{"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":"2026-07-27T19:45:01Z","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":4.0372}},"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":16.69817},"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":79.83353365197684,"medium":65.57074160938022},"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":"2026-07-27T15:58:59Z","match_totals_all":{"draws":128,"losses":188,"wins":546},"match_totals_tracks":{"highest":{"draws":66,"losses":80,"wins":320},"medium":{"draws":62,"losses":108,"wins":226}},"model_slug":"claude-fable-5","overall":{"max":100.0,"mean":73.4445721362937,"min":50.169539127004974},"per_game":{"GB2-01":62.48880272697796,"GB2-02":73.19703425601392,"GB2-03":69.09760234044293,"GB2-04":100.0,"GB2-05":92.3708669015868,"GB2-06":80.12004893199418,"GB2-07":61.39391405879897,"GB2-08":100.0},"per_game_match_totals_all":{"GB2-01":{"draws":0,"losses":44,"wins":70},"GB2-02":{"draws":57,"losses":12,"wins":51},"GB2-03":{"draws":20,"losses":4,"wins":18},"GB2-04":{"draws":34,"losses":16,"wins":64},"GB2-05":{"draws":0,"losses":32,"wins":86},"GB2-06":{"draws":16,"losses":24,"wins":68},"GB2-07":{"draws":0,"losses":40,"wins":78},"GB2-08":{"draws":1,"losses":16,"wins":111}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":0,"losses":24,"wins":34},"GB2-02":{"draws":27,"losses":3,"wins":30},"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":30,"losses":9,"wins":21},"GB2-04":{"draws":25,"losses":15,"wins":18},"GB2-05":{"draws":0,"losses":24,"wins":30},"GB2-06":{"draws":7,"losses":13,"wins":30},"GB2-07":{"draws":0,"losses":15,"wins":41},"GB2-08":{"draws":0,"losses":12,"wins":50}}},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1614.289805193975,"GB2-02":1665.515391796302,"GB2-03":1640.207188118948,"GB2-04":1821.3947826255776,"GB2-05":1897.678809124274,"GB2-06":1705.5493909205152,"GB2-07":1604.40868111242,"GB2-08":1912.1873848057296},"medium":{"GB2-01":1665.451007353691,"GB2-02":1624.69812777023,"GB2-04":1570.2329284352627,"GB2-05":1563.8549313784958,"GB2-06":1656.6232412385289,"GB2-07":1720.961634672591,"GB2-08":1748.30238195533}},"per_game_tracks":{"highest":{"GB2-01":62.48880272697796,"GB2-02":73.19703425601392,"GB2-03":69.09760234044293,"GB2-04":100.0,"GB2-05":92.3708669015868,"GB2-06":80.12004893199418,"GB2-07":61.39391405879897,"GB2-08":100.0},"medium":{"GB2-01":68.96939634840618,"GB2-02":63.452640140055266,"GB2-04":50.169539127004974,"GB2-05":52.92663955035931,"GB2-06":73.07850759598226,"GB2-07":75.98738578456185,"GB2-08":74.41108271929163}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":83.47120747309498,"medium":63.41793679949243},"reasoning_agg":{"highest":{"max":100.0,"mean":83.47120747309498,"min":61.39391405879897},"medium":{"max":75.98738578456185,"mean":63.41793679949243,"min":50.169539127004974}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Setting not tested"},"score_diagnostics":{"ceiling_score":100.0,"reasoning_variance":20.053270673602547},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":100.0,"expected_score":75.22221340360531,"reliability_score":78.4025722156932,"uncertainty_avg":21.597427784306806,"uncertainty_penalty":-8.248994069489669},"medium":{"ceiling_score":75.98738578456185,"expected_score":80.38372029509208,"reliability_score":77.75082850771997,"uncertainty_avg":22.249171492280027,"uncertainty_penalty":16.965783495599645}}},{"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":4.570124999999999}},"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":33.78345000000001},"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":71.7786962163156,"highest":80.58496839660344,"medium":72.42802335561073,"none":65.67482393469044},"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":"2026-07-27T15:56:29Z","match_totals_all":{"draws":304,"losses":451,"wins":1181},"match_totals_tracks":{"highest":{"draws":40,"losses":100,"wins":380},"medium":{"draws":103,"losses":181,"wins":448},"none":{"draws":161,"losses":170,"wins":353}},"model_slug":"claude-opus-5","overall":{"max":99.01750849232472,"mean":67.55600869152525,"min":43.13791710250739},"per_game":{"GB2-01":64.35576459451039,"GB2-02":78.54184751328685,"GB2-03":99.01750849232472,"GB2-04":73.33281812779559,"GB2-05":86.37300771504712,"GB2-07":98.99816924724276,"GB2-08":63.475663086016624},"per_game_all":{"GB2-01