qwen/qwen3.7-plus":{"draws":5,"losses":0,"wins":5},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":0},"tencent/hy3-preview":{"draws":0,"losses":0,"wins":2},"x-ai/grok-4.5":{"draws":2,"losses":31,"wins":1},"x-ai/grok-build-0.1":{"draws":0,"losses":1,"wins":5},"xiaomi/mimo-v2.5":{"draws":8,"losses":6,"wins":10},"z-ai/glm-5.2":{"draws":3,"losses":7,"wins":8}},"moonshotai/kimi-k3":{"claude-fable-5":{"draws":5,"losses":7,"wins":2},"claude-opus-4-5":{"draws":9,"losses":4,"wins":7},"claude-opus-4-8":{"draws":5,"losses":4,"wins":9},"claude-opus-5":{"draws":5,"losses":15,"wins":4},"claude-sonnet-5":{"draws":6,"losses":0,"wins":6},"cohere/north-mini-code":{"draws":5,"losses":0,"wins":7},"google/gemini-3.1-flash-lite":{"draws":7,"losses":1,"wins":4},"google/gemini-3.5-flash":{"draws":8,"losses":6,"wins":2},"google/gemini-3.5-flash-lite":{"draws":30,"losses":12,"wins":18},"google/gemini-3.6-flash":{"draws":28,"losses":12,"wins":14},"google/gemma-4-31b-it":{"draws":4,"losses":2,"wins":4},"gpt-5":{"draws":5,"losses":7,"wins":4},"gpt-5.4":{"draws":4,"losses":3,"wins":7},"gpt-5.4-mini":{"draws":17,"losses":5,"wins":10},"gpt-5.4-nano":{"draws":12,"losses":9,"wins":13},"gpt-5.5":{"draws":8,"losses":3,"wins":5},"gpt-5.6-luna":{"draws":6,"losses":4,"wins":6},"gpt-5.6-sol":{"draws":1,"losses":12,"wins":7},"gpt-5.6-terra":{"draws":8,"losses":3,"wins":5},"inclusionai/ling-3.0-flash":{"draws":12,"losses":1,"wins":7},"meituan/longcat-2.0":{"draws":16,"losses":5,"wins":10},"minimax/minimax-m3":{"draws":4,"losses":1,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":5,"wins":8},"moonshotai/kimi-k3":{"draws":20,"losses":9,"wins":3},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":4,"wins":5},"o3":{"draws":3,"losses":3,"wins":2},"openai/gpt-oss-120b":{"draws":5,"losses":1,"wins":4},"poolside/laguna-s-2.1":{"draws":22,"losses":7,"wins":5},"qwen/qwen3.7-max":{"draws":9,"losses":7,"wins":4},"qwen/qwen3.7-plus":{"draws":5,"losses":0,"wins":3},"stepfun/step-3.7-flash":{"draws":6,"losses":0,"wins":0},"thinkingmachines/inkling":{"draws":18,"losses":6,"wins":8},"x-ai/grok-4.5":{"draws":19,"losses":35,"wins":24},"x-ai/grok-build-0.1":{"draws":11,"losses":0,"wins":5},"xiaomi/mimo-v2.5":{"draws":14,"losses":4,"wins":12},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":4,"wins":4}},"nex-agi/nex-n2-pro":{"claude-fable-5":{"draws":0,"losses":2,"wins":0},"claude-opus-4-5":{"draws":2,"losses":5,"wins":1},"claude-opus-4-8":{"draws":3,"losses":3,"wins":0},"claude-sonnet-5":{"draws":2,"losses":11,"wins":1},"cohere/north-mini-code":{"draws":6,"losses":6,"wins":2},"deepseek/deepseek-v4-flash":{"draws":0,"losses":3,"wins":5},"deepseek/deepseek-v4-pro":{"draws":0,"losses":0,"wins":2},"google/gemini-3.1-flash-lite":{"draws":0,"losses":6,"wins":8},"google/gemini-3.5-flash":{"draws":2,"losses":2,"wins":0},"google/gemini-3.5-flash-lite":{"draws":0,"losses":2,"wins":0},"google/gemini-3.6-flash":{"draws":0,"losses":2,"wins":0},"google/gemma-4-31b-it":{"draws":0,"losses":2,"wins":2},"gpt-4.1":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":0,"losses":4,"wins":2},"gpt-5.4":{"draws":0,"losses":4,"wins":0},"gpt-5.4-mini":{"draws":9,"losses":15,"wins":4},"gpt-5.4-nano":{"draws":4,"losses":10,"wins":16},"gpt-5.5":{"draws":0,"losses":5,"wins":1},"gpt-5.6-luna":{"draws":4,"losses":3,"wins":5},"gpt-5.6-sol":{"draws":0,"losses":2,"wins":0},"gpt-5.6-terra":{"draws":1,"losses":3,"wins":2},"inclusionai/ling-3.0-flash":{"draws":1,"losses":1,"wins":2},"meituan/longcat-2.0":{"draws":0,"losses":0,"wins":2},"minimax/minimax-m3":{"draws":0,"losses":6,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":0,"losses":10,"wins":0},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":6,"wins":2},"openai/gpt-oss-120b":{"draws":2,"losses":3,"wins":1},"poolside/laguna-s-2.1":{"draws":0,"losses":2,"wins":0},"qwen/qwen3.7-max":{"draws":0,"losses":4,"wins":0},"qwen/qwen3.7-plus":{"draws":2,"losses":3,"wins":1},"stepfun/step-3.7-flash":{"draws":1,"losses":1,"wins":2},"thinkingmachines/inkling":{"draws":0,"losses":5,"wins":1},"x-ai/grok-4.5":{"draws":2,"losses":5,"wins":1},"x-ai/grok-build-0.1":{"draws":2,"losses":4,"wins":2},"xiaomi/mimo-v2.5":{"draws":0,"losses":14,"wins":8},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":4,"wins":2},"z-ai/glm-5.2":{"draws":4,"losses":6,"wins":2}},"nvidia/nemotron-3-ultra-550b-a55b":{"claude-fable-5":{"draws":0,"losses":2,"wins":0},"claude-opus-4-5":{"draws":2,"losses":2,"wins":4},"claude-opus-4-8":{"draws":4,"losses":4,"wins":0},"claude-sonnet-5":{"draws":4,"losses":0,"wins":4},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":6},"deepseek/deepseek-v4-flash":{"draws":4,"losses":0,"wins":0},"deepseek/deepseek-v4-pro":{"draws":0,"losses":0,"wins":2},"google/gemini-3.1-flash-lite":{"draws":1,"losses":2,"wins":3},"google/gemini-3.5-flash":{"draws":4,"losses":4,"wins":0},"google/gemini-3.5-flash-lite":{"draws":3,"losses":3,"wins":2},"google/gemini-3.6-flash":{"draws":2,"losses":1,"wins":1},"google/gemma-4-31b-it":{"draws":0,"losses":4,"wins":2},"gpt-4.1":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":1,"losses":1,"wins":2},"gpt-5.4":{"draws":5,"losses":3,"wins":0},"gpt-5.4-mini":{"draws":10,"losses":11,"wins":7},"gpt-5.4-nano":{"draws":17,"losses":6,"wins":13},"gpt-5.5":{"draws":1,"losses":2,"wins":1},"gpt-5.6-luna":{"draws":4,"losses":5,"wins":1},"gpt-5.6-sol":{"draws":0,"losses":4,"wins":0},"gpt-5.6-terra":{"draws":4,"losses":3,"wins":1},"meituan/longcat-2.0":{"draws":4,"losses":1,"wins":1},"minimax/minimax-m3":{"draws":2,"losses":2,"wins":2},"mistralai/mistral-medium-3-5":{"draws":0,"losses":1,"wins":1},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":5,"losses":13,"wins":4},"nex-agi/nex-n2-pro":{"draws":0,"losses":2,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":2,"wins":2},"o3":{"draws":3,"losses":1,"wins":0},"openai/gpt-oss-120b":{"draws":2,"losses":0,"wins":0},"poolside/laguna-s-2.1":{"draws":2,"losses":2,"wins":0},"qwen/qwen3.7-max":{"draws":2,"losses":2,"wins":2},"qwen/qwen3.7-plus":{"draws":2,"losses":2,"wins":2},"stepfun/step-3.7-flash":{"draws":1,"losses":1,"wins":0},"tencent/hy3-preview":{"draws":2,"losses":0,"wins":0},"thinkingmachines/inkling":{"draws":0,"losses":2,"wins":0},"x-ai/grok-4.5":{"draws":0,"losses":4,"wins":4},"x-ai/grok-build-0.1":{"draws":4,"losses":2,"wins":4},"xiaomi/mimo-v2.5":{"draws":8,"losses":3,"wins":1},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":6,"wins":0},"z-ai/glm-5.2":{"draws":7,"losses":5,"wins":2}},"o3":{"claude-fable-5":{"draws":0,"losses":8,"wins":0},"claude-opus-4-5":{"draws":3,"losses":8,"wins":7},"claude-opus-4-8":{"draws":4,"losses":3,"wins":1},"claude-opus-5":{"draws":0,"losses":2,"wins":0},"claude-sonnet-5":{"draws":3,"losses":7,"wins":4},"cohere/north-mini-code":{"draws":1,"losses":2,"wins":1},"deepseek/deepseek-v4-flash":{"draws":4,"losses":2,"wins":6},"deepseek/deepseek-v4-pro":{"draws":0,"losses":2,"wins":0},"google/gemini-3.1-flash-lite":{"draws":6,"losses":0,"wins":4},"google/gemini-3.5-flash":{"draws":0,"losses":0,"wins":4},"google/gemini-3.5-flash-lite":{"draws":0,"losses":1,"wins":3},"google/gemini-3.6-flash":{"draws":1,"losses":1,"wins":0},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":2,"losses":7,"wins":3},"gpt-5.4":{"draws":1,"losses":2,"wins":3},"gpt-5.4-mini":{"draws":7,"losses":11,"wins":16},"gpt-5.4-nano":{"draws":6,"losses":7,"wins":11},"gpt-5.5":{"draws":3,"losses":9,"wins":0},"gpt-5.6-luna":{"draws":2,"losses":3,"wins":1},"gpt-5.6-sol":{"draws":3,"losses":6,"wins":1},"gpt-5.6-terra":{"draws":3,"losses":3,"wins":2},"meituan/longcat-2.0":{"draws":0,"losses":1,"wins":1},"minimax/minimax-m3":{"draws":1,"losses":1,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":3,"wins":3},"moonshotai/kimi-k3":{"draws":5,"losses":2,"wins":3},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":2,"wins":1},"o3":{"draws":0,"losses":1,"wins":1},"openai/gpt-oss-120b":{"draws":3,"losses":1,"wins":0},"poolside/laguna-s-2.1":{"draws":0,"losses":0,"wins":2},"qwen/qwen3.7-max":{"draws":5,"losses":4,"wins":1},"qwen/qwen3.7-plus":{"draws":0,"losses":4,"wins":2},"stepfun/step-3.7-flash":{"draws":1,"losses":1,"wins":2},"tencent/hy3-preview":{"draws":5,"losses":1,"wins":2},"thinkingmachines/inkling":{"draws":0,"losses":1,"wins":1},"x-ai/grok-4.5":{"draws":2,"losses":14,"wins":8},"x-ai/grok-build-0.1":{"draws":3,"losses":0,"wins":3},"xiaomi/mimo-v2.5":{"draws":11,"losses":1,"wins":22},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":2,"wins":2},"z-ai/glm-5.2":{"draws":7,"losses":9,"wins":6}},"openai/gpt-oss-120b":{"claude-opus-4-5":{"draws":6,"losses":6,"wins":2},"claude-opus-4-8":{"draws":3,"losses":2,"wins":3},"claude-sonnet-5":{"draws":0,"losses":6,"wins":4},"cohere/north-mini-code":{"draws":6,"losses":1,"wins":1},"deepseek/deepseek-v4-flash":{"draws":8,"losses":0,"wins":4},"google/gemini-3.1-flash-lite":{"draws":2,"losses":4,"wins":4},"google/gemini-3.5-flash-lite":{"draws":4,"losses":0,"wins":0},"google/gemma-4-31b-it":{"draws":2,"losses":3,"wins":1},"gpt-4.1":{"draws":1,"losses":0,"wins":1},"gpt-5":{"draws":5,"losses":0,"wins":1},"gpt-5.4":{"draws":6,"losses":2,"wins":0},"gpt-5.4-mini":{"draws":13,"losses":11,"wins":8},"gpt-5.4-nano":{"draws":19,"losses":9,"wins":14},"gpt-5.5":{"draws":1,"losses":7,"wins":0},"gpt-5.6-luna":{"draws":10,"losses":3,"wins":3},"gpt-5.6-sol":{"draws":3,"losses":5,"wins":0},"gpt-5.6-terra":{"draws":4,"losses":2,"wins":0},"inclusionai/ling-3.0-flash":{"draws":3,"losses":1,"wins":2},"minimax/minimax-m3":{"draws":0,"losses":3,"wins":3},"mistralai/mistral-medium-3-5":{"draws":3,"losses":1,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":7,"losses":4,"wins":1},"nex-agi/nex-n2-pro":{"draws":4,"losses":1,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":2,"wins":3},"o3":{"draws":3,"losses":0,"wins":1},"openai/gpt-oss-120b":{"draws":5,"losses":1,"wins":0},"poolside/laguna-s-2.1":{"draws":1,"losses":1,"wins":0},"qwen/qwen3.7-max":{"draws":8,"losses":0,"wins":0},"qwen/qwen3.7-plus":{"draws":4,"losses":2,"wins":2},"stepfun/step-3.7-flash":{"draws":5,"losses":5,"wins":0},"tencent/hy3-preview":{"draws":1,"losses":1,"wins":0},"thinkingmachines/inkling":{"draws":3,"losses":0,"wins":5},"x-ai/grok-4.5":{"draws":4,"losses":8,"wins":0},"x-ai/grok-build-0.1":{"draws":1,"losses":9,"wins":2},"xiaomi/mimo-v2.5":{"draws":6,"losses":8,"wins":6},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":2,"wins":0},"z-ai/glm-5.2":{"draws":15,"losses":2,"wins":7}},"poolside/laguna-s-2.1":{"claude-opus-5":{"draws":0,"losses":14,"wins":2},"google/gemini-3.5-flash-lite":{"draws":51,"losses":25,"wins":30},"google/gemini-3.6-flash":{"draws":38,"losses":33,"wins":7},"inclusionai/ling-3.0-flash":{"draws":20,"losses":5,"wins":7},"meituan/longcat-2.0":{"draws":24,"losses":13,"wins":19},"moonshotai/kimi-k3":{"draws":24,"losses":13,"wins":3},"poolside/laguna-s-2.1":{"draws":23,"losses":10,"wins":5},"thinkingmachines/inkling":{"draws":23,"losses":11,"wins":14},"x-ai/grok-4.5":{"draws":20,"losses":16,"wins":6}},"qwen/qwen3.7-max":{"claude-fable-5":{"draws":1,"losses":7,"wins":2},"claude-opus-4-5":{"draws":8,"losses":5,"wins":3},"claude-opus-4-8":{"draws":0,"losses":6,"wins":4},"claude-opus-5":{"draws":0,"losses":4,"wins":4},"claude-sonnet-5":{"draws":3,"losses":6,"wins":3},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":2},"deepseek/deepseek-v4-flash":{"draws":6,"losses":0,"wins":2},"deepseek/deepseek-v4-pro":{"draws":2,"losses":4,"wins":0},"google/gemini-3.1-flash-lite":{"draws":3,"losses":1,"wins":0},"google/gemini-3.5-flash":{"draws":1,"losses":1,"wins":4},"google/gemini-3.5-flash-lite":{"draws":2,"losses":0,"wins":0},"google/gemini-3.6-flash":{"draws":1,"losses":2,"wins":1},"google/gemma-4-31b-it":{"draws":0,"losses":1,"wins":3},"gpt-4.1":{"draws":6,"losses":0,"wins":0},"gpt-5":{"draws":6,"losses":3,"wins":3},"gpt-5.4":{"draws":2,"losses":6,"wins":2},"gpt-5.4-mini":{"draws":15,"losses":11,"wins":12},"gpt-5.4-nano":{"draws":17,"losses":9,"wins":16},"gpt-5.5":{"draws":4,"losses":6,"wins":2},"gpt-5.6-luna":{"draws":6,"losses":4,"wins":0},"gpt-5.6-sol":{"draws":3,"losses":7,"wins":4},"gpt-5.6-terra":{"draws":2,"losses":2,"wins":0},"meituan/longcat-2.0":{"draws":1,"losses":0,"wins":1},"minimax/minimax-m3":{"draws":2,"losses":4,"wins":4},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":9,"losses":4,"wins":7},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":3,"wins":5},"o3":{"draws":5,"losses":1,"wins":4},"openai/gpt-oss-120b":{"draws":6,"losses":0,"wins":0},"qwen/qwen3.7-max":{"draws":2,"losses":0,"wins":2},"qwen/qwen3.7-plus":{"draws":3,"losses":4,"wins":5},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":1,"losses":1,"wins":2},"thinkingmachines/inkling":{"draws":6,"losses":1,"wins":1},"x-ai/grok-4.5":{"