":65.32596068412197,"GB2-02":67.9863088146995,"GB2-03":80.50134150179366,"GB2-04":54.82801440970312,"GB2-05":83.47629189054634,"GB2-07":89.46296304383297,"GB2-08":60.86999316951159},"per_game_match_totals_all":{"GB2-01":{"draws":55,"losses":78,"wins":151},"GB2-02":{"draws":116,"losses":46,"wins":124},"GB2-03":{"draws":15,"losses":49,"wins":180},"GB2-04":{"draws":105,"losses":67,"wins":120},"GB2-05":{"draws":0,"losses":69,"wins":245},"GB2-06":{"draws":13,"losses":7,"wins":36},"GB2-07":{"draws":0,"losses":44,"wins":160},"GB2-08":{"draws":0,"losses":91,"wins":165}},"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":59},"GB2-02":{"draws":47,"losses":17,"wins":38},"GB2-03":{"draws":2,"losses":13,"wins":67},"GB2-04":{"draws":47,"losses":25,"wins":32},"GB2-05":{"draws":0,"losses":28,"wins":88},"GB2-07":{"draws":0,"losses":24,"wins":86},"GB2-08":{"draws":0,"losses":40,"wins":78}},"none":{"GB2-01":{"draws":48,"losses":14,"wins":42},"GB2-02":{"draws":50,"losses":15,"wins":39},"GB2-03":{"draws":12,"losses":30,"wins":40},"GB2-04":{"draws":38,"losses":31,"wins":39},"GB2-05":{"draws":0,"losses":29,"wins":89},"GB2-06":{"draws":13,"losses":7,"wins":36},"GB2-07":{"draws":0,"losses":19,"wins":35},"GB2-08":{"draws":0,"losses":25,"wins":33}}},"per_game_raw_elo_all":{"GB2-01":1642.0240416144632,"GB2-02":1650.104463597365,"GB2-03":1708.91479419204,"GB2-04":1598.6882196718095,"GB2-05":1827.210583172504,"GB2-07":1829.8385052698006,"GB2-08":1665.7712279463783},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1639.1615937053887,"GB2-02":1699.158468705878,"GB2-03":1819.3735501939022,"GB2-04":1696.9563654007216,"GB2-05":1859.1162007965604,"GB2-07":1910.1513048995253,"GB2-08":1689.6876237550243},"medium":{"GB2-01":1622.5515776650714,"GB2-02":1633.82345004235,"GB2-03":1780.1898306547898,"GB2-04":1537.8170890563795,"GB2-05":1798.8199679947602,"GB2-07":1837.285337815342,"GB2-08":1735.7828651797977},"none":{"GB2-01":1664.3589534729288,"GB2-02":1617.3314720438675,"GB2-03":1527.1810017274283,"GB2-04":1561.2912045583273,"GB2-05":1823.6955807261916,"GB2-06":1774.1459218022244,"GB2-07":1742.0788730945349,"GB2-08":1571.8431949043122}},"per_game_tracks":{"highest":{"GB2-01":64.35576459451039,"GB2-02":78.54184751328685,"GB2-03":99.01750849232472,"GB2-04":73.33281812779559,"GB2-05":86.37300771504712,"GB2-07":98.99816924724276,"GB2-08":63.475663086016624},"medium":{"GB2-01":63.04667059518091,"GB2-02":64.61344185255442,"GB2-03":92.54364815769259,"GB2-04":43.13791710250739,"GB2-05":80.55197914748385,"GB2-07":90.82151908302893,"GB2-08":72.280987550827},"none":{"GB2-01":68.57544686267458,"GB2-02":60.80363707825724,"GB2-03":49.94286785536366,"GB2-04":48.01330799880638,"GB2-05":83.50388880910803,"GB2-06":89.13691320039523,"GB2-07":78.56920080122724,"GB2-08":46.853328871691126}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":73.59490781264122,"medium":70.0500817123776,"none":59.02303654955689},"reasoning_agg":{"highest":{"max":99.01750849232472,"mean":73.59490781264122,"min":63.475663086016624},"medium":{"max":92.54364815769259,"mean":70.0500817123776,"min":43.13791710250739},"none":{"max":83.50388880910803,"mean":59.02303654955689,"min":48.01330799880638}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Thinking disabled"},"score_diagnostics":{"ceiling_score":99.01750849232472,"expected_score":83.70050383566715,"reasoning_variance":14.571871263084333,"reliability_score":71.96992457951688,"uncertainty_avg":28.03007542048312,"uncertainty_penalty":16.1444951441419},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":99.01750849232472,"expected_score":78.11525737738678,"reliability_score":65.66311905569697,"uncertainty_avg":34.33688094430304,"uncertainty_penalty":4.520349564745558},"medium":{"ceiling_score":92.54364815769259,"expected_score":89.15228111266161,"reliability_score":74.93279559470454,"uncertainty_avg":25.06720440529545,"uncertainty_penalty":19.102199400284007},"none":{"ceiling_score":83.50388880910803,"expected_score":85.8547263898339,"reliability_score":75.59004947047396,"uncertainty_avg":24.409950529526046,"uncertainty_penalty":26.831689840277008}}},{"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":21.140645},"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":25.878314999999997},"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":57.785527760572016,"highest":71.87937601