draws":9,"losses":13,"wins":14},"x-ai/grok-build-0.1":{"draws":0,"losses":6,"wins":2},"xiaomi/mimo-v2.5":{"draws":6,"losses":5,"wins":5},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":2,"wins":8},"z-ai/glm-5.2":{"draws":6,"losses":7,"wins":5}},"qwen/qwen3.7-plus":{"claude-fable-5":{"draws":1,"losses":5,"wins":0},"claude-opus-4-5":{"draws":6,"losses":8,"wins":4},"claude-opus-4-8":{"draws":4,"losses":11,"wins":3},"claude-sonnet-5":{"draws":6,"losses":3,"wins":3},"cohere/north-mini-code":{"draws":4,"losses":3,"wins":5},"deepseek/deepseek-v4-flash":{"draws":8,"losses":1,"wins":7},"deepseek/deepseek-v4-pro":{"draws":0,"losses":2,"wins":0},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":6},"google/gemini-3.5-flash":{"draws":2,"losses":7,"wins":1},"google/gemini-3.5-flash-lite":{"draws":4,"losses":0,"wins":0},"google/gemini-3.6-flash":{"draws":2,"losses":0,"wins":0},"google/gemma-4-31b-it":{"draws":0,"losses":3,"wins":1},"gpt-5":{"draws":2,"losses":1,"wins":1},"gpt-5.4":{"draws":4,"losses":6,"wins":0},"gpt-5.4-mini":{"draws":10,"losses":6,"wins":16},"gpt-5.4-nano":{"draws":13,"losses":2,"wins":23},"gpt-5.5":{"draws":2,"losses":2,"wins":0},"gpt-5.6-luna":{"draws":2,"losses":3,"wins":3},"gpt-5.6-sol":{"draws":4,"losses":0,"wins":2},"gpt-5.6-terra":{"draws":5,"losses":2,"wins":9},"minimax/minimax-m3":{"draws":3,"losses":2,"wins":3},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":5,"wins":0},"moonshotai/kimi-k3":{"draws":5,"losses":3,"wins":2},"nex-agi/nex-n2-pro":{"draws":2,"losses":1,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":4,"wins":2},"o3":{"draws":0,"losses":2,"wins":4},"openai/gpt-oss-120b":{"draws":6,"losses":0,"wins":2},"poolside/laguna-s-2.1":{"draws":1,"losses":0,"wins":1},"qwen/qwen3.7-max":{"draws":3,"losses":5,"wins":4},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":4},"stepfun/step-3.7-flash":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":2,"losses":2,"wins":2},"x-ai/grok-4.5":{"draws":2,"losses":13,"wins":3},"x-ai/grok-build-0.1":{"draws":2,"losses":1,"wins":7},"xiaomi/mimo-v2.5":{"draws":9,"losses":2,"wins":7},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":5,"wins":1},"z-ai/glm-5.2":{"draws":13,"losses":10,"wins":3}},"stepfun/step-3.7-flash":{"claude-fable-5":{"draws":2,"losses":6,"wins":0},"claude-opus-4-5":{"draws":9,"losses":4,"wins":1},"claude-opus-4-8":{"draws":0,"losses":0,"wins":2},"claude-opus-5":{"draws":0,"losses":2,"wins":0},"claude-sonnet-5":{"draws":2,"losses":4,"wins":0},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":3},"deepseek/deepseek-v4-flash":{"draws":4,"losses":0,"wins":8},"deepseek/deepseek-v4-pro":{"draws":2,"losses":0,"wins":0},"google/gemini-3.1-flash-lite":{"draws":2,"losses":2,"wins":2},"google/gemini-3.5-flash":{"draws":0,"losses":2,"wins":2},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":4},"gpt-5":{"draws":2,"losses":2,"wins":0},"gpt-5.4":{"draws":1,"losses":0,"wins":3},"gpt-5.4-mini":{"draws":10,"losses":6,"wins":6},"gpt-5.4-nano":{"draws":8,"losses":5,"wins":1},"gpt-5.5":{"draws":4,"losses":4,"wins":2},"gpt-5.6-luna":{"draws":2,"losses":2,"wins":0},"gpt-5.6-sol":{"draws":2,"losses":2,"wins":0},"gpt-5.6-terra":{"draws":4,"losses":2,"wins":0},"minimax/minimax-m3":{"draws":0,"losses":2,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":6,"losses":0,"wins":0},"nex-agi/nex-n2-pro":{"draws":0,"losses":1,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":1,"losses":0,"wins":1},"o3":{"draws":1,"losses":2,"wins":1},"openai/gpt-oss-120b":{"draws":3,"losses":0,"wins":5},"qwen/qwen3.7-max":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":2,"losses":0,"wins":2},"thinkingmachines/inkling":{"draws":2,"losses":0,"wins":0},"x-ai/grok-4.5":{"draws":7,"losses":4,"wins":3},"x-ai/grok-build-0.1":{"draws":2,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":10,"losses":5,"wins":5},"z-ai/glm-5.2":{"draws":0,"losses":4,"wins":0}},"thinkingmachines/inkling":{"claude-opus-4-5":{"draws":4,"losses":1,"wins":3},"claude-opus-4-8":{"draws":0,"losses":4,"wins":2},"claude-opus-5":{"draws":1,"losses":13,"wins":2},"claude-sonnet-5":{"draws":2,"losses":2,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":0},"deepseek/deepseek-v4-flash":{"draws":8,"losses":5,"wins":11},"deepseek/deepseek-v4-pro":{"draws":0,"losses":1,"wins":1},"google/gemini-3.1-flash-lite":{"draws":3,"losses":4,"wins":5},"google/gemini-3.5-flash":{"draws":0,"losses":2,"wins":0},"google/gemini-3.5-flash-lite":{"draws":23,"losses":36,"wins":37},"google/gemini-3.6-flash":{"draws":23,"losses":33,"wins":28},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":2},"gpt-4.1":{"draws":0,"losses":2,"wins":0},"gpt-5.4":{"draws":2,"losses":1,"wins":1},"gpt-5.4-mini":{"draws":8,"losses":8,"wins":6},"gpt-5.4-nano":{"draws":7,"losses":9,"wins":22},"gpt-5.5":{"draws":3,"losses":4,"wins":3},"gpt-5.6-luna":{"draws":2,"losses":0,"wins":0},"gpt-5.6-sol":{"draws":0,"losses":3,"wins":1},"gpt-5.6-terra":{"draws":2,"losses":2,"wins":0},"inclusionai/ling-3.0-flash":{"draws":8,"losses":11,"wins":17},"meituan/longcat-2.0":{"draws":13,"losses":23,"wins":18},"minimax/minimax-m3":{"draws":2,"losses":1,"wins":1},"mistralai/mistral-medium-3-5":{"draws":2,"losses":1,"wins":3},"moonshotai/kimi-k3":{"draws":14,"losses":16,"wins":4},"nex-agi/nex-n2-pro":{"draws":0,"losses":1,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":1,"wins":1},"o3":{"draws":0,"losses":4,"wins":0},"openai/gpt-oss-120b":{"draws":1,"losses":1,"wins":0},"poolside/laguna-s-2.1":{"draws":7,"losses":19,"wins":14},"qwen/qwen3.7-max":{"draws":2,"losses":1,"wins":1},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":2},"stepfun/step-3.7-flash":{"draws":0,"losses":1,"wins":1},"tencent/hy3-preview":{"draws":0,"losses":2,"wins":2},"thinkingmachines/inkling":{"draws":16,"losses":23,"wins":17},"x-ai/grok-4.5":{"draws":11,"losses":30,"wins":5},"xiaomi/mimo-v2.5":{"draws":11,"losses":6,"wins":3},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":2,"wins":4},"z-ai/glm-5.2":{"draws":4,"losses":10,"wins":4}},"x-ai/grok-4.5":{"claude-fable-5":{"draws":11,"losses":17,"wins":14},"claude-opus-4-5":{"draws":11,"losses":15,"wins":28},"claude-opus-4-8":{"draws":3,"losses":4,"wins":17},"claude-opus-5":{"draws":12,"losses":76,"wins":20},"claude-sonnet-5":{"draws":7,"losses":3,"wins":16},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":6},"deepseek/deepseek-v4-flash":{"draws":5,"losses":2,"wins":5},"deepseek/deepseek-v4-pro":{"draws":0,"losses":1,"wins":1},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":6},"google/gemini-3.5-flash":{"draws":11,"losses":9,"wins":6},"google/gemini-3.5-flash-lite":{"draws":18,"losses":11,"wins":47},"google/gemini-3.6-flash":{"draws":11,"losses":26,"wins":29},"google/gemma-4-31b-it":{"draws":4,"losses":3,"wins":15},"gpt-4.1":{"draws":1,"losses":3,"wins":4},"gpt-5":{"draws":6,"losses":2,"wins":14},"gpt-5.4":{"draws":12,"losses":18,"wins":16},"gpt-5.4-mini":{"draws":24,"losses":15,"wins":37},"gpt-5.4-nano":{"draws":12,"losses":19,"wins":41},"gpt-5.5":{"draws":10,"losses":15,"wins":15},"gpt-5.6-luna":{"draws":9,"losses":6,"wins":13},"gpt-5.6-sol":{"draws":11,"losses":20,"wins":21},"gpt-5.6-terra":{"draws":12,"losses":6,"wins":20},"inclusionai/ling-3.0-flash":{"draws":6,"losses":1,"wins":19},"meituan/longcat-2.0":{"draws":6,"losses":6,"wins":32},"minimax/minimax-m3":{"draws":10,"losses":0,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":29},"moonshotai/kimi-k3":{"draws":18,"losses":27,"wins":39},"nex-agi/nex-n2-pro":{"draws":2,"losses":1,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":4,"wins":2},"o3":{"draws":2,"losses":6,"wins":14},"openai/gpt-oss-120b":{"draws":5,"losses":0,"wins":9},"poolside/laguna-s-2.1":{"draws":8,"losses":9,"wins":19},"qwen/qwen3.7-max":{"draws":9,"losses":12,"wins":13},"qwen/qwen3.7-plus":{"draws":4,"losses":3,"wins":9},"stepfun/step-3.7-flash":{"draws":5,"losses":2,"wins":5},"tencent/hy3-preview":{"draws":4,"losses":1,"wins":5},"thinkingmachines/inkling":{"draws":10,"losses":5,"wins":23},"x-ai/grok-4.5":{"draws":30,"losses":37,"wins":39},"x-ai/grok-build-0.1":{"draws":6,"losses":2,"wins":14},"xiaomi/mimo-v2.5":{"draws":9,"losses":4,"wins":31},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":4,"wins":7},"z-ai/glm-5.2":{"draws":9,"losses":20,"wins":29}},"x-ai/grok-build-0.1":{"claude-fable-5":{"draws":0,"losses":0,"wins":2},"claude-opus-4-5":{"draws":9,"losses":9,"wins":2},"claude-opus-4-8":{"draws":5,"losses":4,"wins":5},"claude-opus-5":{"draws":4,"losses":0,"wins":2},"claude-sonnet-5":{"draws":1,"losses":10,"wins":1},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":4},"deepseek/deepseek-v4-flash":{"draws":8,"losses":4,"wins":10},"deepseek/deepseek-v4-pro":{"draws":8,"losses":1,"wins":1},"google/gemini-3.1-flash-lite":{"draws":7,"losses":1,"wins":10},"google/gemini-3.5-flash":{"draws":4,"losses":4,"wins":0},"google/gemini-3.5-flash-lite":{"draws":0,"losses":2,"wins":2},"google/gemini-3.6-flash":{"draws":0,"losses":2,"wins":0},"google/gemma-4-31b-it":{"draws":5,"losses":4,"wins":5},"gpt-5":{"draws":6,"losses":5,"wins":3},"gpt-5.4":{"draws":2,"losses":2,"wins":0},"gpt-5.4-mini":{"draws":3,"losses":9,"wins":12},"gpt-5.4-nano":{"draws":13,"losses":6,"wins":15},"gpt-5.5":{"draws":7,"losses":2,"wins":5},"gpt-5.6-luna":{"draws":14,"losses":6,"wins":0},"gpt-5.6-sol":{"draws":4,"losses":6,"wins":6},"gpt-5.6-terra":{"draws":4,"losses":6,"wins":0},"meituan/longcat-2.0":{"draws":1,"losses":3,"wins":2},"minimax/minimax-m3":{"draws":5,"losses":3,"wins":6},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":5,"wins":1},"moonshotai/kimi-k3":{"draws":11,"losses":5,"wins":0},"nex-agi/nex-n2-pro":{"draws":4,"losses":2,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":6,"wins":4},"o3":{"draws":3,"losses":7,"wins":0},"openai/gpt-oss-120b":{"draws":3,"losses":2,"wins":9},"poolside/laguna-s-2.1":{"draws":1,"losses":0,"wins":3},"qwen/qwen3.7-max":{"draws":0,"losses":2,"wins":8},"qwen/qwen3.7-plus":{"draws":2,"losses":8,"wins":2},"stepfun/step-3.7-flash":{"draws":4,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":0,"losses":2,"wins":0},"thinkingmachines/inkling":{"draws":2,"losses":2,"wins":2},"x-ai/grok-4.5":{"draws":8,"losses":14,"wins":4},"xiaomi/mimo-v2.5":{"draws":12,"losses":5,"wins":11},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":4,"wins":0},"z-ai/glm-5.2":{"draws":4,"losses":6,"wins":4}},"xiaomi/mimo-v2.5":{"claude-fable-5":{"draws":1,"losses":7,"wins":0},"claude-opus-4-5":{"draws":25,"losses":8,"wins":7},"claude-opus-4-8":{"draws":12,"losses":9,"wins":1},"claude-opus-5":{"draws":1,"losses":5,"wins":0},"claude-sonnet-5":{"draws":23,"losses":12,"wins":5},"cohere/north-mini-code":{"draws":6,"losses":8,"wins":4},"deepseek/deepseek-v4-flash":{"draws":6,"losses":6,"wins":10},"deepseek/deepseek-v4-pro":{"draws":2,"losses":0,"wins":2},"google/gemini-3.1-flash-lite":{"draws":6,"losses":6,"wins":12},"google/gemini-3.5-flash":{"draws":5,"losses":6,"wins":3},"google/gemini-3.6-flash":{"draws":4,"losses":2,"wins":0},"google/gemma-4-31b-it":{"draws":0,"losses":4,"wins":4},"gpt-5":{"draws":14,"losses":4,"wins":8},"gpt-5.4":{"draws":9,"losses":5,"wins":2},"gpt-5.4-mini":{"draws":31,"losses":21,"wins":26},"gpt-5.4-nano":{"draws":30,"losses":20,"wins":32},"gpt-5.5":{"draws":14,"losses":4,"wins":0},"gpt-5.6-luna":{"draws":9,"losses":4,"wins":7},"gpt-5.6-sol":{"draws":6,"losses":3,"wins":3},"gpt-5.6-terra":{"draws":10,"losses":12,"wins":2},"meituan/longcat-2.0":{"draws":2,"losses":2,"wins":2},"minimax/minimax-m3":{"draws":9,"losses":7,"wins":8},"mistralai/mistral-medium-3-5":{"draws":0,"losses":2,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":9,"wins":4},"moonshotai/kimi-k3":{"draws":18,"losses":12,"wins":4},"nex-agi/nex-n2-pro":{"draws":0,"losses":6,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":5,"wins":5},"o3":{"draws":8,"losses":22,"wins":0},"openai/gpt-oss-120b":{"draws":6,"losses":6,"wins":6},"poolside/laguna-s-2.1":{"draws":0,"losses":2,"wins":4},"qwen/qwen3.7-max":{"draws":5,"losses":3,"wins":4},"qwen/qwen3.7-plus":{"draws":9,"losses":7,"wins":2},"stepfun/step-3.7-flash":{"draws":10,"losses":3,"wins":3},"tencent/hy3-preview":{"draws":5,"losses":4,"wins":7},"thinkingmachines/inkling":{"draws":9,"losses":3,"wins":10},"x-ai/grok-4.5":{"draws":8,"losses":23,"wins":3},"x-ai/grok-build-0.1":{"draws":9,"losses":11,"wins":4},"xiaomi/mimo-v2.5":{"draws":28,"losses":12,"wins":12},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":2,"wins":4},"z-ai/glm-5.2":{"draws":16,"losses":26,"wins":12}},"xiaomi/mimo-v2.5-pro":{"claude-fable-5":{"draws":0,"losses":16,"wins":0},"claude-opus-4-5":{"draws":1,"losses":6,"wins":5},"claude-opus-4-8":{"draws":2,"losses":12,"wins":2},"claude-opus-5":{"draws":3,"losses":1,"wins":0},"claude-sonnet-5":{"draws":2,"losses":4,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":4,"wins":0},"deepseek/deepseek-v4-flash":{"draws":6,"losses":6,"wins":8},"deepseek/deepseek-v4-pro":{"draws":1,"losses":1,"wins":0},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":4},"google/gemini-3.5-flash":{"draws":2,"losses":2,"wins":2},"google/gemini-3.5-flash-lite":{"draws":2,"losses":1,"wins":1},"google/gemini-3.6-flash":{"draws":1,"losses":3,"wins":0},"google/gemma-4-31b-it":{"draws":0,"losses":2,"wins":2},"gpt-4.1":{"draws":0,"losses":3,"wins":3},"gpt-5":{"draws":5,"losses":5,"wins":2},"gpt-5.4":{"draws":4,"losses":14,"wins":6},"gpt-5.4-mini":{"draws":7,"losses":9,"wins":8},"gpt-5.4-nano":{"draws":12,"losses":10,"wins":16},"gpt-5.5":{"draws":1,"losses":3,"wins":4},"gpt-5.6-luna":{"draws":4,"losses":4,"wins":8},"gpt-5.6-sol":{"draws":0,"losses":6,"wins":0},"gpt-5.6-terra":{"draws":2,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":2,"losses":0,"wins":6},"minimax/minimax-m3":{"draws":4,"losses":3,"wins":3},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":2,"losses":6,"wins":4},"nex-agi/nex-n2-pro":{"draws":0,"losses":2,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":0,"wins":8},"o3":{"draws":0,"losses":2,"wins":2},"openai/gpt-oss-120b":{"draws":2,"losses":1,"wins":3},"poolside/laguna-s-2.1":{"draws":2,"losses":0,"wins":2},"qwen/qwen3.7-max":{"draws":2,"losses":6,"wins":2},"qwen/qwen3.7-plus":{"draws":2,"losses":1,"wins":5},"tencent/hy3-preview":{"draws":2,"losses":3,"wins":1},"thinkingmachines/inkling":{"draws":0,"losses":0,"wins":2},"x-ai/grok-4.5":{"draws":3,"losses":11,"wins":8},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":2,"losses":3,"wins":7},"z-ai/glm-5.2":{"draws":0,"losses":4,"wins":4}},"z-ai/glm-5.2":{"claude-fable-5":{"draws":0,"losses":8,"wins":4},"claude-opus-4-5":{"draws":7,"losses":7,"wins":6},"claude-opus-4-8":{"draws":12,"losses":9,"wins":5},"claude-opus-5":{"draws":0,"losses":10,"wins":0},"claude-sonnet-5":{"draws":13,"losses":5,"wins":4},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":1},"deepseek/deepseek-v4-flash":{"draws":10,"losses":3,"wins":13},"deepseek/deepseek-v4-pro":{"draws":6,"losses":7,"wins":5},"google/gemini-3.1-flash-lite":{"draws":8,"losses":1,"wins":3},"google/gemini-3.5-flash":{"draws":5,"losses":4,"wins":5},"google/gemini-3.5-flash-lite":{"draws":2,"losses":0,"wins":0},"google/gemini-3.6-flash":{"draws":4,"losses":2,"wins":4},"google/gemma-4-31b-it":{"draws":1,"losses":0,"wins":3},"gpt-4.1":{"draws":1,"losses":2,"wins":5},"gpt-5":{"draws":2,"losses":3,"wins":9},"gpt-5.4":{"draws":10,"losses":7,"wins":3},"gpt-5.4-mini":{"draws":16,"losses":11,"wins":17},"gpt-5.4-nano":{"draws":25,"losses":18,"wins":21},"gpt-5.5":{"draws":6,"losses":6,"wins":6},"gpt-5.6-luna":{"draws":7,"losses":3,"wins":10},"gpt-5.6-sol":{"draws":3,"losses":8,"wins":3},"gpt-5.6-terra":{"draws":6,"losses":9,"wins":5},"inclusionai/ling-3.0-flash":{"draws":0,"losses":1,"wins":1},"meituan/longcat-2.0":{"draws":2,"losses":0,"wins":4},"minimax/minimax-m3":{"draws":2,"losses":4,"wins":2},"mistralai/mistral-medium-3-5":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":3,"wins":3},"moonshotai/kimi-k3":{"draws":4,"losses":8,"wins":4},"nex-agi/nex-n2-pro":{"draws":2,"losses":3,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":2,"wins":4},"o3":{"draws":4,"losses":3,"wins":3},"openai/gpt-oss-120b":{"draws":6,"losses":1,"wins":3},"poolside/laguna-s-2.1":{"draws":0,"losses":2,"wins":2},"qwen/qwen3.7-max":{"draws":3,"losses":2,"wins":3},"qwen/qwen3.7-plus":{"draws":6,"losses":2,"wins":10},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":8,"losses":1,"wins":3},"thinkingmachines/inkling":{"draws":1,"losses":0,"wins":5},"x-ai/grok-4.5":{"draws":1,"losses":16,"wins":11},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":17,"losses":4,"wins":11},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":1,"wins":5},"z-ai/glm-5.2":{"draws":31,"losses":13,"wins":12}}},"none":{"claude-opus-4-5":{"claude-fable-5":{"draws":1,"losses":3,"wins":0},"claude-opus-4-5":{"draws":10,"losses":2,"wins":6},"claude-opus-4-8":{"draws":0,"losses":4,"wins":4},"claude-opus-5":{"draws":3,"losses":14,"wins":1},"claude-sonnet-5":{"draws":4,"losses":2,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":6},"deepseek/deepseek-v4-flash":{"draws":11,"losses":1,"wins":6},"deepseek/deepseek-v4-pro":{"draws":2,"losses":5,"wins":5},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":0},"google/gemini-3.5-flash":{"draws":2,"losses":0,"wins":0},"google/gemini-3.5-flash-lite":{"draws":0,"losses":2,"wins":0},"google/gemini-3.6-flash":{"draws":0,"losses":1,"wins":1},"google/gemma-4-31b-it":{"draws":2,"losses":2,"wins":2},"gpt-5.4":{"draws":5,"losses":5,"wins":8},"gpt-5.4-mini":{"draws":12,"losses":4,"wins":14},"gpt-5.4-nano":{"draws":13,"losses":9,"wins":14},"gpt-5.5":{"draws":7,"losses":3,"wins":2},"gpt-5.6-luna":{"draws":8,"losses":1,"wins":5},"gpt-5.6-sol":{"draws":4,"losses":9,"wins":3},"gpt-5.6-terra":{"draws":9,"losses":5,"wins":6},"meituan/longcat-2.0":{"draws":4,"losses":1,"wins":3},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":2},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":7,"losses":17,"wins":4},"nex-agi/nex-n2-pro":{"draws":4,"losses":3,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":3,"wins":4},"o3":{"draws":2,"losses":3,"wins":5},"openai/gpt-oss-120b":{"draws":4,"losses":0,"wins":4},"qwen/qwen3.7-max":{"draws":1,"losses":3,"wins":4},"qwen/qwen3.7-plus":{"draws":4,"losses":0,"wins":4},"stepfun/step-3.7-flash":{"draws":4,"losses":1,"wins":1},"tencent/hy3-preview":{"draws":2,"losses":3,"wins":7},"thinkingmachines/inkling":{"draws":2,"losses":2,"wins":2},"x-ai/grok-4.5":{"draws":8,"losses":14,"wins":10},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":11,"losses":6,"wins":9},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":7,"wins":3},"z-ai/glm-5.2":{"draws":2,"losses":6,"wins":12}},"claude-opus-4-8":{"claude-fable-5":{"draws":0,"losses":4,"wins":0},"claude-opus-4-5":{"draws":0,"losses":2,"wins":6},"claude-opus-4-8":{"draws":2,"losses":0,"wins":2},"claude-opus-5":{"draws":0,"losses":2,"wins":4},"claude-sonnet-5":{"draws":2,"losses":7,"wins":3},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":4},"deepseek/deepseek-v4-flash":{"draws":3,"losses":4,"wins":11},"deepseek/deepseek-v4-pro":{"draws":4,"losses":4,"wins":8},"google/gemini-3.1-flash-lite":{"draws":0,"losses":3,"wins":3},"google/gemini-3.5-flash":{"draws":1,"losses":1,"wins":0},"google/gemini-3.5-flash-lite":{"draws":1,"losses":1,"wins":2},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":4},"gpt-4.1":{"draws":1,"losses":0,"wins":3},"gpt-5":{"draws":2,"losses":1,"wins":1},"gpt-5.4":{"draws":0,"losses":6,"wins":4},"gpt-5.4-mini":{"draws":10,"losses":6,"wins":18},"gpt-5.4-nano":{"draws":8,"losses":9,"wins":19},"gpt-5.5":{"draws":1,"losses":10,"wins":3},"gpt-5.6-luna":{"draws":3,"losses":5,"wins":2},"gpt-5.6-sol":{"draws":4,"losses":5,"wins":3},"gpt-5.6-terra":{"draws":7,"losses":4,"wins":3},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":6},"mistralai/mistral-medium-3-5":{"draws":0,"losses":2,"wins":2},"moonshotai/kimi-k3":{"draws":9,"losses":8,"wins":5},"nex-agi/nex-n2-pro":{"draws":2,"losses":2,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":1,"wins":1},"o3":{"draws":1,"losses":4,"wins":5},"openai/gpt-oss-120b":{"draws":4,"losses":4,"wins":0},"poolside/laguna-s-2.1":{"draws":0,"losses":1,"wins":5},"qwen/qwen3.7-max":{"draws":2,"losses":5,"wins":3},"qwen/qwen3.7-plus":{"draws":0,"losses":2,"wins":2},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":0,"losses":1,"wins":5},"thinkingmachines/inkling":{"draws":0,"losses":2,"wins":2},"x-ai/grok-4.5":{"draws":10,"losses":10,"wins":6},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":4,"losses":3,"wins":13},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":4,"wins":6},"z-ai/glm-5.2":{"draws":8,"losses":11,"wins":3}},"claude-opus-5":{"claude-fable-5":{"draws":6,"losses":9,"wins":7},"claude-opus-4-5":{"draws":7,"losses":7,"wins":22},"claude-opus-4-8":{"draws":5,"losses":5,"wins":8},"claude-opus-5":{"draws":19,"losses":60,"wins":35},"claude-sonnet-5":{"draws":8,"losses":3,"wins":7},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":2},"deepseek/deepseek-v4-flash":{"draws":2,"losses":0,"wins":0},"deepseek/deepseek-v4-pro":{"draws":0,"losses":0,"wins":6},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":4},"google/gemini-3.5-flash":{"draws":1,"losses":3,"wins":8},"google/gemini-3.5-flash-lite":{"draws":6,"losses":2,"wins":6},"google/gemini-3.6-flash":{"draws":5,"losses":14,"wins":9},"gpt-4.1":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":2,"losses":0,"wins":8},"gpt-5.4":{"draws":7,"losses":15,"wins":8},"gpt-5.4-mini":{"draws":3,"losses":3,"wins":14},"gpt-5.4-nano":{"draws":4,"losses":3,"wins":19},"gpt-5.5":{"draws":5,"losses":6,"wins":11},"gpt-5.6-luna":{"draws":1,"losses":1,"wins":6},"gpt-5.6-sol":{"draws":9,"losses":2,"wins":15},"gpt-5.6-terra":{"draws":6,"losses":6,"wins":12},"inclusionai/ling-3.0-flash":{"draws":5,"losses":0,"wins":3},"meituan/longcat-2.0":{"draws":3,"losses":2,"wins":3},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":4},"moonshotai/kimi-k3":{"draws":10,"losses":8,"wins":20},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":0,"wins":0},"o3":{"draws":0,"losses":0,"wins":4},"poolside/laguna-s-2.1":{"draws":2,"losses":2,"wins":12},"qwen/qwen3.7-max":{"draws":0,"losses":3,"wins":5},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":1,"losses":0,"wins":1},"thinkingmachines/inkling":{"draws":1,"losses":1,"wins":4},"x-ai/grok-4.5":{"draws":14,"losses":6,"wins":46},"x-ai/grok-build-0.1":{"draws":3,"losses":1,"wins":0},"xiaomi/mimo-v2.5":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":0,"wins":4},"z-ai/glm-5.2":{"draws":5,"losses":4,"wins":23}},"claude-sonnet-5":{"claude-fable-5":{"draws":0,"losses":2,"wins":0},"claude-opus-4-5":{"draws":5,"losses":1,"wins":2},"claude-opus-4-8":{"draws":4,"losses":5,"wins":3},"claude-opus-5":{"draws":3,"losses":11,"wins":2},"claude-sonnet-5":{"draws":3,"losses":1,"wins":4},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":3},"deepseek/deepseek-v4-flash":{"draws":8,"losses":5,"wins":1},"deepseek/deepseek-v4-pro":{"draws":2,"losses":0,"wins":0},"google/gemini-3.1-flash-lite":{"draws":2,"losses":2,"wins":0},"google/gemini-3.5-flash":{"draws":2,"losses":2,"wins":0},"google/gemini-3.5-flash-lite":{"draws":4,"losses":0,"wins":2},"google/gemini-3.6-flash":{"draws":2,"losses":2,"wins":0},"google/gemma-4-31b-it":{"draws":6,"losses":0,"wins":0},"gpt-4.1":{"draws":1,"losses":0,"wins":3},"gpt-5":{"draws":5,"losses":3,"wins":4},"gpt-5.4":{"draws":4,"losses":2,"wins":2},"gpt-5.4-mini":{"draws":6,"losses":8,"wins":8},"gpt-5.4-nano":{"draws":15,"losses":5,"wins":6},"gpt-5.5":{"draws":2,"losses":2,"wins":4},"gpt-5.6-luna":{"draws":5,"losses":3,"wins":4},"gpt-5.6-sol":{"draws":0,"losses":2,"wins":2},"gpt-5.6-terra":{"draws":3,"losses":2,"wins":3},"inclusionai/ling-3.0-flash":{"draws":2,"losses":0,"wins":2},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":0},"mistralai/mistral-medium-3-5":{"draws":2,"losses":4,"wins":0},"moonshotai/kimi-k3":{"draws":2,"losses":2,"wins":2},"nex-agi/nex-n2-pro":{"draws":3,"losses":1,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":2,"wins":4},"o3":{"draws":0,"losses":1,"wins":1},"openai/gpt-oss-120b":{"draws":0,"losses":2,"wins":4},"poolside/laguna-s-2.1":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.7-max":{"draws":3,"losses":0,"wins":1},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":4},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":2,"losses":2,"wins":0},"thinkingmachines/inkling":{"draws":0,"losses":1,"wins":1},"x-ai/grok-4.5":{"draws":2,"losses":4,"wins":0},"xiaomi/mimo-v2.5":{"draws":10,"losses":9,"wins":5},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":2},"z-ai/glm-5.2":{"draws":7,"losses":12,"wins":11}},"cohere/north-mini-code":{"claude-opus-4-5":{"draws":4,"losses":6,"wins":0},"claude-opus-4-8":{"draws":0,"losses":4,"wins":0},"claude-opus-5":{"draws":2,"losses":8,"wins":2},"claude-sonnet-5":{"draws":0,"losses":2,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":3,"wins":1},"deepseek/deepseek-v4-flash":{"draws":10,"losses":8,"wins":4},"deepseek/deepseek-v4-pro":{"draws":4,"losses":6,"wins":0},"google/gemini-3.1-flash-lite":{"draws":0,"losses":3,"wins":3},"google/gemini-3.5-flash-lite":{"draws":0,"losses":2,"wins":0},"google/gemini-3.6-flash":{"draws":0,"losses":0,"wins":2},"google/gemma-4-31b-it":{"draws":1,"losses":3,"wins":2},"gpt-4.1":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":0,"losses":2,"wins":0},"gpt-5.4":{"draws":4,"losses":4,"wins":2},"gpt-5.4-mini