763771,"medium":48.48149951346338,"none":52.99570775061495},"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":"2026-07-27T15:59:13Z","match_totals_all":{"draws":483,"losses":337,"wins":692},"match_totals_tracks":{"highest":{"draws":101,"losses":87,"wins":298},"medium":{"draws":181,"losses":131,"wins":172},"none":{"draws":201,"losses":119,"wins":222}},"model_slug":"gpt-5-4","overall":{"max":100.0,"mean":57.785527760572016,"min":25.189567064800336},"per_game":{"GB2-01":100.0,"GB2-02":57.273546807227696,"GB2-03":38.82631568621353,"GB2-04":60.3067010884318,"GB2-05":96.57379066170128,"GB2-06":89.6862854041758,"GB2-07":91.89097628140996,"GB2-08":40.47739221194158},"per_game_all":{"GB2-01":86.2798189006943,"GB2-02":38.008913735959496,"GB2-03":41.68585971327056,"GB2-04":45.09168575804907,"GB2-05":74.01402108656715,"GB2-06":84.22034347083279,"GB2-07":60.016624146319224,"GB2-08":32.966955272883524},"per_game_match_totals_all":{"GB2-01":{"draws":28,"losses":21,"wins":139},"GB2-02":{"draws":160,"losses":14,"wins":24},"GB2-03":{"draws":67,"losses":45,"wins":36},"GB2-04":{"draws":116,"losses":28,"wins":50},"GB2-05":{"draws":0,"losses":61,"wins":151},"GB2-06":{"draws":25,"losses":28,"wins":113},"GB2-07":{"draws":0,"losses":73,"wins":125},"GB2-08":{"draws":87,"losses":67,"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":26,"losses":13,"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":39},"GB2-07":{"draws":0,"losses":24,"wins":34},"GB2-08":{"draws":21,"losses":26,"wins":19}},"none":{"GB2-01":{"draws":2,"losses":6,"wins":58},"GB2-02":{"draws":64,"losses":1,"wins":1},"GB2-03":{"draws":29,"losses":8,"wins":13},"GB2-04":{"draws":49,"losses":8,"wins":11},"GB2-05":{"draws":0,"losses":25,"wins":59},"GB2-06":{"draws":6,"losses":15,"wins":37},"GB2-07":{"draws":0,"losses":43,"wins":33},"GB2-08":{"draws":51,"losses":13,"wins":10}}},"per_game_raw_elo_all":{"GB2-01":1796.8672140383114,"GB2-02":1515.783506695615,"GB2-03":1472.9328461674459,"GB2-04":1542.117030700547,"GB2-05":1738.234004999634,"GB2-06":1737.5711311990744,"GB2-07":1592.3487771159262,"GB2-08":1477.7397172629446},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1904.3194643073384,"GB2-02":1597.2143177522778,"GB2-03":1459.0530820785134,"GB2-04":1617.2220685254226,"GB2-05":1933.7094741760584,"GB2-06":1779.224826819665,"GB2-07":1841.7924577346591,"GB2-08":1526.706490224709},"medium":{"GB2-01":1645.4310233167598,"GB2-02":1461.361568758212,"GB2-03":1401.825348329168,"GB2-04":1514.0229127508078,"GB2-05":1528.5904299300091,"GB2-06":1795.322614521401,"GB2-07":1565.920523238979,"GB2-08":1455.9222743715295},"none":{"GB2-01":1840.8511544908365,"GB2-02":1488.7746335763547,"GB2-03":1557.920108094656,"GB2-04":1495.1061108254105,"GB2-05":1752.4021108928348,"GB2-06":1638.165952256158,"GB2-07":1369.3333503741408,"GB2-08":1450.5903871925957}},"per_game_tracks":{"highest":{"GB2-01":100.0,"GB2-02":57.273546807227696,"GB2-03":38.82631568621353,"GB2-04":60.3067010884318,"GB2-05":96.57379066170128,"GB2-06":89.6862854041758,"GB2-07":91.89097628140996,"GB2-08":40.47739221194158},"medium":{"GB2-01":66.72123593215844,"GB2-02":25.189567064800336,"GB2-03":30.14898379651178,"GB2-04":38.977121778303186,"GB2-05":49.31725364553898,"GB2-06":91.83061764137966,"GB2-07":56.25034027872709,"GB2-08":29.41687597028761},"none":{"GB2-01":92.11822076992448,"GB2-02":31.56362733585045,"GB2-03":56.08227965708637,"GB2-04":35.99123440741221,"GB2-05":76.1510189524612,"GB2-06":71.14412736694287,"GB2-07":31.908555878820593,"GB2-08":29.006597636421393}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":71.87937601763771,"medium":48.48149951346338,"none":52.995707750614955},"reasoning_agg":{"highest":{"max":100.0,"mean":71.87937601763771,"min":38.82631568621353},"medium":{"max":91.83061764137966,"mean":48.48149951346338,"min":25.189567064800336},"none":{"max":92.11822076992448,"mean":52.995707750614955,"min":29.006597636421393}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"score_diagnostics":{"ceiling_score":100.0,"expected_score":56.869197963388686,"reasoning_variance":23.397876504174327,"reliability_score":80.82713671038417,"uncertainty_avg":19.172863289615826,"uncertainty_penalty":-0.9163297971833302},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":100.0,"expected_score":64.8270022716312,"reliability_score":79.69850244595662,"uncertainty_avg":20.301497554043387,"uncertainty_penalty":-7.052373746006509},"medium":{"ceiling_score":91.83061764137966,"expected_score":45.99159715363357,"reliability_score":79.83525270950189,"uncertainty_avg":20.164747290498116,"uncertainty_penalty":-2.489902359829813},"none":{"ceiling_score":92.11822076992448,"expected_score":59.78899446490131,"reliability_score":82.94765497569402,"uncertainty_avg":17.05234502430598,"uncertainty_penalty":6.793286714286353}}},{"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":4.11992},"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":1.0694849999999998}},"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":85.663355},"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":56.29728534700427,"highest":65.28432384240854,"medium":57.80705078732788,"none":45.8004814112764},"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":"2026-07-27T15:58:56Z","match_totals_all":{"draws":311,"losses":441,"wins":718},"match_totals_tracks":{"highest":{"draws":59,"losses":138,"wins":293},"medium":{"draws":103,"losses":126,"wins":223},"none":{"draws":149,"losses":177,"wins":202}},"model_slug":"gpt-5-6-sol","overall":{"max":100.0,"mean":56.297285347004276,"min":15.99986870925893},"per_game":{"GB2-01":75.64277085800467,"GB2-02":100.0,"GB2-03":61.14974362057465,"GB2-04":66.43667406598968,"GB2-05":72.56906281561947,"GB2-06":76.11062624621614,"GB2-07":54.36584442360475,"GB2-08":15.99986870925893},"per_game_all":{"GB2-01":63.90860345973533,"GB2-02":59.93839887433928,"GB2-03":55.973497929729,"GB2-04":44.28429527911254,"GB2-05":64.28821040449408,"GB2-06":64.5744117735315,"GB2-07":58.852890409896496,"GB2-08":38.55797464519595},"per_game_match_totals_all":{"GB2-01":{"draws":15,"losses":60,"wins":103},"GB2-02":{"draws":84,"losses":21,"wins":71},"GB2-03":{"draws":49,"losses":43,"wins":68},"GB2-04":{"draws":125,"losses":10,"wins":33},"GB2-05":{"draws":0,"losses":66,"wins":138},"GB2-06":{"draws":16,"losses":83,"wins":95},"GB2-07":{"draws":0,"losses":84,"wins":116},"GB2-08":{"draws":22,"losses":74,"wins":94}},"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":4,"losses":14,"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":27,"losses":11,"wins":22},"GB2-03":{"draws":12,"losses":11,"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":32},"GB2-07":{"draws":0,"losses":25,"wins":33},"GB2-08":{"draws":5,"losses":17,"wins":40}},"none":{"GB2-01":{"draws":15,"losses":19,"wins":32},"GB2-02":{"draws":46,"losses":6,"wins":6},"GB2-03":{"draws":33,"losses":18,"wins":17},"GB2-04":{"draws":49,"losses":4,"wins":3},"GB2-05":{"draws":0,"losses":25,"wins":43},"GB2-06":{"draws":1,"losses":49,"wins":34},"GB2-07":{"draws":0,"losses":31,"wins":33},"GB2-08":{"draws":5,"losses":25,"wins":34}}},"per_game_raw_elo_all":{"GB2-01":1624.8509037177107,"GB2-02":1610.5515683940985,"GB2-03":1556.2116210626298,"GB2-04":1541.5983936582245,"GB2-05":1655.636759727902,"GB2-06":1586.8717828515776,"GB2-07":1583.067090389494,"GB2-08":1516.0189545142075},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1716.2957199694602,"GB2-02":1778.6483184624055,"GB2-03":1590.350902249458,"GB2-04":1653.789369331552,"GB2-05":1723.892992498132,"GB2-06":1676.3558507059174,"GB2-07":1544.1316071761985,"GB2-08":1369.9378527645924},"medium":{"GB2-01":1590.5607673020877,"GB2-02":1552.434703520284,"GB2-03":1581.5282621482136,"GB2-04":1490.518146546648,"GB2-05":1642.6315145680098,"GB2-06":1677.6556396548986,"GB2-07":1613.041766542292,"GB2-08":1669.5691004601476},"none":{"GB2-01":1567.6962238815845,"GB2-02":1500.5716831996058,"GB2-03":1496.7556987902174,"GB2-04":1480.4876650964738,"GB2-05":1600.385772117564,"GB2-06":1406.6038581939165,"GB2-07":1592.027897449992,"GB2-08":1508.549910317883}},"per_game_tracks":{"highest":{"GB2-01":75.64277085800467,"GB2-02":100.0,"GB2-03":61.14974362057465,"GB2-04":66.43667406598968,"GB2-05":72.56906281561947,"GB2-06":76.11062624621614,"GB2-07":54.36584442360475,"GB2-08":15.99986870925893},"medium":{"GB2-01":59.188964919420734,"GB2-02":46.201035877446856,"GB2-03":59.66421699198599,"GB2-04":34.29690331835047,"GB2-05":62.43323967778432,"GB2-06":76.15659509023824,"GB2-07":62.284218510036965,"GB2-08":62.23123191335946},"none":{"GB2-01":56.894074601780616,"GB2-02":33.61416074557098,"GB2-03":47.10653317662637,"GB2-04":32.11930845299747,"GB2-05":57.86232872007845,"GB2-06":41.45601398414009,"GB