":{"draws":14,"losses":13,"wins":5},"gpt-5.4-nano":{"draws":10,"losses":16,"wins":10},"gpt-5.5":{"draws":6,"losses":2,"wins":0},"gpt-5.6-luna":{"draws":2,"losses":2,"wins":4},"gpt-5.6-sol":{"draws":0,"losses":3,"wins":1},"gpt-5.6-terra":{"draws":2,"losses":4,"wins":0},"inclusionai/ling-3.0-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":2,"losses":0,"wins":0},"minimax/minimax-m3":{"draws":0,"losses":5,"wins":3},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":0,"losses":4,"wins":0},"nex-agi/nex-n2-pro":{"draws":0,"losses":2,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":2,"wins":2},"o3":{"draws":0,"losses":8,"wins":2},"openai/gpt-oss-120b":{"draws":6,"losses":4,"wins":0},"poolside/laguna-s-2.1":{"draws":0,"losses":0,"wins":2},"qwen/qwen3.7-max":{"draws":1,"losses":4,"wins":1},"qwen/qwen3.7-plus":{"draws":5,"losses":4,"wins":1},"stepfun/step-3.7-flash":{"draws":2,"losses":7,"wins":1},"tencent/hy3-preview":{"draws":2,"losses":0,"wins":0},"thinkingmachines/inkling":{"draws":3,"losses":1,"wins":0},"x-ai/grok-4.5":{"draws":1,"losses":7,"wins":0},"xiaomi/mimo-v2.5":{"draws":12,"losses":9,"wins":5},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":4,"wins":2},"z-ai/glm-5.2":{"draws":7,"losses":0,"wins":1}},"deepseek/deepseek-v4-flash":{"claude-fable-5":{"draws":1,"losses":3,"wins":0},"claude-opus-4-5":{"draws":17,"losses":7,"wins":0},"claude-opus-4-8":{"draws":4,"losses":12,"wins":2},"claude-opus-5":{"draws":2,"losses":0,"wins":0},"claude-sonnet-5":{"draws":9,"losses":4,"wins":9},"cohere/north-mini-code":{"draws":10,"losses":6,"wins":6},"deepseek/deepseek-v4-flash":{"draws":31,"losses":30,"wins":25},"deepseek/deepseek-v4-pro":{"draws":8,"losses":4,"wins":8},"google/gemini-3.1-flash-lite":{"draws":6,"losses":0,"wins":2},"google/gemini-3.5-flash":{"draws":11,"losses":2,"wins":1},"google/gemini-3.5-flash-lite":{"draws":5,"losses":3,"wins":0},"google/gemini-3.6-flash":{"draws":9,"losses":4,"wins":1},"google/gemma-4-31b-it":{"draws":10,"losses":5,"wins":9},"gpt-4.1":{"draws":2,"losses":4,"wins":2},"gpt-5":{"draws":2,"losses":0,"wins":0},"gpt-5.4":{"draws":14,"losses":11,"wins":3},"gpt-5.4-mini":{"draws":48,"losses":30,"wins":24},"gpt-5.4-nano":{"draws":32,"losses":17,"wins":27},"gpt-5.5":{"draws":16,"losses":12,"wins":2},"gpt-5.6-luna":{"draws":23,"losses":13,"wins":10},"gpt-5.6-sol":{"draws":4,"losses":17,"wins":3},"gpt-5.6-terra":{"draws":10,"losses":24,"wins":4},"inclusionai/ling-3.0-flash":{"draws":4,"losses":1,"wins":3},"meituan/longcat-2.0":{"draws":3,"losses":1,"wins":0},"minimax/minimax-m3":{"draws":4,"losses":12,"wins":8},"mistralai/mistral-medium-3-5":{"draws":4,"losses":8,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":15,"losses":29,"wins":4},"nex-agi/nex-n2-pro":{"draws":14,"losses":13,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":3,"wins":5},"o3":{"draws":5,"losses":9,"wins":6},"openai/gpt-oss-120b":{"draws":16,"losses":7,"wins":9},"poolside/laguna-s-2.1":{"draws":7,"losses":1,"wins":0},"qwen/qwen3.7-max":{"draws":10,"losses":13,"wins":3},"qwen/qwen3.7-plus":{"draws":12,"losses":7,"wins":11},"stepfun/step-3.7-flash":{"draws":12,"losses":11,"wins":9},"tencent/hy3-preview":{"draws":12,"losses":5,"wins":5},"thinkingmachines/inkling":{"draws":8,"losses":5,"wins":5},"x-ai/grok-4.5":{"draws":23,"losses":22,"wins":5},"x-ai/grok-build-0.1":{"draws":4,"losses":4,"wins":2},"xiaomi/mimo-v2.5":{"draws":18,"losses":26,"wins":22},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":8,"wins":4},"z-ai/glm-5.2":{"draws":12,"losses":12,"wins":10}},"deepseek/deepseek-v4-pro":{"claude-fable-5":{"draws":1,"losses":3,"wins":0},"claude-opus-4-5":{"draws":2,"losses":5,"wins":5},"claude-opus-4-8":{"draws":6,"losses":8,"wins":4},"claude-opus-5":{"draws":0,"losses":3,"wins":1},"claude-sonnet-5":{"draws":3,"losses":3,"wins":2},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":6},"deepseek/deepseek-v4-flash":{"draws":12,"losses":10,"wins":6},"deepseek/deepseek-v4-pro":{"draws":0,"losses":4,"wins":0},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":0},"google/gemini-3.5-flash-lite":{"draws":1,"losses":1,"wins":0},"google/gemma-4-31b-it":{"draws":2,"losses":1,"wins":3},"gpt-5":{"draws":0,"losses":2,"wins":2},"gpt-5.4":{"draws":3,"losses":6,"wins":3},"gpt-5.4-mini":{"draws":17,"losses":4,"wins":15},"gpt-5.4-nano":{"draws":15,"losses":11,"wins":12},"gpt-5.5":{"draws":4,"losses":5,"wins":1},"gpt-5.6-luna":{"draws":7,"losses":2,"wins":3},"gpt-5.6-sol":{"draws":2,"losses":5,"wins":5},"gpt-5.6-terra":{"draws":4,"losses":2,"wins":4},"inclusionai/ling-3.0-flash":{"draws":1,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":1,"losses":1,"wins":0},"minimax/minimax-m3":{"draws":3,"losses":4,"wins":3},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":1,"wins":1},"moonshotai/kimi-k3":{"draws":6,"losses":5,"wins":3},"nex-agi/nex-n2-pro":{"draws":2,"losses":5,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":2,"wins":2},"o3":{"draws":2,"losses":4,"wins":2},"openai/gpt-oss-120b":{"draws":2,"losses":1,"wins":3},"qwen/qwen3.7-max":{"draws":9,"losses":3,"wins":6},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":4},"stepfun/step-3.7-flash":{"draws":5,"losses":1,"wins":4},"tencent/hy3-preview":{"draws":4,"losses":4,"wins":0},"thinkingmachines/inkling":{"draws":2,"losses":1,"wins":3},"x-ai/grok-4.5":{"draws":6,"losses":13,"wins":9},"x-ai/grok-build-0.1":{"draws":4,"losses":1,"wins":1},"xiaomi/mimo-v2.5":{"draws":3,"losses":6,"wins":9},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":5,"wins":4},"z-ai/glm-5.2":{"draws":6,"losses":8,"wins":6}},"google/gemini-3.1-flash-lite":{"claude-opus-4-5":{"draws":2,"losses":0,"wins":0},"claude-opus-4-8":{"draws":0,"losses":2,"wins":0},"claude-sonnet-5":{"draws":0,"losses":2,"wins":0},"cohere/north-mini-code":{"draws":0,"losses":3,"wins":1},"deepseek/deepseek-v4-flash":{"draws":6,"losses":5,"wins":3},"deepseek/deepseek-v4-pro":{"draws":2,"losses":1,"wins":1},"google/gemini-3.1-flash-lite":{"draws":0,"losses":6,"wins":2},"google/gemini-3.5-flash":{"draws":1,"losses":1,"wins":0},"google/gemini-3.5-flash-lite":{"draws":0,"losses":4,"wins":0},"google/gemini-3.6-flash":{"draws":2,"losses":0,"wins":0},"google/gemma-4-31b-it":{"draws":0,"losses":3,"wins":3},"gpt-4.1":{"draws":2,"losses":2,"wins":0},"gpt-5":{"draws":0,"losses":2,"wins":0},"gpt-5.4-mini":{"draws":9,"losses":9,"wins":2},"gpt-5.4-nano":{"draws":2,"losses":8,"wins":10},"gpt-5.5":{"draws":2,"losses":2,"wins":0},"gpt-5.6-luna":{"draws":1,"losses":3,"wins":2},"gpt-5.6-sol":{"draws":2,"losses":2,"wins":0},"gpt-5.6-terra":{"draws":0,"losses":4,"wins":0},"meituan/longcat-2.0":{"draws":0,"losses":3,"wins":1},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":4},"mistralai/mistral-medium-3-5":{"draws":2,"losses":2,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":0,"losses":2,"wins":0},"nex-agi/nex-n2-pro":{"draws":0,"losses":2,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":7,"wins":1},"o3":{"draws":0,"losses":2,"wins":0},"openai/gpt-oss-120b":{"draws":0,"losses":0,"wins":2},"qwen/qwen3.7-max":{"draws":2,"losses":1,"wins":1},"qwen/qwen3.7-plus":{"draws":1,"losses":5,"wins":0},"stepfun/step-3.7-flash":{"draws":2,"losses":1,"wins":1},"tencent/hy3-preview":{"draws":0,"losses":1,"wins":1},"thinkingmachines/inkling":{"draws":5,"losses":3,"wins":2},"x-ai/grok-4.5":{"draws":2,"losses":1,"wins":1},"x-ai/grok-build-0.1":{"draws":2,"losses":4,"wins":0},"xiaomi/mimo-v2.5":{"draws":4,"losses":2,"wins":4},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":6,"wins":0},"z-ai/glm-5.2":{"draws":3,"losses":6,"wins":1}},"google/gemini-3.5-flash-lite":{"claude-opus-5":{"draws":5,"losses":12,"wins":3},"google/gemini-3.5-flash-lite":{"draws":48,"losses":35,"wins":41},"google/gemini-3.6-flash":{"draws":47,"losses":42,"wins":21},"inclusionai/ling-3.0-flash":{"draws":20,"losses":1,"wins":17},"meituan/longcat-2.0":{"draws":18,"losses":17,"wins":36},"moonshotai/kimi-k3":{"draws":23,"losses":21,"wins":12},"poolside/laguna-s-2.1":{"draws":28,"losses":17,"wins":17},"thinkingmachines/inkling":{"draws":25,"losses":22,"wins":23},"x-ai/grok-4.5":{"draws":14,"losses":35,"wins":19}},"google/gemini-3.6-flash":{"claude-opus-5":{"draws":0,"losses":18,"wins":2},"google/gemini-3.5-flash-lite":{"draws":71,"losses":33,"wins":36},"google/gemini-3.6-flash":{"draws":43,"losses":31,"wins":26},"inclusionai/ling-3.0-flash":{"draws":30,"losses":11,"wins":17},"meituan/longcat-2.0":{"draws":25,"losses":21,"wins":24},"moonshotai/kimi-k3":{"draws":26,"losses":22,"wins":6},"poolside/laguna-s-2.1":{"draws":28,"losses":18,"wins":18},"thinkingmachines/inkling":{"draws":34,"losses":26,"wins":32},"x-ai/grok-4.5":{"draws":15,"losses":28,"wins":19}},"google/gemma-4-31b-it":{"claude-fable-5":{"draws":0,"losses":2,"wins":0},"claude-opus-4-5":{"draws":4,"losses":0,"wins":0},"claude-opus-4-8":{"draws":4,"losses":4,"wins":0},"claude-sonnet-5":{"draws":4,"losses":0,"wins":0},"cohere/north-mini-code":{"draws":1,"losses":2,"wins":3},"deepseek/deepseek-v4-flash":{"draws":13,"losses":14,"wins":11},"deepseek/deepseek-v4-pro":{"draws":4,"losses":4,"wins":2},"google/gemini-3.1-flash-lite":{"draws":4,"losses":1,"wins":3},"google/gemini-3.5-flash":{"draws":2,"losses":0,"wins":0},"google/gemini-3.5-flash-lite":{"draws":0,"losses":0,"wins":2},"google/gemini-3.6-flash":{"draws":1,"losses":0,"wins":1},"google/gemma-4-31b-it":{"draws":2,"losses":1,"wins":1},"gpt-5.4":{"draws":4,"losses":3,"wins":1},"gpt-5.4-mini":{"draws":12,"losses":10,"wins":12},"gpt-5.4-nano":{"draws":5,"losses":11,"wins":12},"gpt-5.5":{"draws":4,"losses":2,"wins":0},"gpt-5.6-luna":{"draws":2,"losses":1,"wins":7},"gpt-5.6-sol":{"draws":4,"losses":4,"wins":0},"gpt-5.6-terra":{"draws":4,"losses":10,"wins":0},"inclusionai/ling-3.0-flash":{"draws":0,"losses":1,"wins":1},"meituan/longcat-2.0":{"draws":0,"losses":3,"wins":3},"minimax/minimax-m3":{"draws":0,"losses":6,"wins":2},"mistralai/mistral-medium-3-5":{"draws":2,"losses":4,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":6,"wins":0},"moonshotai/kimi-k3":{"draws":7,"losses":1,"wins":0},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":0,"wins":2},"o3":{"draws":2,"losses":1,"wins":1},"openai/gpt-oss-120b":{"draws":0,"losses":2,"wins":6},"qwen/qwen3.7-max":{"draws":1,"losses":1,"wins":2},"qwen/qwen3.7-plus":{"draws":0,"losses":2,"wins":6},"stepfun/step-3.7-flash":{"draws":0,"losses":3,"wins":3},"tencent/hy3-preview":{"draws":2,"losses":5,"wins":1},"thinkingmachines/inkling":{"draws":0,"losses":4,"wins":0},"x-ai/grok-4.5":{"draws":1,"losses":9,"wins":0},"x-ai/grok-build-0.1":{"draws":5,"losses":2,"wins":1},"xiaomi/mimo-v2.5":{"draws":2,"losses":10,"wins":6},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":4,"wins":2},"z-ai/glm-5.2":{"draws":2,"losses":4,"wins":2}},"gpt-4.1":{"claude-fable-5":{"draws":0,"losses":0,"wins":2},"claude-opus-4-5":{"draws":5,"losses":2,"wins":1},"claude-opus-4-8":{"draws":1,"losses":7,"wins":2},"claude-opus-5":{"draws":6,"losses":18,"wins":0},"claude-sonnet-5":{"draws":5,"losses":6,"wins":1},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":3},"deepseek/deepseek-v4-flash":{"draws":4,"losses":7,"wins":11},"google/gemini-3.1-flash-lite":{"draws":4,"losses":3,"wins":3},"google/gemini-3.5-flash":{"draws":0,"losses":4,"wins":0},"google/gemini-3.5-flash-lite":{"draws":0,"losses":1,"wins":1},"google/gemini-3.6-flash":{"draws":1,"losses":0,"wins":3},"gpt-5":{"draws":4,"losses":3,"wins":1},"gpt-5.4":{"draws":3,"losses":0,"wins":1},"gpt-5.4-mini":{"draws":12,"losses":11,"wins":5},"gpt-5.4-nano":{"draws":2,"losses":8,"wins":4},"gpt-5.5":{"draws":3,"losses":7,"wins":2},"gpt-5.6-luna":{"draws":2,"losses":4,"wins":0},"gpt-5.6-sol":{"draws":3,"losses":6,"wins":1},"gpt-5.6-terra":{"draws":3,"losses":0,"wins":1},"inclusionai/ling-3.0-flash":{"draws":3,"losses":0,"wins":1},"meituan/longcat-2.0":{"draws":0,"losses":1,"wins":5},"minimax/minimax-m3":{"draws":0,"losses":1,"wins":7},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":1,"wins":1},"moonshotai/kimi-k3":{"draws":4,"losses":3,"wins":5},"nex-agi/nex-n2-pro":{"draws":3,"losses":1,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":2,"wins":4},"o3":{"draws":1,"losses":1,"wins":0},"openai/gpt-oss-120b":{"draws":3,"losses":3,"wins":2},"poolside/laguna-s-2.1":{"draws":4,"losses":1,"wins":1},"qwen/qwen3.7-max":{"draws":6,"losses":0,"wins":0},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":4,"losses":0,"wins":4},"thinkingmachines/inkling":{"draws":0,"losses":0,"wins":2},"x-ai/grok-4.5":{"draws":1,"losses":5,"wins":4},"xiaomi/mimo-v2.5":{"draws":0,"losses":2,"wins":6},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":5,"wins":5},"z-ai/glm-5.2":{"draws":6,"losses":15,"wins":11}},"gpt-5.4":{"claude-fable-5":{"draws":0,"losses":4,"wins":2},"claude-opus-4-5":{"draws":8,"losses":8,"wins":4},"claude-opus-4-8":{"draws":0,"losses":4,"wins":4},"claude-opus-5":{"draws":2,"losses":8,"wins":4},"claude-sonnet-5":{"draws":1,"losses":0,"wins":3},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":2},"deepseek/deepseek-v4-flash":{"draws":17,"losses":4,"wins":11},"deepseek/deepseek-v4-pro":{"draws":3,"losses":4,"wins":7},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":2},"google/gemini-3.5-flash":{"draws":0,"losses":3,"wins":1},"google/gemini-3.5-flash-lite":{"draws":4,"losses":0,"wins":2},"google/gemini-3.6-flash":{"draws":2,"losses":4,"wins":4},"google/gemma-4-31b-it":{"draws":4,"losses":1,"wins":3},"gpt-5":{"draws":0,"losses":0,"wins":6},"gpt-5.4":{"draws":4,"losses":3,"wins":3},"gpt-5.4-mini":{"draws":22,"losses":4,"wins":16},"gpt-5.4-nano":{"draws":15,"losses":7,"wins":16},"gpt-5.5":{"draws":4,"losses":6,"wins":4},"gpt-5.6-luna":{"draws":10,"losses":1,"wins":7},"gpt-5.6-sol":{"draws":4,"losses":5,"wins":9},"gpt-5.6-terra":{"draws":2,"losses":3,"wins":7},"minimax/minimax-m3":{"draws":2,"losses":4,"wins":4},"mistralai/mistral-medium-3-5":{"draws":1,"losses":0,"wins":3},"moonshotai/kimi-k3":{"draws":6,"losses":5,"wins":11},"nex-agi/nex-n2-pro":{"draws":5,"losses":0,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":1,"losses":0,"wins":1},"o3":{"draws":4,"losses":1,"wins":5},"openai/gpt-oss-120b":{"draws":6,"losses":2,"wins":2},"poolside/laguna-s-2.1":{"draws":0,"losses":2,"wins":0},"qwen/qwen3.7-max":{"draws":2,"losses":0,"wins":6},"qwen/qwen3.7-plus":{"draws":4,"losses":0,"wins":2},"stepfun/step-3.7-flash":{"draws":3,"losses":0,"wins":3},"tencent/hy3-preview":{"draws":5,"losses":3,"wins":4},"thinkingmachines/inkling":{"draws":2,"losses":1,"wins":3},"x-ai/grok-4.5":{"draws":10,"losses":5,"wins":19},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":14,"losses":3,"wins":11},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":4,"wins":6},"z-ai/glm-5.2":{"draws":18,"losses":3,"wins":3}},"gpt-5.4-mini":{"claude-fable-5":{"draws":0,"losses":2,"wins":0},"claude-opus-4-5":{"draws":15,"losses":15,"wins":6},"claude-opus-4-8":{"draws":15,"losses":12,"wins":3},"claude-opus-5":{"draws":1,"losses":1,"wins":0},"claude-sonnet-5":{"draws":15,"losses":11,"wins":0},"cohere/north-mini-code":{"draws":12,"losses":5,"wins":9},"deepseek/deepseek-v4-flash":{"draws":49,"losses":24,"wins":31},"deepseek/deepseek-v4-pro":{"draws":16,"losses":14,"wins":2},"google/gemini-3.1-flash-lite":{"draws":7,"losses":5,"wins":14},"google/gemini-3.5-flash":{"draws":8,"losses":2,"wins":2},"google/gemini-3.5-flash-lite":{"draws":5,"losses":8,"wins":5},"google/gemini-3.6-flash":{"draws":4,"losses":2,"wins":0},"google/gemma-4-31b-it":{"draws":11,"losses":12,"wins":9},"gpt-4.1":{"draws":5,"losses":2,"wins":5},"gpt-5":{"draws":6,"losses":4,"wins":0},"gpt-5.4":{"draws":24,"losses":15,"wins":3},"gpt-5.4-mini":{"draws":43,"losses":41,"wins":30},"gpt-5.4-nano":{"draws":49,"losses":42,"wins":39},"gpt-5.5":{"draws":24,"losses":3,"wins":5},"gpt-5.6-luna":{"draws":18,"losses":8,"wins":18},"gpt-5.6-sol":{"draws":8,"losses":14,"wins":4},"gpt-5.6-terra":{"draws":20,"losses":20,"wins":6},"inclusionai/ling-3.0-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":2,"losses":6,"wins":4},"minimax/minimax-m3":{"draws":7,"losses":12,"wins":9},"mistralai/mistral-medium-3-5":{"draws":8,"losses":5,"wins":13},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":22,"losses":18,"wins":8},"nex-agi/nex-n2-pro":{"draws":10,"losses":10,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":6,"wins":5},"o3":{"draws":7,"losses":16,"wins":3},"openai/gpt-oss-120b":{"draws":8,"losses":16,"wins":14},"poolside/laguna-s-2.1":{"draws":3,"losses":3,"wins":4},"qwen/qwen3.7-max":{"draws":8,"losses":8,"wins":4},"qwen/qwen3.7-plus":{"draws":10,"losses":15,"wins":7},"stepfun/step-3.7-flash":{"draws":9,"losses":16,"wins":15},"tencent/hy3-preview":{"draws":11,"losses":10,"wins":9},"thinkingmachines/inkling":{"draws":10,"losses":8,"wins":10},"x-ai/grok-4.5":{"draws":26,"losses":23,"wins":1},"x-ai/grok-build-0.1":{"draws":0,"losses":3,"wins":1},"xiaomi/mimo-v2.5":{"draws":41,"losses":39,"wins":24},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":3,"wins":6},"z-ai/glm-5.2":{"draws":25,"losses":17,"wins":12}},"gpt-5.4-nano":{"claude-fable-5":{"draws":2,"losses":4,"wins":0},"claude-opus-4-5":{"draws":12,"losses":16,"wins":4},"claude-opus-4-8":{"draws":11,"losses":17,"wins":12},"claude-opus-5":{"draws":1,"losses":10,"wins":1},"claude-sonnet-5":{"draws":6,"losses":4,"wins":4},"cohere/north-mini-code":{"draws":9,"losses":7,"wins":10},"deepseek/deepseek-v4-flash":{"draws":40,"losses":33,"wins":23},"deepseek/deepseek-v4-pro":{"draws":15,"losses":10,"wins":7},"google/gemini-3.1-flash-lite":{"draws":9,"losses":11,"wins":6},"google/gemini-3.5-flash":{"draws":5,"losses":3,"wins":2},"google/gemini-3.5-flash-lite":{"draws":9,"losses":9,"wins":2},"google/gemini-3.6-flash":{"draws":5,"losses":7,"wins":2},"google/gemma-4-31b-it":{"draws":7,"losses":12,"wins":9},"gpt-4.1":{"draws":2,"losses":1,"wins":3},"gpt-5":{"draws":7,"losses":2,"wins":3},"gpt-5.4":{"draws":10,"losses":12,"wins":2},"gpt-5.4-mini":{"draws":44,"losses":37,"wins":41},"gpt-5.4-nano":{"draws":39,"losses":46,"wins":37},"gpt-5.5":{"draws":18,"losses":9,"wins":7},"gpt-5.6-luna":{"draws":15,"losses":10,"wins":13},"gpt-5.6-sol":{"draws":6,"losses":20,"wins":12},"gpt-5.6-terra":{"draws":15,"losses":3,"wins":12},"inclusionai/ling-3.0-flash":{"draws":10,"losses":2,"wins":0},"meituan/longcat-2.0":{"draws":7,"losses":6,"wins":5},"minimax/minimax-m3":{"draws":13,"losses":7,"wins":8},"mistralai/mistral-medium-3-5":{"draws":7,"losses":6,"wins":7},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":0,"wins":3},"moonshotai/kimi-k3":{"draws":19,"losses":25,"wins":12},"nex-agi/nex-n2-pro":{"draws":14,"losses":10,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":3,"wins":5},"o3":{"draws":16,"losses":11,"wins":13},"openai/gpt-oss-120b":{"draws":33,"losses":10,"wins":15},"poolside/laguna-s-2.1":{"draws":8,"losses":4,"wins":0},"qwen/qwen3.7-max":{"draws":19,"losses":9,"wins":6},"qwen/qwen3.7-plus":{"draws":10,"losses":11,"wins":7},"stepfun/step-3.7-flash":{"draws":7,"losses":14,"wins":3},"tencent/hy3-preview":{"draws":21,"losses":15,"wins":2},"thinkingmachines/inkling":{"draws":3,"losses":16,"wins":5},"x-ai/grok-4.5":{"draws":22,"losses":26,"wins":14},"x-ai/grok-build-0.1":{"draws":1,"losses":1,"wins":2},"xiaomi/mimo-v2.5":{"draws":43,"losses":33,"wins":22},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":11,"wins":10},"z-ai/glm-5.2":{"draws":27,"losses":33,"wins":18}},"gpt-5.5":{"claude-opus-4-5":{"draws":7,"losses":5,"wins":4},"claude-opus-4-8":{"draws":2,"losses":4,"wins":2},"claude-opus-5":{"draws":2,"losses":0,"wins":0},"claude-sonnet-5":{"draws":0,"losses":2,"wins":2},"cohere/north-mini-code":{"draws":6,"losses":0,"wins":2},"deepseek/deepseek-v4-flash":{"draws":17,"losses":2,"wins":11},"deepseek/deepseek-v4-pro":{"draws":6,"losses":1,"wins":5},"google/gemini-3.5-flash":{"draws":1,"losses":0,"wins":1},"google/gemini-3.5-flash-lite":{"draws":2,"losses":0,"wins":0},"google/gemini-3.6-flash":{"draws":2,"losses":0,"wins":0},"google/gemma-4-31b-it":{"draws":4,"losses":1,"wins":3},"gpt-4.1":{"draws":1,"losses":2,"wins":1},"gpt-5":{"draws":2,"losses":0,"wins":0},"gpt-5.4":{"draws":6,"losses":5,"wins":3},"gpt-5.4-mini":{"draws":23,"losses":4,"wins":3},"gpt-5.4-nano":{"draws":20,"losses":2,"wins":6},"gpt-5.5":{"draws":5,"losses":4,"wins":1},"gpt-5.6-luna":{"draws":7,"losses":2,"wins":3},"gpt-5.6-sol":{"draws":6,"losses":7,"wins":3},"gpt-5.6-terra":{"draws":9,"losses":3,"wins":4},"minimax/minimax-m3":{"draws":2,"losses":3,"wins":3},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":10,"losses":6,"wins":6},"nex-agi/nex-n2-pro":{"draws":4,"losses":2,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":1,"wins":0},"o3":{"draws":3,"losses":2,"wins":1},"openai/gpt-oss-120b":{"draws":9,"losses":0,"wins":1},"qwen/qwen3.7-max":{"draws":3,"losses":4,"wins":1},"qwen/qwen3.7-plus":{"draws":5,"losses":0,"wins":3},"stepfun/step-3.7-flash":{"draws":2,"losses":2,"wins":6},"tencent/hy3-preview":{"draws":6,"losses":5,"wins":3},"thinkingmachines/inkling":{"draws":3,"losses":1,"wins":0},"x-ai/grok-4.5":{"draws":7,"losses":11,"wins":2},"x-ai/grok-build-0.1":{"draws":4,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":14,"losses":1,"wins":5},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":3,"wins":2},"z-ai/glm-5.2":{"draws":10,"losses":5,"wins":7}},"gpt-5.6-luna":{"claude-opus-4-5":{"draws":6,"losses":2,"wins":0},"claude-opus-4-8":{"draws":5,"losses":2,"wins":1},"claude-sonnet-5":{"draws":4,"losses":0,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":8,"wins":2},"deepseek/deepseek-v4-flash":{"draws":25,"losses":11,"wins":8},"deepseek/deepseek-v4-pro":{"draws":7,"losses":2,"wins":1},"google/gemini-3.1-flash-lite":{"draws":3,"losses":9,"wins":4},"google/gemini-3.5-flash-lite":{"draws":2,"losses":4,"wins":0},"google/gemini-3.6-flash":{"draws":0,"losses":2,"wins":0},"google/gemma-4-31b-it":{"draws":2,"losses":7,"wins":1},"gpt-5":{"draws":2,"losses":2,"wins":0},"gpt-5.4":{"draws":7,"losses":8,"wins":1},"gpt-5.4-mini":{"draws":11,"losses":19,"wins":6},"gpt-5.4-nano":{"draws":18,"losses":20,"wins":8},"gpt-5.5":{"draws":8,"losses":2,"wins":2},"gpt-5.6-luna":{"draws":8,"losses":10,"wins":0},"gpt-5.6-sol":{"draws":2,"losses":4,"wins":0},"gpt-5.6-terra":{"draws":5,"losses":5,"wins":0},"inclusionai/ling-3.0-flash":{"draws":0,"losses":2,"wins":0},"meituan/longcat-2.0":{"draws":2,"losses":2,"wins":0},"minimax/minimax-m3":{"draws":6,"losses":5,"wins":1},"mistralai/mistral-medium-3-5":{"draws":0,"losses":6,"wins":1},"moonshotai/kimi-k3":{"draws":3,"losses":2,"wins":1},"nex-agi/nex-n2-pro":{"draws":4,"losses":4,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":3,"wins":1},"o3":{"draws":0,"losses":5,"wins":1},"openai/gpt-oss-120b":{"draws":6,"losses":8,"wins":4},"qwen/qwen3.7-max":{"draws":6,"losses":2,"wins":0},"qwen/qwen3.7-plus":{"draws":5,"losses":5,"wins":2},"stepfun/step-3.7-flash":{"draws":1,"losses":9,"wins":2},"tencent/hy3-preview":{"draws":2,"losses":3,"wins":3},"thinkingmachines/inkling":{"draws":1,"losses":1,"wins":0},"x-ai/grok-4.5":{"draws":6,"losses":1,"wins":3},"x-ai/grok-build-0.1":{"draws":4,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":8,"losses":20,"wins":4},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":3,"wins":0},"z-ai/glm-5.2":{"draws":7,"losses":8,"wins":5}},"gpt-5.6-sol":{"claude-fable-5":{"draws":0,"losses":2,"wins":0},"claude-opus-4-5":{"draws":6,"losses":5,"wins":9},"claude-opus-4-8":{"draws":6,"losses":5,"wins":5},"claude-opus-5":{"draws":5,"losses":5,"wins":0},"claude-sonnet-5":{"draws":2,"losses":3,"wins":1},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":1},"deepseek/deepseek-v4-flash":{"draws":6,"losses":7,"wins":15},"deepseek/deepseek-v4-pro":{"draws":2,"losses":5,"wins":5},"google/gemini-3.1-flash-lite":{"draws":3,"losses":1,"wins":0},"google/gemini-3.5-flash-lite":{"draws":3,"losses":1,"wins":0},"google/gemini-3.6-flash":{"draws":0,"losses":0,"wins":2},"google/gemma-4-31b-it":{"draws":6,"losses":2,"wins":2},"gpt-4.1":{"draws":3,"losses":1,"wins":2},"gpt-5.4":{"draws":4,"losses":7,"wins":5},"gpt-5.4-mini":{"draws":7,"losses":6,"wins":9},"gpt-5.4-nano":{"draws":3,"losses":10,"wins":13},"gpt-5.5":{"draws":7,"losses":3,"wins":4},"gpt-5.6-luna":{"draws":4,"losses":3,"wins":5},"gpt-5.6-sol":{"draws":0,"losses":5,"wins":3},"gpt-5.6-terra":{"draws":5,"losses":8,"wins":7},"inclusionai/ling-3.0-flash":{"draws":0,"losses":1,"wins":1},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":8},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":8,"losses":19,"wins":15},"nex-agi/nex-n2-pro":{"draws":0,"losses":3,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":2,"wins":4},"o3":{"draws":2,"losses":4,"wins":2},"openai/gpt-oss-120b":{"draws":0,"losses":1,"wins":1},"poolside/laguna-s-2.1":{"draws":0,"losses":2,"wins":0},"qwen/qwen3.7-max":{"draws":3,"losses":7,"wins":6},"qwen/qwen3.7-plus":{"draws":0,"losses":1,"wins":5},"stepfun/step-3.7-flash":{"draws":2,"losses":3,"wins":3},"tencent/hy3-preview":{"draws":7,"losses":5,"wins":8},"x-ai/grok-4.5":{"draws":13,"losses":15,"wins":14},"x-ai/grok-build-0.1":{"draws":2,"losses":4,"wins":2},"xiaomi/mimo-v2.5":{"draws":6,"losses":8,"wins":12},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":3,"wins":4},"z-ai/glm-5.2":{"draws":10,"losses":13,"wins":7}},"gpt-5.6-terra":{"claude-fable-5":{"draws":0,"losses":2,"wins":0},"claude-opus-4-5":{"draws":5,"losses":5,"wins":4},"claude-opus-4-8":{"draws":10,"losses":3,"wins":3},"claude-opus-5":{"draws":3,"losses":0,"wins":1},"claude-sonnet-5":{"draws":5,"losses":5,"wins":0},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":4},"deepseek/deepseek-v4-flash":{"draws":15,"losses":8,"wins":25},"deepseek/deepseek-v4-pro":{"draws":6,"losses":4,"wins":2},"google/gemini-3.1-flash-lite":{"draws":0,"losses":2,"wins":0},"google/gemini-3.5-flash":{"draws":2,"losses":2,"wins":0},"google/gemini-3.5-flash-lite":{"draws":2,"losses":0,"wins":0},"google/gemini-3.6-flash":{"draws":2,"losses":0,"wins":0},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":8},"gpt-4.1":{"draws":2,"losses":0,"wins":0},"gpt-5.4":{"draws":2,"losses":11,"wins":5},"gpt-5.4-mini":{"draws":24,"losses":11,"wins":13},"gpt-5.4-nano":{"draws":16,"losses":6,"wins":4},"gpt-5.5":{"draws":7,"losses":6,"wins":3},"gpt-5.6-luna":{"draws":7,"losses":2,"wins":7},"gpt-5.6-sol":{"draws":7,"losses":8,"wins":3},"gpt-5.6-terra":{"draws":0,"losses":2,"wins":0},"inclusionai/ling-3.0-flash":{"draws":4,"losses":0,"wins":0},"minimax/minimax-m3":{"draws":2,"losses":6,"wins":0},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":2,"wins":1},"moonshotai/kimi-k3":{"draws":12,"losses":13,"wins":5},"nex-agi/nex-n2-pro":{"draws":4,"losses":4,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":3,"wins":2},"o3":{"draws":4,"losses":3,"wins":3},"openai/gpt-oss-120b":{"draws":2,"losses":2,"wins":0},"poolside/laguna-s-2.1":{"draws":0,"losses":1,"wins":1},"qwen/qwen3.7-max":{"draws":5,"losses":4,"wins":5},"qwen/qwen3.7-plus":{"draws":4,"losses":2,"wins":0},"stepfun/step-3.7-flash":{"draws":10,"losses":1,"wins":3},"tencent/hy3-preview":{"draws":6,"losses":2,"wins":0},"thinkingmachines/inkling":{"draws":4,"losses":0,"wins":0},"x-ai/grok-4.5":{"draws":14,"losses":13,"wins":3},"xiaomi/mimo-v2.5":{"draws":11,"losses":6,"wins":7},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":5,"wins":3},"z-ai/glm-5.2":{"draws":6,"losses":5,"wins":5}},"inclusionai/ling-3.0-flash":{"claude-opus-4-5":{"draws":3,"losses":2,"wins":1},"claude-opus-5":{"draws":3,"losses":5,"wins":0},"claude-sonnet-5":{"draws":2,"losses":4,"wins":0},"cohere/north-mini-code":{"draws":4,"losses":1,"wins":1},"deepseek/deepseek-v4-flash":{"draws":10,"losses":10,"wins":4},"deepseek/deepseek-v4-pro":{"draws":1,"losses":0,"wins":1},"google/gemini-3.1-flash-lite":{"draws":5,"losses":3,"wins":0},"google/gemini-3.5-flash":{"draws":6,"losses":0,"wins":0},"google/gemini-3.5-flash-lite":{"draws":39,"losses":32,"wins":7},"google/gemini-3.6-flash":{"draws":55,"losses":21,"wins":4},"google/gemma-4-31b-it":{"draws":0,"losses":2,"wins":2},"gpt-4.1":{"draws":3,"losses":1,"wins":0},"gpt-5.4":{"draws":3,"losses":2,"wins":1},"gpt-5.4-mini":{"draws":4,"losses":2,"wins":0},"gpt-5.4-nano":{"draws":17,"losses":0,"wins":7},"gpt-5.5":{"draws":2,"losses":0,"wins":0},"gpt-5.6-luna":{"draws":5,"losses":0,"wins":3},"gpt-5.6-sol":{"draws":1,"losses":2,"wins":1},"gpt-5.6-terra":{"draws":4,"losses":0,"wins":0},"inclusionai/ling-3.0-flash":{"draws":10,"losses":12,"wins":10},"meituan/longcat-2.0":{"draws":24,"losses":20,"wins":10},"minimax/minimax-m3":{"draws":2,"losses":1,"wins":1},"mistralai/mistral-medium-3-5":{"draws":2,"losses":4,"wins":0},"moonshotai/kimi-k3":{"draws":16,"losses":11,"wins":1},"nex-agi/nex-n2-pro":{"draws":1,"losses":5,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":3,"wins":1},"openai/gpt-oss-120b":{"draws":3,"losses":2,"wins":1},"poolside/laguna-s-2.1":{"draws":26,"losses":12,"wins":6},"qwen/qwen3.7-max":{"draws":0,"losses":2,"wins":0},"qwen/qwen3.7-plus":{"draws":0,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":4,"losses":3,"wins":1},"thinkingmachines/inkling":{"draws":21,"losses":20,"wins":13},"x-ai/grok-4.5":{"draws":9,"losses":26,"wins":3},"xiaomi/mimo-v2.5":{"draws":6,"losses":0,"wins":2},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":0,"wins":1},"z-ai/glm-5.2":{"draws":6,"losses":5,"wins":3}},"meituan/longcat-2.0":{"claude-opus-4-5":{"draws":4,"losses":5,"wins":5},"claude-opus-4-8":{"draws":2,"losses":0,"wins":0},"claude-opus-5":{"draws":4,"losses":6,"wins":4},"claude-sonnet-5":{"draws":4,"losses":6,"wins":0},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":0},"deepseek/deepseek-v4-flash":{"draws":6,"losses":5,"wins":5},"deepseek/deepseek-v4-pro":{"draws":1,"losses":0,"wins":1},"google/gemini-3.1-flash-lite":{"draws":4,"losses":8,"wins":6},"google/gemini-3.5-flash":{"draws":3,"losses":0,"wins":1},"google/gemini-3.5-flash-lite":{"draws":45,"losses":45,"wins":36},"google/gemini-3.6-flash":{"draws":39,"losses":41,"wins":24},"google/gemma-4-31b-it":{"draws":0,"losses":3,"wins":3},"gpt-4.1":{"draws":0,"losses":5,"wins":1},"gpt-5":{"draws":3,"losses":1,"wins":2},"gpt-5.4":{"draws":1,"losses":1,"wins":0},"gpt-5.4-mini":{"draws":7,"losses":12,"wins":9},"gpt-5.4-nano":{"draws":13,"losses":16,"wins":15},"gpt-5.5":{"draws":0,"losses":1,"wins":1},"gpt-5.6-luna":{"draws":2,"losses":2,"wins":2},"gpt-5.6-sol":{"draws":0,"losses":0,"wins":2},"gpt-5.6-terra":{"draws":2,"losses":2,"wins":2},"inclusionai/ling-3.0-flash":{"draws":19,"losses":14,"wins":21},"meituan/longcat-2.0":{"draws":15,"losses":24,"wins":17},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":2},"mistralai/mistral-medium-3-5":{"draws":0,"losses":2,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":3,"wins":1},"moonshotai/kimi-k3":{"draws":24,"losses":19,"wins":7},"nex-agi/nex-n2-pro":{"draws":0,"losses":2,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":3,"wins":3},"o3":{"draws":0,"losses":3,"wins":1},"openai/gpt-oss-120b":{"draws":2,"losses":0,"wins":0},"poolside/laguna-s-2.1":{"draws":33,"losses":21,"wins":12},"qwen/qwen3.7-max":{"draws":2,"losses":2,"wins":0},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":5,"losses":1,"wins":2},"thinkingmachines/inkling":{"draws":19,"losses":29,"wins":28},"x-ai/grok-4.5":{"draws":10,"losses":30,"wins":12},"x-ai/grok-build-0.1":{"draws":1,"losses":2,"wins":3},"xiaomi/mimo-v2.5":{"draws":10,"losses":6,"wins":12},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":10,"wins":0},"z-ai/glm-5.2":{"draws":13,"losses":8,"wins":3}},"minimax/minimax-m3":{"claude-fable-5":{"draws":0,"losses":2,"wins":0},"claude-opus-4-5":{"draws":4,"losses":8,"wins":2},"claude-opus-4-8":{"draws":0,"losses":6,"wins":0},"claude-opus-5":{"draws":0,"losses":9,"wins":1},"cohere/north-mini-code":{"draws":0,"losses":2,"wins":4},"deepseek/deepseek-v4-flash":{"draws":2,"losses":8,"wins":18},"deepseek/deepseek-v4-pro":{"draws":3,"losses":3,"wins":4},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":0},"google/gemini-3.5-flash-lite":{"draws":3,"losses":1,"wins":2},"google/gemini-3.6-flash":{"draws":0,"losses":2,"wins":0},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":6},"gpt-4.1":{"draws":0,"losses":4,"wins":0},"gpt-5":{"draws":1,"losses":2,"wins":3},"gpt-5.4":{"draws":2,"losses":8,"wins":4},"gpt-5.4-mini":{"draws":13,"losses":6,"wins":13},"gpt-5.4-nano":{"draws":15,"losses":7,"wins":6},"gpt-5.5":{"draws":4,"losses":5,"wins":5},"gpt-5.6-luna":{"draws":2,"losses":1,"wins":5},"gpt-5.6-sol":{"draws":0,"losses":6,"wins":0},"gpt-5.6-terra":{"draws":4,"losses":4,"wins":4},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":4,"losses":11,"wins":3},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":0,"wins":4},"o3":{"draws":4,"losses":5,"wins":3},"openai/gpt-oss-120b":{"draws":2,"losses":1,"wins":1},"qwen/qwen3.7-max":{"draws":2,"losses":3,"wins":1},"qwen/qwen3.7-plus":{"draws":1,"losses":1,"wins":4},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":2,"losses":2,"wins":2},"thinkingmachines/inkling":{"draws":2,"losses":1,"wins":5},"x-ai/grok-4.5":{"draws":6,"losses":12,"wins":2},"x-ai/grok-build-0.1":{"draws":0,"losses":1,"wins":3},"xiaomi/mimo-v2.5":{"draws":7,"losses":5,"wins":8},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":4,"wins":4},"z-ai/glm-5.2":{"draws":6,"losses":3,"wins":9}},"mistralai/mistral-medium-3-5":{"claude-opus-4-5":{"draws":0,"losses":8,"wins":0},"claude-opus-4-8":{"draws":0,"losses":2,"wins":2},"claude-sonnet-5":{"draws":2,"losses":0,"wins":2},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":0},"deepseek/deepseek-v4-flash":{"draws":9,"losses":8,"wins":13},"deepseek/deepseek-v4-pro":{"draws":2,"losses":2,"wins":0},"google/gemini-3.1-flash-lite":{"draws":0,"losses":1,"wins":1},"google/gemini-3.5-flash-lite":{"draws":0,"losses":1,"wins":1},"google/gemma-4-31b-it":{"draws":2,"losses":2,"wins":2},"gpt-5":{"draws":0,"losses":0,"wins":2},"gpt-5.4":{"draws":1,"losses":1,"wins":0},"gpt-5.4-mini":{"draws":6,"losses":13,"wins":5},"gpt-5.4-nano":{"draws":8,"losses":7,"wins":5},"gpt-5.5":{"draws":2,"losses":2,"wins":0},"gpt-5.6-luna":{"draws":0,"losses":1,"wins":4},"gpt-5.6-sol":{"draws":0,"losses":4,"wins":0},"gpt-5.6-terra":{"draws":2,"losses":6,"wins":0},"inclusionai/ling-3.0-flash":{"draws":2,"losses":0,"wins":2},"minimax/minimax-m3":{"draws":0,"losses":4,"wins":0},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":2,"losses":4,"wins":0},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":3,"wins":3},"o3":{"draws":0,"losses":4,"wins":0},"openai/gpt-oss-120b":{"draws":4,"losses":3,"wins":1},"poolside/laguna-s-2.1":{"draws":0,"losses":2,"wins":0},"qwen/qwen3.7-max":{"draws":2,"losses":3,"wins":1},"qwen/qwen3.7-plus":{"draws":2,"losses":3,"wins":3},"stepfun/step-3.7-flash":{"draws":0,"losses":5,"wins":5},"tencent/hy3-preview":{"draws":2,"losses":0,"wins":2},"thinkingmachines/inkling":{"draws":0,"losses":2,"wins":2},"x-ai/grok-build-0.1":{"draws":0,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":2,"losses":10,"wins":6},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":4,"wins":0},"z-ai/glm-5.2":{"draws":0,"losses":4,"wins":10}},"moonshotai/kimi-k3":{"claude-opus-4-5":{"draws":7,"losses":4,"wins":13},"claude-opus-4-8":{"draws":5,"losses":5,"wins":8},"claude-opus-5":{"draws":6,"losses":32,"wins":4},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":4},"deepseek/deepseek-v4-flash":{"draws":13,"losses":3,"wins":26},"deepseek/deepseek-v4-pro":{"draws":6,"losses":3,"wins":5},"google/gemini-3.5-flash-lite":{"draws":23,"losses":14,"wins":39},"google/gemini-3.6-flash":{"draws":18,"losses":22,"wins":24},"google/gemma-4-31b-it":{"draws":5,"losses":0,"wins":1},"gpt-5.4":{"draws":6,"losses":11,"wins":5},"gpt-5.4-mini":{"draws":19,"losses":8,"wins":17},"gpt-5.4-nano":{"draws":11,"losses":10,"wins":21},"gpt-5.5":{"draws":8,"losses":6,"wins":6},"gpt-5.6-luna":{"draws":3,"losses":1,"wins":2},"gpt-5.6-sol":{"draws":7,"losses":14,"wins":11},"gpt-5.6-terra":{"draws":10,"losses":5,"wins":9},"inclusionai/ling-3.0-flash":{"draws":11,"losses":1,"wins":6},"meituan/longcat-2.0":{"draws":10,"losses":6,"wins":18},"minimax/minimax-m3":{"draws":4,"losses":3,"wins":11},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":4},"moonshotai/kimi-k3":{"draws":17,"losses":16,"wins":15},"nex-agi/nex-n2-pro":{"draws":2,"losses":4,"wins":6},"o3":{"draws":6,"losses":5,"wins":13},"openai/gpt-oss-120b":{"draws":5,"losses":1,"wins":12},"poolside/laguna-s-2.1":{"draws":13,"losses":6,"wins":13},"qwen/qwen3.7-max":{"draws":6,"losses":5,"wins":9},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":0},"stepfun/step-3.7-flash":{"draws":4,"losses":4,"wins":14},"tencent/hy3-preview":{"draws":3,"losses":3,"wins":6},"thinkingmachines/inkling":{"draws":11,"losses":5,"wins":22},"x-ai/grok-4.5":{"draws":34,"losses":31,"wins":35},"xiaomi/mimo-v2.5":{"draws":5,"losses":12,"wins":17},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":3,"wins":7}},"nex-agi/nex-n2-pro":{"claude-fable-5":{"draws":0,"losses":2,"wins":0},"claude-opus-4-5":{"draws":4,"losses":0,"wins":2},"claude-opus-4-8":{"draws":7,"losses":3,"wins":2},"claude-opus-5":{"draws":0,"losses":2,"wins":0},"claude-sonnet-5":{"draws":2,"losses":3,"wins":3},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":4},"deepseek/deepseek-v4-flash":{"draws":18,"losses":7,"wins":15},"deepseek/deepseek-v4-pro":{"draws":2,"losses":3,"wins":5},"google/gemini-3.1-flash-lite":{"draws":2,"losses":2,"wins":2},"google/gemini-3.5-flash-lite":{"draws":0,"losses":2,"wins":0},"google/gemma-4-31b-it":{"draws":2,"losses":2,"wins":0},"gpt-4.1":{"draws":3,"losses":0,"wins":1},"gpt-5.4":{"draws":6,"losses":6,"wins":0},"gpt-5.4-mini":{"draws":10,"losses":9,"wins":9},"gpt-5.4-nano":{"draws":17,"losses":7,"wins":8},"gpt-5.5":{"draws":4,"losses":2,"wins":2},"gpt-5.6-luna":{"draws":5,"losses":1,"wins":2},"gpt-5.6-sol":{"draws":0,"losses":3,"wins":3},"gpt-5.6-terra":{"draws":8,"losses":6,"wins":4},"inclusionai/ling-3.0-flash":{"draws":0,"losses":1,"wins":3},"minimax/minimax-m3":{"draws":4,"losses":6,"wins":0},"mistralai/mistral-medium-3-5":{"draws":2,"losses":4,"wins":2},"moonshotai/kimi-k3":{"draws":6,"losses":10,"wins":4},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":0,"wins":2},"o3":{"draws":4,"losses":4,"wins":0},"openai/gpt-oss-120b":{"draws":9,"losses":3,"wins":2},"poolside/laguna-s-2.1":{"draws":0,"losses":2,"wins":0},"qwen/qwen3.7-max":{"draws":5,"losses":5,"wins":2},"qwen/qwen3.7-plus":{"draws":0,"losses":2,"wins":2},"stepfun/step-3.7-flash":{"draws":4,"losses":1,"wins":3},"tencent/hy3-preview":{"draws":9,"losses":0,"wins":3},"thinkingmachines/inkling":{"draws":0,"losses":5,"wins":3},"x-ai/grok-4.5":{"draws":3,"losses":12,"wins":3},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":12,"losses":6,"wins":6},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":1,"wins":3},"z-ai/glm-5.2":{"draws":6,"losses":8,"wins":6}},"nvidia/nemotron-3-ultra-550b-a55b":{"claude-opus-4-5":{"draws":0,"losses":4,"wins":2},"claude-opus-4-8":{"draws":0,"losses":3,"wins":5},"claude-opus-5":{"draws":2,"losses":4,"wins":0},"claude-sonnet-5":{"draws":3,"losses":4,"wins":5},"cohere/north-mini-code":{"draws":3,"losses":5,"wins":0},"deepseek/deepseek-v4-flash":{"draws":4,"losses":6,"wins":2},"deepseek/deepseek-v4-pro":{"draws":4,"losses":4,"wins":0},"google/gemini-3.1-flash-lite":{"draws":3,"losses":5,"wins":2},"google/gemini-3.5-flash":{"draws":2,"losses":2,"wins":0},"google/gemini-3.5-flash-lite":{"draws":0,"losses":2,"wins":0},"google/gemini-3.6-flash":{"draws":2,"losses":0,"wins":0},"google/gemma-4-31b-it":{"draws":0,"losses":2,"wins":2},"gpt-5":{"draws":3,"losses":2,"wins":1},"gpt-5.4":{"draws":3,"losses":1,"wins":2},"gpt-5.4-mini":{"draws":9,"losses":4,"wins":5},"gpt-5.4-nano":{"draws":10,"losses":5,"wins":3},"gpt-5.5":{"draws":9,"losses":1,"wins":0},"gpt-5.6-luna":{"draws":2,"losses":2,"wins":4},"gpt-5.6-sol":{"draws":0,"losses":8,"wins":2},"gpt-5.6-terra":{"draws":6,"losses":0,"wins":2},"inclusionai/ling-3.0-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":1,"losses":2,"wins":1},"minimax/minimax-m3":{"draws":4,"losses":3,"wins":3},"mistralai/mistral-medium-3-5":{"draws":0,"losses":4,"wins":2},"moonshotai/kimi-k3":{"draws":1,"losses":2,"wins":1},"nex-agi/nex-n2-pro":{"draws":4,"losses":2,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":0,"wins":2},"o3":{"draws":0,"losses":2,"wins":2},"openai/gpt-oss-120b":{"draws":3,"losses":3,"wins":2},"poolside/laguna-s-2.1":{"draws":0,"losses":1,"wins":1},"qwen/qwen3.7-max":{"draws":0,"losses":4,"wins":2},"qwen/qwen3.7-plus":{"draws":0,"losses":2,"wins":2},"stepfun/step-3.7-flash":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":1,"losses":3,"wins":2},"thinkingmachines/inkling":{"draws":0,"losses":1,"wins":3},"x-ai/grok-4.5":{"draws":3,"losses":3,"wins":2},"x-ai/grok-build-0.1":{"draws":4,"losses":2,"wins":2},"xiaomi/mimo-v2.5":{"draws":3,"losses":4,"wins":5},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":2,"wins":0},"z-ai/glm-5.2":{"draws":3,"losses":6,"wins":7}},"o3":{"claude-opus-4-5":{"draws":2,"losses":4,"wins":2},"claude-opus-4-8":{"draws":1,"losses":3,"wins":2},"claude-opus-5":{"draws":0,"losses":14,"wins":0},"cohere/north-mini-code":{"draws":0,"losses":2,"wins":6},"deepseek/deepseek-v4-flash":{"draws":5,"losses":6,"wins":7},"deepseek/deepseek-v4-pro":{"draws":2,"losses":1,"wins":3},"google/gemma-4-31b-it":{"draws":2,"losses":1,"wins":1},"gpt-5.4":{"draws":4,"losses":5,"wins":1},"gpt-5.4-mini":{"draws":4,"losses":3,"wins":13},"gpt-5.4-nano":{"draws":13,"losses":10,"wins":7},"gpt-5.5":{"draws":2,"losses":0,"wins":2},"gpt-5.6-luna":{"draws":0,"losses":1,"wins":5},"gpt-5.6-sol":{"draws":2,"losses":2,"wins":4},"gpt-5.6-terra":{"draws":4,"losses":1,"wins":3},"minimax/minimax-m3":{"draws":3,"losses":3,"wins":4},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":4},"moonshotai/kimi-k3":{"draws":6,"losses":13,"wins":5},"nex-agi/nex-n2-pro":{"draws":4,"losses":0,"wins":2},"openai/gpt-oss-120b":{"draws":4,"losses":1,"wins":11},"qwen/qwen3.7-max":{"draws":4,"losses":0,"wins":2},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":4},"stepfun/step-3.7-flash":{"draws":3,"losses":3,"wins":8},"tencent/hy3-preview":{"draws":6,"losses":0,"wins":0},"x-ai/grok-4.5":{"draws":8,"losses":13,"wins":7},"xiaomi/mimo-v2.5":{"draws":4,"losses":6,"wins":4},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":0,"wins":4}},"openai/gpt-oss-120b":{"claude-opus-4-5":{"draws":2,"losses":2,"wins":0},"claude-opus-4-8":{"draws":2,"losses":0,"wins":2},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":4},"deepseek/deepseek-v4-flash":{"draws":11,"losses":9,"wins":2},"deepseek/deepseek-v4-pro":{"draws":2,"losses":3,"wins":1},"google/gemma-4-31b-it":{"draws":0,"losses":6,"wins":2},"gpt-5.4":{"draws":4,"losses":2,"wins":0},"gpt-5.4-mini":{"draws":7,"losses":12,"wins":13},"gpt-5.4-nano":{"draws":23,"losses":11,"wins":8},"gpt-5.5":{"draws":6,"losses":0,"wins":0},"gpt-5.6-luna":{"draws":3,"losses":4,"wins":7},"gpt-5.6-sol":{"draws":0,"losses":1,"wins":1},"gpt-5.6-terra":{"draws":2,"losses":0,"wins":2},"minimax/minimax-m3":{"draws":2,"losses":1,"wins":1},"mistralai/mistral-medium-3-5":{"draws":1,"losses":0,"wins":3},"moonshotai/kimi-k3":{"draws":5,"losses":12,"wins":1},"nex-agi/nex-n2-pro":{"draws":5,"losses":2,"wins":1},"o3":{"draws":4,"losses":11,"wins":1},"qwen/qwen3.7-max":{"draws":2,"losses":1,"wins":3},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":6},"stepfun/step-3.7-flash":{"draws":3,"losses":9,"wins":2},"tencent/hy3-preview":{"draws":4,"losses":0,"wins":0},"x-ai/grok-4.5":{"draws":9,"losses":11,"wins":0},"xiaomi/mimo-v2.5":{"draws":6,"losses":5,"wins":9},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":4,"wins":0}},"poolside/laguna-s-2.1":{"claude-fable-5":{"draws":0,"losses":2,"wins":4},"claude-opus-4-5":{"draws":0,"losses":2,"wins":0},"claude-opus-4-8":{"draws":0,"losses":5,"wins":1},"claude-opus-5":{"draws":2,"losses":16,"wins":0},"claude-sonnet-5":{"draws":3,"losses":1,"wins":0},"cohere/north-mini-code":{"draws":4,"losses":4,"wins":2},"deepseek/deepseek-v4-flash":{"draws":7,"losses":3,"wins":8},"deepseek/deepseek-v4-pro":{"draws":0,"losses":2,"wins":2},"google/gemini-3.1-flash-lite":{"draws":4,"losses":1,"wins":1},"google/gemini-3.5-flash":{"draws":9,"losses":1,"wins":2},"google/gemini-3.5-flash-lite":{"draws":35,"losses":24,"wins":47},"google/gemini-3.6-flash":{"draws":28,"losses":33,"wins":19},"gpt-4.1":{"draws":4,"losses":1,"wins":1},"gpt-5":{"draws":4,"losses":1,"wins":3},"gpt-5.4":{"draws":0,"losses":2,"wins":2},"gpt-5.4-mini":{"draws":7,"losses":9,"wins":6},"gpt-5.4-nano":{"draws":14,"losses":4,"wins":10},"gpt-5.5":{"draws":1,"losses":2,"wins":3},"gpt-5.6-luna":{"draws":2,"losses":5,"wins":1},"gpt-5.6-sol":{"draws":0,"losses":4,"wins":2},"gpt-5.6-terra":{"draws":2,"losses":1,"wins":1},"inclusionai/ling-3.0-flash":{"draws":13,"losses":6,"wins":13},"meituan/longcat-2.0":{"draws":21,"losses":20,"wins":19},"mistralai/mistral-medium-3-5":{"draws":0,"losses":1,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":1},"moonshotai/kimi-k3":{"draws":21,"losses":15,"wins":14},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":1,"wins":3},"o3":{"draws":0,"losses":2,"wins":0},"openai/gpt-oss-120b":{"draws":1,"losses":0,"wins":1},"poolside/laguna-s-2.1":{"draws":21,"losses":12,"wins":17},"qwen/qwen3.7-max":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.7-plus":{"draws":1,"losses":1,"wins":0},"tencent/hy3-preview":{"draws":0,"losses":4,"wins":4},"thinkingmachines/inkling":{"draws":11,"losses":18,"wins":31},"x-ai/grok-4.5":{"draws":9,"losses":42,"wins":15},"x-ai/grok-build-0.1":{"draws":1,"losses":3,"wins":0},"xiaomi/mimo-v2.5":{"draws":4,"losses":4,"wins":2},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":2,"wins":2},"z-ai/glm-5.2":{"draws":12,"losses":10,"wins":10}},"qwen/qwen3.7-max":{"claude-opus-4-5":{"draws":3,"losses":9,"wins":4},"claude-opus-4-8":{"draws":2,"losses":5,"wins":3},"claude-opus-5":{"draws":0,"losses":13,"wins":1},"claude-sonnet-5":{"draws":2,"losses":1,"wins":1},"cohere/north-mini-code":{"draws":3,"losses":2,"wins":5},"deepseek/deepseek-v4-flash":{"draws":8,"losses":8,"wins":14},"deepseek/deepseek-v4-pro":{"draws":7,"losses":3,"wins":6},"google/gemini-3.1-flash-lite":{"draws":1,"losses":1,"wins":2},"google/gemini-3.5-flash":{"draws":2,"losses":1,"wins":3},"google/gemma-4-31b-it":{"draws":1,"losses":2,"wins":1},"gpt-5":{"draws":0,"losses":3,"wins":1},"gpt-5.4":{"draws":2,"losses":4,"wins":0},"gpt-5.4-mini":{"draws":9,"losses":8,"wins":11},"gpt-5.4-nano":{"draws":19,"losses":6,"wins":11},"gpt-5.5":{"draws":3,"losses":1,"wins":4},"gpt-5.6-luna":{"draws":12,"losses":3,"wins":3},"gpt-5.6-sol":{"draws":3,"losses":8,"wins":5},"gpt-5.6-terra":{"draws":5,"losses":5,"wins":4},"inclusionai/ling-3.0-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":1,"losses":0,"wins":1},"minimax/minimax-m3":{"draws":2,"losses":2,"wins":4},"mistralai/mistral-medium-3-5":{"draws":2,"losses":3,"wins":3},"moonshotai/kimi-k3":{"draws":6,"losses":9,"wins":5},"nex-agi/nex-n2-pro":{"draws":3,"losses":2,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":1,"wins":1},"o3":{"draws":4,"losses":2,"wins":0},"openai/gpt-oss-120b":{"draws":6,"losses":3,"wins":1},"poolside/laguna-s-2.1":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.7-max":{"draws":2,"losses":2,"wins":0},"qwen/qwen3.7-plus":{"draws":2,"losses":1,"wins":1},"stepfun/step-3.7-flash":{"draws":2,"losses":3,"wins":5},"tencent/hy3-preview":{"draws":7,"losses":2,"wins":1},"thinkingmachines/inkling":{"draws":2,"losses":0,"wins":0},"x-ai/grok-4.5":{"draws":8,"losses":11,"wins":5},"x-ai/grok-build-0.1":{"draws":0,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":4,"losses":5,"wins":7},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":1,"wins":3},"z-ai/glm-5.2":{"draws":8,"losses":4,"wins":6}},"qwen/qwen3.7-plus":{"claude-fable-5":{"draws":0,"losses":2,"wins":0},"claude-opus-4-5":{"draws":12,"losses":3,"wins":1},"claude-opus-4-8":{"draws":0,"losses":4,"wins":2},"claude-opus-5":{"draws":0,"losses":2,"wins":0},"claude-sonnet-5":{"draws":4,"losses":2,"wins":0},"cohere/north-mini-code":{"draws":3,"losses":0,"wins":3},"deepseek/deepseek-v4-flash":{"draws":9,"losses":13,"wins":8},"deepseek/deepseek-v4-pro":{"draws":2,"losses":2,"wins":0},"google/gemini-3.1-flash-lite":{"draws":1,"losses":2,"wins":5},"google/gemini-3.5-flash":{"draws":0,"losses":2,"wins":0},"google/gemini-3.5-flash-lite":{"draws":0,"losses":3,"wins":3},"google/gemma-4-31b-it":{"draws":0,"losses":8,"wins":2},"gpt-5.4":{"draws":2,"losses":2,"wins":0},"gpt-5.4-mini":{"draws":14,"losses":8,"wins":14},"gpt-5.4-nano":{"draws":10,"losses":9,"wins":17},"gpt-5.5":{"draws":5,"losses":3,"wins":0},"gpt-5.6-luna":{"draws":7,"losses":2,"wins":5},"gpt-5.6-sol":{"draws":0,"losses":5,"wins":1},"gpt-5.6-terra":{"draws":4,"losses":4,"wins":2},"inclusionai/ling-3.0-flash":{"draws":0,"losses":0,"wins":2},"minimax/minimax-m3":{"draws":1,"losses":5,"wins":2},"mistralai/mistral-medium-3-5":{"draws":0,"losses":3,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":2,"losses":1,"wins":1},"nex-agi/nex-n2-pro":{"draws":0,"losses":2,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":1,"losses":0,"wins":3},"o3":{"draws":0,"losses":4,"wins":0},"openai/gpt-oss-120b":{"draws":2,"losses":8,"wins":0},"qwen/qwen3.7-max":{"draws":2,"losses":1,"wins":1},"qwen/qwen3.7-plus":{"draws":2,"losses":4,"wins":0},"stepfun/step-3.7-flash":{"draws":0,"losses":5,"wins":3},"tencent/hy3-preview":{"draws":0,"losses":3,"wins":1},"thinkingmachines/inkling":{"draws":2,"losses":2,"wins":0},"x-ai/grok-4.5":{"draws":5,"losses":13,"wins":0},"x-ai/grok-build-0.1":{"draws":0,"losses":1,"wins":1},"xiaomi/mimo-v2.5":{"draws":0,"losses":9,"wins":3},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":6,"wins":0},"z-ai/glm-5.2":{"draws":4,"losses":9,"wins":7}},"stepfun/step-3.7-flash":{"claude-opus-4-5":{"draws":4,"losses":0,"wins":0},"claude-opus-4-8":{"draws":0,"losses":2,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":4},"deepseek/deepseek-v4-flash":{"draws":10,"losses":9,"wins":5},"deepseek/deepseek-v4-pro":{"draws":3,"losses":4,"wins":1},"google/gemma-4-31b-it":{"draws":0,"losses":3,"wins":3},"gpt-5.4":{"draws":3,"losses":3,"wins":0},"gpt-5.4-mini":{"draws":7,"losses":13,"wins":12},"gpt-5.4-nano":{"draws":6,"losses":2,"wins":12},"gpt-5.5":{"draws":1,"losses":5,"wins":0},"gpt-5.6-luna":{"draws":1,"losses":2,"wins":9},"gpt-5.6-sol":{"draws":2,"losses":3,"wins":3},"gpt-5.6-terra":{"draws":6,"losses":3,"wins":1},"minimax/minimax-m3":{"draws":2,"losses":2,"wins":0},"mistralai/mistral-medium-3-5":{"draws":0,"losses":3,"wins":3},"moonshotai/kimi-k3":{"draws":4,"losses":14,"wins":4},"nex-agi/nex-n2-pro":{"draws":4,"losses":3,"wins":1},"o3":{"draws":3,"losses":8,"wins":3},"openai/gpt-oss-120b":{"draws":3,"losses":2,"wins":9},"qwen/qwen3.7-max":{"draws":2,"losses":4,"wins":2},"qwen/qwen3.7-plus":{"draws":0,"losses":1,"wins":3},"tencent/hy3-preview":{"draws":3,"losses":3,"wins":2},"x-ai/grok-4.5":{"draws