2-07":59.90860829604776,"GB2-08":37.44282331296946}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":65.28432384240854,"medium":57.80705078732788,"none":45.8004814112764},"reasoning_agg":{"highest":{"max":100.0,"mean":65.28432384240854,"min":15.99986870925893},"medium":{"max":76.15659509023824,"mean":57.80705078732788,"min":34.29690331835047},"none":{"max":59.90860829604776,"mean":45.8004814112764,"min":32.11930845299747}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"score_diagnostics":{"ceiling_score":100.0,"expected_score":55.682152101056346,"reasoning_variance":19.48384243113214,"reliability_score":79.91369178992845,"uncertainty_avg":20.08630821007155,"uncertainty_penalty":-0.6151332459479306},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":100.0,"expected_score":57.107489697312545,"reliability_score":79.74749232499101,"uncertainty_avg":20.252507675008992,"uncertainty_penalty":-8.176834145095995},"medium":{"ceiling_score":76.15659509023824,"expected_score":60.71040748518685,"reliability_score":77.62595775122665,"uncertainty_avg":22.374042248773346,"uncertainty_penalty":2.9033566978589676},"none":{"ceiling_score":59.90860829604776,"expected_score":49.228559120669665,"reliability_score":82.3676252935677,"uncertainty_avg":17.632374706432305,"uncertainty_penalty":3.428077709393264}}},{"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":0.1445437333333333,"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":0.1445437333333333,"mean":0.08597182777777779,"median":0.08538879999999999,"min":0.041110400000000005,"recorded_attempt_count":104,"run_count":64,"total":5.5669699999999995},"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":52.1253411881881,"highest":49.379431746431635,"medium":60.377588250409744,"none":46.61900356772293},"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":"2026-07-27T16:02:13Z","match_totals_all":{"draws":941,"losses":1156,"wins":1859},"match_totals_tracks":{"highest":{"draws":261,"losses":479,"wins":698},"medium":{"draws":354,"losses":419,"wins":755},"none":{"draws":326,"losses":258,"wins":406}},"model_slug":"x-ai-grok-4-5","overall":{"max":85.57962471129208,"mean":52.125341188188095,"min":20.684453538846107},"per_game":{"GB2-01":64.73590439615545,"GB2-02":37.890496423277526,"GB2-03":42.329296821438945,"GB2-04":22.82665639057853,"GB2-05":48.87639190655733,"GB2-06":56.081285429963856,"GB2-07":58.63055697544416,"GB2-08":63.66486562803726},"per_game_all":{"GB2-01":62.694165600436946,"GB2-02":34.75426876229246,"GB2-03":37.83507905726652,"GB2-04":29.035782488596187,"GB2-05":57.18724598939931,"GB2-06":56.382977460172555,"GB2-07":66.98753479982126,"GB2-08":72.12567534751956},"per_game_match_totals_all":{"GB2-01":{"draws":128,"losses":134,"wins":282},"GB2-02":{"draws":274,"losses":68,"wins":72},"GB2-03":{"draws":142,"losses":117,"wins":77},"GB2-04":{"draws":350,"losses":91,"wins":65},"GB2-05":{"draws":0,"losses":189,"wins":303},"GB2-06":{"draws":45,"losses":240,"wins":277},"GB2-07":{"draws":0,"losses":201,"wins":365},"GB2-08":{"draws":2,"losses":116,"wins":418}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":34,"losses":50,"wins":126},"GB2-02":{"draws":79,"losses":32,"wins":37},"GB2-03":{"draws":27,"losses":15,"wins":16},"GB2-04":{"draws":108,"losses":52,"wins":24},"GB2-05":{"draws":0,"losses":68,"wins":80},"GB2-06":{"draws":13,"losses":108,"wins":119},"GB2-07":{"draws":0,"losses":99,"wins":131},"GB2-08":{"draws":0,"losses":55,"wins":165}},"medium":{"GB2-01":{"draws":25,"losses":67,"wins":118},"GB2-02":{"draws":82,"losses":21,"wins":31},"GB2-03":{"draws":72,"losses":40,"wins":48},"GB2-04":{"draws":152,"losses":27,"wins":29},"GB2-05":{"draws":0,"losses":75,"wins":139},"GB2-06":{"draws":22,"losses":81,"wins":101},"GB2-07":{"draws":0,"losses":76,"wins":130},"GB2-08":{"draws":1,"losses":32,"wins":159}},"none":{"GB2-01":{"draws":69,"losses":17,"wins":38},"GB2-02":{"draws":113,"losses":15,"wins":4},"GB2-03":{"draws":43,"losses":62,"wins":13},"GB2-04":{"draws":90,"losses":12,"wins":12},"GB2-05":{"draws":0,"losses":46,"wins":84},"GB2-06":{"draws":10,"losses":51,"wins":57},"GB2-07":{"draws":0,"losses":26,"wins":104},"GB2-08":{"draws":1,"losses":29,"wins":94}}},"per_game_raw_elo_all":{"GB2-01":1622.4969051918226,"GB2-02":1516.372117165378,"GB2-03":1458.5864730309333,"GB2-04":1487.8208034182799,"GB2-05":1618.5115285753907,"GB2-06":1547.6408360453654,"GB2-07":1655.149646139396,"GB2-08":1742.0974619767876},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1646.62225026505,"GB2-02":1532.1302271015347,"GB2-03":1497.3469365962942,"GB2-04":1453.3641057916232,"GB2-05":1540.9682819146449,"GB2-06":1536.2640974459425,"GB2-07":1596.3056410970028,"GB2-08":1693.9837411017909},"medium":{"GB2-01":1634.8861943996365,"GB2-02":1544.4679193719608,"GB2-03":1523.4968144156458,"GB2-04":1505.1670799235726,"GB2-05":1702.336443752434,"GB2-06":1569.0930229588678,"GB2-07":1639.0601903035001,"GB2-08":1819.9291865090927},"none":{"GB2-01":1585.9822709107812,"GB2-02":1472.518205022639,"GB2-03":1354.9156680808603,"GB2-04":1504.9312245396438,"GB2-05":1612.229860059093,"GB2-06":1537.5653877312857,"GB2-07":1730.0831070176853,"GB2-08":1712.3794583194792}},"per_game_tracks":{"highest":{"GB2-01":64.73590439615545,"GB2-02":37.890496423277526,"GB2-03":42.329296821438945,"GB2-04":22.82665639057853,"GB2-05":48.87639190655733,"GB2-06":56.081285429963856,"GB2-07":58.63055697544416,"GB2-08":63.66486562803726},"medium":{"GB2-01":65.72208019034245,"GB2-02":44.82965387274463,"GB2-03":50.491486811514505,"GB2-04":38.01628425017713,"GB2-05":69.855634801012,"GB2-06":62.424425877527234,"GB2-07":66.10151548866789,"GB2-08":85.57962471129208},"none":{"GB2-01":57.62451221481294,"GB2-02":21.54265599085522,"GB2-03":20.684453538846107,"GB2-04":26.264406825032907,"GB2-05":52.829711260628585,"GB2-06":50.643221073026574,"GB2-07":76.23053193535173,"GB2-08":67.13253570322934}},"provider_color":"#9CA3AF","provider_company":"xAI","provider_key":"x-ai","provider_text_color":"#0b1120","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":49.37943174643163,"medium":60.377588250409744,"none":46.61900356772293},"reasoning_agg":{"highest":{"max":64.73590439615545,"mean":49.37943174643163,"min":22.82665639057853},"medium":{"max":85.57962471129208,"mean":60.377588250409744,"min":38.01628425017713},"none":{"max":76.23053193535173,"mean":46.61900356772293,"min":20.684453538846107}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"score_diagnostics":{"ceiling_score":85.57962471129208,"expected_score":52.45566063977649,"reasoning_variance":13.758584682686816,"reliability_score":66.48385291888184,"uncertainty_avg":33.516147081118156,"uncertainty_penalty":0.3303194515883945},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":64.73590439615545,"expected_score":37.96503364199897,"reliability_score":59.25201129144873,"uncertainty_avg":40.74798870855127,"uncertainty_penalty":-11.414398104432657},"medium":{"ceiling_score":85.57962471129208,"expected_score":63.1195067232293,"reliability_score":82.29855745477391,"uncertainty_avg":17.70144254522609,"uncertainty_penalty":2.741918472819556},"none":{"ceiling_score":76.23053193535173,"expected_score":56.282441554101226,"reliability_score":57.90099001042289,"uncertainty_avg":42.09900998957711,"uncertainty_penalty":9.663437986378298}}},{"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":21.885475},"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":3.542855},"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":26.566350000000003},"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":52.99438473749701,"highest":68.15184887212627,"medium":48.09744784101551,"none":42.483436102261635},"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":"2026-07-27T15:58:56Z","match_totals_all":{"draws":495,"losses":337,"wins":509},"match_totals_tracks":{"highest":{"draws":98,"losses":94,"wins":241},"medium":{"draws":153,"losses":144,"wins":157},"none":{"draws":244,"losses":99,"wins":111}},"model_slug":"gpt-5-5","overall":{"max":88.02796582947613,"mean":51.70012612911366,"min":27.049679476012503},"per_game":{"GB2-01":77.04163766987543,"GB2-03":49.27053092873559,"GB2-04":30.921753926830576,"GB2-05":83.82486081338791,"GB2-06":82.20988966457762,"GB2-07":88.02796582947613,"GB2-08":65.76630327200057},"per_game_all":{"GB2-01":60.91295410370185,"GB2-03":47.05052390337801,"GB2-04":31.6112858174841,"GB2-05":67.78821508957408,"GB2-07":65.50336218976439,"GB2-08":45.09996732107964},"per_game_match_totals_all":{"GB2-01":{"draws":119,"losses":28,"wins":55},"GB2-02":{"draws":99,"losses":14,"wins":15},"GB2-03":{"draws":59,"losses":32,"wins":34},"GB2-04":{"draws":130,"losses":38,"wins":26},"GB2-05":{"draws":0,"losses":63,"wins":129},"GB2-06":{"draws":8,"losses":52,"wins":64},"GB2-07":{"draws":0,"losses":62,"wins":124},"GB2-08":{"draws":80,"losses":48,"wins":62}},"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":42,"losses":13,"wins":11},"GB2-05":{"draws":0,"losses":15,"wins":53},"GB2-06":{"draws":8,"losses":20,"wins":38},"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":31,"losses":12,"wins":15},"GB2-03":{"draws":19,"losses":13,"wins":8},"GB2-04":{"draws":40,"losses":13,"wins":9},"GB2-05":{"draws":0,"losses":23,"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":62,"losses":13,"wins":11},"GB2-02":{"draws":68,"losses":2,"wins":0},"GB2-03":{"draws":20,"losses":9,"wins":17},"GB2-04":{"draws":48,"losses":12,"wins":6},"GB2-05":{"draws":0,"losses":25,"wins":39},"GB2-07":{"draws":0,"losses":28,"wins":34},"GB2-08":{"draws":46,"losses":10,"wins":4}}},"per_game_raw_elo_all":{"GB2-01":1599.020756293388,"GB2-03":1509.622399660403,"GB2-04":1474.3319436856373,"GB2-05":1686.9846879360964,"GB2-07":1636.5521310622705,"GB2-08":1558.35496113326},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1726.2827891456054,"GB2-03":1524.6990353724188,"GB2-04":1470.3598482849127,"GB2-05":1822.9563803754577,"GB2-06":1718.0303169897015,"GB2-07":1810.87837198572,"GB2-08":1690.1796710479507},"medium":{"GB2-01":1579.6537688986575,"GB2-02":1535.714251788026,"GB2-03":1470.0062111246496,"GB2-04":1453.9356837685343,"GB2-05":1648.4542713590818,"GB2-06":1450.542154271933,"GB2-07":1638.802982390646,"GB2-08":1541.9180516740412},"none":{"GB2-01":1491.1257108359016,"GB2-02":1501.6155054033272,"GB2-03":1534.1619524841408,"GB2-04":1498.700299003465,"GB2-05":1589.5434120737496,"GB2-07":1459.9750388104458,"GB2-08":1442.9671606777888}},"per_game_tracks":{"highest":{"GB2-01":77.04163766987543,"GB2-03":49.27053092873559,"GB2-04":30.921753926830576,"GB2-05":83.82486081338791,"GB2-06":82.20988966457762,"GB2-07":88.02796582947613,"GB2-08":65.76630327200057},"medium":{"GB2-01":57.905585560065134,"GB2-02":42.00382249149155,"GB2-03":40.192204570731214,"GB2-04":27.3472600456232,"GB2-05":63.11245564094769,"GB2-06":46.151391350129174,"GB2-07":65.58294385391025,"GB2-08":42.483919215225825},"none":{"GB2-01":47.79163908116498,"GB2-02":34.962548767694756,"GB2-03":51.688836210667226,"GB2-04":36.564843479998515,"GB2-05":56.42732881438667,"GB2-07":42.899176885906776,"GB2-08":27.049679476012503}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":65.91430169096594,"medium":48.09744784101551,"none":41.088628855359524},"reasoning_agg":{"highest":{"max":88.02796582947613,"mean":65.91430169096594,"min":30.921753926830576},"medium":{"max":65.58294385391025,"mean":48.09744784101551,"min":27.3472600456232},"none":{"max":56.42732881438667,"mean":41.088628855359524,"min":27.049679476012503}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"score_diagnostics":{"ceiling_score":88.02796582947613,"expected_score":50.71823550735375,"reasoning_variance":24.82567283560642,"reliability_score":79.21122435545541,"uncertainty_avg":20.788775644544582,"uncertainty_penalty":-0.9818906217599164},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":88.02796582947613,"expected_score":59.892074330688665,"reliability_score":79.93351412987363,"uncertainty_avg":20.066485870126364,"uncertainty_penalty":-6.022227360277277},"medium":{"ceiling_score":65.58294385391025,"expected_score":43.854513335347846,"reliability_score":77.54956713687731,"uncertainty_avg":22.450432863122682,"uncertainty_penalty":-4.242934505667662},"none":{"ceiling_score":56.42732881438667,"expected_score":46.06543488616178,"reliability_score":81.46545518934204,"uncertainty_avg":18.53454481065796,"uncertainty_penalty":4.976806030802258}}},{"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":1.4245200000000002},"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":7.107714999999999},"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":47.145709991924356},"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":"2026-07-27T15:58:41Z","match_totals_all":{"draws":174,"losses":146,"wins":180},"match_totals_tracks":{"none":{"draws":174,"losses":146,"wins":180}},"model_slug":"claude-opus-4-5","overall":{"max":59.15070675443215,"mean":47.14570999192436,"min":35.18281284883366},"per_game_match_totals_all":{"GB2-01":{"draws":41,"losses":10,"wins":11},"GB2-02":{"draws":54,"losses":5,"wins":3},"GB2-03":{"draws":