":2,"losses":14,"wins":2},"xiaomi/mimo-v2.5":{"draws":6,"losses":8,"wins":8},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":1,"wins":0}},"tencent/hy3-preview":{"claude-fable-5":{"draws":1,"losses":1,"wins":4},"claude-opus-4-5":{"draws":3,"losses":6,"wins":3},"claude-opus-4-8":{"draws":1,"losses":6,"wins":1},"claude-opus-5":{"draws":1,"losses":5,"wins":2},"claude-sonnet-5":{"draws":5,"losses":2,"wins":3},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":2},"deepseek/deepseek-v4-flash":{"draws":14,"losses":5,"wins":7},"deepseek/deepseek-v4-pro":{"draws":4,"losses":0,"wins":4},"google/gemini-3.5-flash":{"draws":0,"losses":2,"wins":0},"google/gemini-3.5-flash-lite":{"draws":2,"losses":1,"wins":1},"google/gemini-3.6-flash":{"draws":2,"losses":0,"wins":2},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":2},"gpt-4.1":{"draws":2,"losses":0,"wins":0},"gpt-5.4":{"draws":9,"losses":7,"wins":2},"gpt-5.4-mini":{"draws":12,"losses":10,"wins":6},"gpt-5.4-nano":{"draws":21,"losses":3,"wins":18},"gpt-5.5":{"draws":6,"losses":6,"wins":4},"gpt-5.6-luna":{"draws":4,"losses":3,"wins":3},"gpt-5.6-sol":{"draws":6,"losses":6,"wins":2},"gpt-5.6-terra":{"draws":8,"losses":0,"wins":2},"inclusionai/ling-3.0-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":3,"losses":1,"wins":0},"minimax/minimax-m3":{"draws":4,"losses":2,"wins":2},"mistralai/mistral-medium-3-5":{"draws":2,"losses":2,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":5,"losses":6,"wins":3},"nex-agi/nex-n2-pro":{"draws":7,"losses":3,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":0,"wins":0},"o3":{"draws":9,"losses":0,"wins":1},"openai/gpt-oss-120b":{"draws":4,"losses":0,"wins":0},"poolside/laguna-s-2.1":{"draws":0,"losses":3,"wins":3},"qwen/qwen3.7-max":{"draws":4,"losses":0,"wins":2},"qwen/qwen3.7-plus":{"draws":2,"losses":1,"wins":1},"stepfun/step-3.7-flash":{"draws":5,"losses":4,"wins":3},"tencent/hy3-preview":{"draws":1,"losses":1,"wins":0},"thinkingmachines/inkling":{"draws":0,"losses":1,"wins":1},"x-ai/grok-4.5":{"draws":11,"losses":5,"wins":8},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":9,"losses":6,"wins":3},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":2,"wins":5},"z-ai/glm-5.2":{"draws":15,"losses":6,"wins":1}},"thinkingmachines/inkling":{"claude-fable-5":{"draws":0,"losses":2,"wins":0},"claude-opus-4-5":{"draws":2,"losses":3,"wins":3},"claude-opus-4-8":{"draws":0,"losses":3,"wins":1},"claude-opus-5":{"draws":0,"losses":17,"wins":1},"claude-sonnet-5":{"draws":2,"losses":1,"wins":1},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":1},"deepseek/deepseek-v4-flash":{"draws":3,"losses":5,"wins":6},"deepseek/deepseek-v4-pro":{"draws":2,"losses":4,"wins":0},"google/gemini-3.1-flash-lite":{"draws":4,"losses":2,"wins":2},"google/gemini-3.5-flash":{"draws":0,"losses":4,"wins":0},"google/gemini-3.5-flash-lite":{"draws":32,"losses":31,"wins":33},"google/gemini-3.6-flash":{"draws":40,"losses":40,"wins":10},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":2,"losses":2,"wins":0},"gpt-5.4":{"draws":4,"losses":2,"wins":0},"gpt-5.4-mini":{"draws":10,"losses":6,"wins":8},"gpt-5.4-nano":{"draws":6,"losses":7,"wins":13},"gpt-5.5":{"draws":2,"losses":5,"wins":1},"gpt-5.6-luna":{"draws":5,"losses":0,"wins":1},"gpt-5.6-sol":{"draws":1,"losses":2,"wins":1},"gpt-5.6-terra":{"draws":4,"losses":0,"wins":0},"inclusionai/ling-3.0-flash":{"draws":15,"losses":13,"wins":18},"meituan/longcat-2.0":{"draws":16,"losses":31,"wins":15},"minimax/minimax-m3":{"draws":0,"losses":4,"wins":0},"mistralai/mistral-medium-3-5":{"draws":2,"losses":4,"wins":2},"moonshotai/kimi-k3":{"draws":15,"losses":19,"wins":4},"nex-agi/nex-n2-pro":{"draws":0,"losses":3,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":3,"wins":5},"o3":{"draws":0,"losses":3,"wins":1},"openai/gpt-oss-120b":{"draws":2,"losses":4,"wins":0},"poolside/laguna-s-2.1":{"draws":15,"losses":17,"wins":14},"qwen/qwen3.7-max":{"draws":6,"losses":0,"wins":0},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":0},"stepfun/step-3.7-flash":{"draws":2,"losses":9,"wins":1},"thinkingmachines/inkling":{"draws":18,"losses":13,"wins":19},"x-ai/grok-4.5":{"draws":16,"losses":24,"wins":8},"x-ai/grok-build-0.1":{"draws":2,"losses":2,"wins":2},"xiaomi/mimo-v2.5":{"draws":11,"losses":9,"wins":6},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":2,"wins":0},"z-ai/glm-5.2":{"draws":3,"losses":7,"wins":6}},"x-ai/grok-4.5":{"claude-opus-4-5":{"draws":4,"losses":7,"wins":11},"claude-opus-4-8":{"draws":7,"losses":6,"wins":7},"claude-opus-5":{"draws":4,"losses":27,"wins":3},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":7},"deepseek/deepseek-v4-flash":{"draws":18,"losses":5,"wins":21},"deepseek/deepseek-v4-pro":{"draws":3,"losses":6,"wins":9},"google/gemini-3.5-flash-lite":{"draws":31,"losses":9,"wins":28},"google/gemini-3.6-flash":{"draws":17,"losses":33,"wins":18},"google/gemma-4-31b-it":{"draws":1,"losses":0,"wins":5},"gpt-5.4":{"draws":8,"losses":13,"wins":3},"gpt-5.4-mini":{"draws":21,"losses":1,"wins":16},"gpt-5.4-nano":{"draws":17,"losses":16,"wins":21},"gpt-5.5":{"draws":5,"losses":3,"wins":8},"gpt-5.6-luna":{"draws":4,"losses":2,"wins":0},"gpt-5.6-sol":{"draws":9,"losses":10,"wins":11},"gpt-5.6-terra":{"draws":12,"losses":2,"wins":8},"inclusionai/ling-3.0-flash":{"draws":9,"losses":3,"wins":10},"meituan/longcat-2.0":{"draws":9,"losses":10,"wins":9},"minimax/minimax-m3":{"draws":6,"losses":2,"wins":10},"moonshotai/kimi-k3":{"draws":35,"losses":32,"wins":25},"nex-agi/nex-n2-pro":{"draws":3,"losses":3,"wins":8},"o3":{"draws":8,"losses":7,"wins":13},"openai/gpt-oss-120b":{"draws":9,"losses":0,"wins":11},"poolside/laguna-s-2.1":{"draws":12,"losses":8,"wins":12},"qwen/qwen3.7-max":{"draws":8,"losses":4,"wins":8},"qwen/qwen3.7-plus":{"draws":3,"losses":0,"wins":7},"stepfun/step-3.7-flash":{"draws":2,"losses":2,"wins":14},"tencent/hy3-preview":{"draws":6,"losses":5,"wins":5},"thinkingmachines/inkling":{"draws":10,"losses":5,"wins":23},"x-ai/grok-4.5":{"draws":18,"losses":23,"wins":13},"xiaomi/mimo-v2.5":{"draws":8,"losses":7,"wins":15},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":4,"wins":10}},"xiaomi/mimo-v2.5":{"claude-fable-5":{"draws":1,"losses":3,"wins":0},"claude-opus-4-5":{"draws":8,"losses":12,"wins":10},"claude-opus-4-8":{"draws":3,"losses":13,"wins":2},"claude-opus-5":{"draws":2,"losses":1,"wins":1},"claude-sonnet-5":{"draws":7,"losses":4,"wins":7},"cohere/north-mini-code":{"draws":11,"losses":5,"wins":10},"deepseek/deepseek-v4-flash":{"draws":26,"losses":28,"wins":30},"deepseek/deepseek-v4-pro":{"draws":5,"losses":9,"wins":6},"google/gemini-3.1-flash-lite":{"draws":2,"losses":4,"wins":2},"google/gemini-3.5-flash":{"draws":7,"losses":1,"wins":2},"google/gemini-3.5-flash-lite":{"draws":2,"losses":3,"wins":1},"google/gemini-3.6-flash":{"draws":4,"losses":5,"wins":3},"google/gemma-4-31b-it":{"draws":0,"losses":8,"wins":6},"gpt-4.1":{"draws":0,"losses":5,"wins":1},"gpt-5":{"draws":4,"losses":4,"wins":2},"gpt-5.4":{"draws":10,"losses":13,"wins":3},"gpt-5.4-mini":{"draws":30,"losses":31,"wins":39},"gpt-5.4-nano":{"draws":32,"losses":28,"wins":32},"gpt-5.5":{"draws":11,"losses":5,"wins":4},"gpt-5.6-luna":{"draws":8,"losses":3,"wins":17},"gpt-5.6-sol":{"draws":4,"losses":10,"wins":6},"gpt-5.6-terra":{"draws":11,"losses":9,"wins":6},"inclusionai/ling-3.0-flash":{"draws":2,"losses":2,"wins":0},"meituan/longcat-2.0":{"draws":2,"losses":8,"wins":4},"minimax/minimax-m3":{"draws":5,"losses":5,"wins":8},"mistralai/mistral-medium-3-5":{"draws":2,"losses":5,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":1,"wins":2},"moonshotai/kimi-k3":{"draws":5,"losses":17,"wins":12},"nex-agi/nex-n2-pro":{"draws":9,"losses":8,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":3,"wins":4},"o3":{"draws":6,"losses":7,"wins":7},"openai/gpt-oss-120b":{"draws":10,"losses":9,"wins":5},"qwen/qwen3.7-max":{"draws":2,"losses":6,"wins":6},"qwen/qwen3.7-plus":{"draws":0,"losses":3,"wins":9},"stepfun/step-3.7-flash":{"draws":8,"losses":13,"wins":11},"tencent/hy3-preview":{"draws":7,"losses":5,"wins":4},"thinkingmachines/inkling":{"draws":5,"losses":6,"wins":5},"x-ai/grok-4.5":{"draws":13,"losses":31,"wins":8},"x-ai/grok-build-0.1":{"draws":1,"losses":0,"wins":1},"xiaomi/mimo-v2.5":{"draws":16,"losses":8,"wins":10},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":8,"wins":7},"z-ai/glm-5.2":{"draws":24,"losses":23,"wins":9}},"xiaomi/mimo-v2.5-pro":{"claude-opus-4-5":{"draws":2,"losses":4,"wins":8},"claude-opus-4-8":{"draws":6,"losses":3,"wins":5},"claude-opus-5":{"draws":3,"losses":10,"wins":1},"claude-sonnet-5":{"draws":0,"losses":3,"wins":1},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":4},"deepseek/deepseek-v4-flash":{"draws":8,"losses":9,"wins":7},"deepseek/deepseek-v4-pro":{"draws":2,"losses":3,"wins":5},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":8},"google/gemini-3.5-flash":{"draws":1,"losses":1,"wins":0},"google/gemini-3.5-flash-lite":{"draws":0,"losses":4,"wins":0},"google/gemma-4-31b-it":{"draws":0,"losses":2,"wins":4},"gpt-4.1":{"draws":0,"losses":2,"wins":2},"gpt-5":{"draws":0,"losses":1,"wins":1},"gpt-5.4":{"draws":4,"losses":5,"wins":1},"gpt-5.4-mini":{"draws":12,"losses":10,"wins":4},"gpt-5.4-nano":{"draws":10,"losses":11,"wins":11},"gpt-5.5":{"draws":5,"losses":2,"wins":3},"gpt-5.6-luna":{"draws":5,"losses":0,"wins":1},"gpt-5.6-sol":{"draws":3,"losses":4,"wins":3},"gpt-5.6-terra":{"draws":2,"losses":3,"wins":3},"inclusionai/ling-3.0-flash":{"draws":1,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":0,"losses":0,"wins":4},"minimax/minimax-m3":{"draws":0,"losses":2,"wins":6},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":4},"moonshotai/kimi-k3":{"draws":4,"losses":7,"wins":3},"nex-agi/nex-n2-pro":{"draws":4,"losses":3,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":1,"wins":1},"o3":{"draws":4,"losses":4,"wins":0},"openai/gpt-oss-120b":{"draws":5,"losses":0,"wins":7},"poolside/laguna-s-2.1":{"draws":0,"losses":2,"wins":0},"qwen/qwen3.7-max":{"draws":4,"losses":5,"wins":1},"qwen/qwen3.7-plus":{"draws":4,"losses":0,"wins":6},"stepfun/step-3.7-flash":{"draws":1,"losses":1,"wins":4},"tencent/hy3-preview":{"draws":1,"losses":3,"wins":2},"thinkingmachines/inkling":{"draws":0,"losses":4,"wins":2},"x-ai/grok-4.5":{"draws":1,"losses":13,"wins":4},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":5,"losses":8,"wins":5},"z-ai/glm-5.2":{"draws":9,"losses":9,"wins":0}},"z-ai/glm-5.2":{"claude-fable-5":{"draws":0,"losses":6,"wins":2},"claude-opus-4-5":{"draws":17,"losses":22,"wins":11},"claude-opus-4-8":{"draws":6,"losses":8,"wins":12},"claude-opus-5":{"draws":4,"losses":22,"wins":4},"claude-sonnet-5":{"draws":8,"losses":16,"wins":10},"cohere/north-mini-code":{"draws":5,"losses":1,"wins":0},"deepseek/deepseek-v4-flash":{"draws":14,"losses":25,"wins":23},"deepseek/deepseek-v4-pro":{"draws":0,"losses":6,"wins":6},"google/gemini-3.1-flash-lite":{"draws":2,"losses":3,"wins":5},"google/gemini-3.5-flash":{"draws":3,"losses":8,"wins":3},"google/gemini-3.5-flash-lite":{"draws":1,"losses":5,"wins":6},"google/gemini-3.6-flash":{"draws":2,"losses":5,"wins":1},"google/gemma-4-31b-it":{"draws":1,"losses":4,"wins":3},"gpt-4.1":{"draws":4,"losses":5,"wins":7},"gpt-5":{"draws":3,"losses":12,"wins":11},"gpt-5.4":{"draws":19,"losses":0,"wins":5},"gpt-5.4-mini":{"draws":37,"losses":25,"wins":34},"gpt-5.4-nano":{"draws":22,"losses":37,"wins":43},"gpt-5.5":{"draws":7,"losses":7,"wins":6},"gpt-5.6-luna":{"draws":18,"losses":12,"wins":14},"gpt-5.6-sol":{"draws":11,"losses":15,"wins":10},"gpt-5.6-terra":{"draws":15,"losses":12,"wins":11},"inclusionai/ling-3.0-flash":{"draws":2,"losses":2,"wins":4},"meituan/longcat-2.0":{"draws":3,"losses":3,"wins":4},"minimax/minimax-m3":{"draws":4,"losses":5,"wins":5},"mistralai/mistral-medium-3-5":{"draws":0,"losses":10,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":5,"wins":4},"moonshotai/kimi-k3":{"draws":5,"losses":10,"wins":5},"nex-agi/nex-n2-pro":{"draws":8,"losses":5,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":17,"wins":11},"o3":{"draws":1,"losses":8,"wins":7},"openai/gpt-oss-120b":{"draws":9,"losses":5,"wins":4},"poolside/laguna-s-2.1":{"draws":3,"losses":5,"wins":6},"qwen/qwen3.7-max":{"draws":4,"losses":8,"wins":8},"qwen/qwen3.7-plus":{"draws":7,"losses":7,"wins":6},"stepfun/step-3.7-flash":{"draws":0,"losses":1,"wins":5},"tencent/hy3-preview":{"draws":10,"losses":3,"wins":9},"thinkingmachines/inkling":{"draws":2,"losses":8,"wins":6},"x-ai/grok-4.5":{"draws":7,"losses":15,"wins":10},"x-ai/grok-build-0.1":{"draws":0,"losses":4,"wins":4},"xiaomi/mimo-v2.5":{"draws":23,"losses":15,"wins":24},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":2,"wins":4},"z-ai/glm-5.2":{"draws":32,"losses":26,"wins":28}}}}}