37,"losses":9,"wins":8},"GB2-04":{"draws":34,"losses":11,"wins":9},"GB2-05":{"draws":0,"losses":24,"wins":42},"GB2-06":{"draws":2,"losses":35,"wins":27},"GB2-07":{"draws":0,"losses":33,"wins":31},"GB2-08":{"draws":6,"losses":19,"wins":49}},"per_game_match_totals_tracks":{"none":{"GB2-01":{"draws":41,"losses":10,"wins":11},"GB2-02":{"draws":54,"losses":5,"wins":3},"GB2-03":{"draws":37,"losses":9,"wins":8},"GB2-04":{"draws":34,"losses":11,"wins":9},"GB2-05":{"draws":0,"losses":24,"wins":42},"GB2-06":{"draws":2,"losses":35,"wins":27},"GB2-07":{"draws":0,"losses":33,"wins":31},"GB2-08":{"draws":6,"losses":19,"wins":49}}},"per_game_raw_elo_tracks":{"none":{"GB2-01":1440.0631482289907,"GB2-02":1505.4621431048597,"GB2-03":1544.092140040724,"GB2-04":1531.367240999507,"GB2-05":1537.0274446215944,"GB2-06":1471.0980280128524,"GB2-07":1489.8456094590335,"GB2-08":1645.4486548697253}},"per_game_tracks":{"none":{"GB2-01":40.23843353793476,"GB2-02":35.18281284883366,"GB2-03":54.1033903036507,"GB2-04":42.06024334765576,"GB2-05":50.38845226238323,"GB2-06":49.2174811242672,"GB2-07":46.82415975623741,"GB2-08":59.15070675443215}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"none":47.14570999192436},"reasoning_agg":{"none":{"max":59.15070675443215,"mean":47.14570999192436,"min":35.18281284883366}},"reasoning_labels":{"highest":"Extended thinking (legacy shared budget)","medium":"Extended thinking (legacy shared budget)","none":"Thinking field omitted"},"score_diagnostics":{"ceiling_score":59.15070675443215},"score_diagnostics_by_reasoning":{"none":{"ceiling_score":59.15070675443215,"expected_score":56.45038655147627,"reliability_score":80.78967326891069,"uncertainty_avg":19.21032673108931,"uncertainty_penalty":9.304676559551908}}},{"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":0.6220906500000001}},"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":49.706703889348866,"highest":58.041752847231834,"medium":49.334561143165935,"none":38.663748074092574},"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":"2026-07-27T16:06:56Z","match_totals_all":{"draws":767,"losses":535,"wins":742},"match_totals_tracks":{"highest":{"draws":106,"losses":59,"wins":173},"medium":{"draws":389,"losses":268,"wins":389},"none":{"draws":272,"losses":208,"wins":180}},"model_slug":"google-gemini-3-6-flash","overall":{"max":90.24764585966038,"mean":46.94208557765952,"min":22.04868244275925},"per_game":{"GB2-01":38.001139620161496,"GB2-03":35.706944523905,"GB2-04":68.37465172530936,"GB2-05":80.52103910064591,"GB2-06":90.24764585966038,"GB2-08":35.39909625370884},"per_game_all":{"GB2-01":44.6664717478007,"GB2-03":47.76462261815015,"GB2-04":44.132434512258236,"GB2-05":66.87745369017141,"GB2-06":67.64610531645589,"GB2-08":27.153135451256844},"per_game_match_totals_all":{"GB2-01":{"draws":92,"losses":68,"wins":86},"GB2-02":{"draws":200,"losses":8,"wins":0},"GB2-03":{"draws":92,"losses":62,"wins":72},"GB2-04":{"draws":168,"losses":32,"wins":54},"GB2-05":{"draws":0,"losses":97,"wins":185},"GB2-06":{"draws":27,"losses":94,"wins":175},"GB2-07":{"draws":0,"losses":95,"wins":131},"GB2-08":{"draws":188,"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":35,"losses":26,"wins":63},"GB2-02":{"draws":123,"losses":5,"wins":0},"GB2-03":{"draws":37,"losses":30,"wins":37},"GB2-04":{"draws":87,"losses":18,"wins":23},"GB2-05":{"draws":0,"losses":55,"wins":95},"GB2-06":{"draws":14,"losses":40,"wins":78},"GB2-07":{"draws":0,"losses":58,"wins":80},"GB2-08":{"draws":93,"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":1481.961007186649,"GB2-03":1512.2356497142664,"GB2-04":1544.6479083848078,"GB2-05":1684.8912542998216,"GB2-06":1617.275840650309,"GB2-08":1449.3086244277758},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1433.3176275999922,"GB2-03":1443.3679574628934,"GB2-04":1667.9321943610776,"GB2-05":1807.478590078014,"GB2-06":1790.5024736608507,"GB2-08":1506.7738994568635},"medium":{"GB2-01":1585.485564292801,"GB2-02":1476.3566802074506,"GB2-03":1557.9570166952826,"GB2-04":1487.6071390852817,"GB2-05":1708.169873719953,"GB2-06":1700.2585711313377,"GB2-07":1467.6059977114926,"GB2-08":1406.5687072472667},"none":{"GB2-01":1427.0798296671542,"GB2-02":1479.3188858458,"GB2-03":1535.381974984623,"GB2-04":1478.404391708064,"GB2-05":1539.0252991014984,"GB2-06":1361.0664771587387,"GB2-07":1593.8243127331189,"GB2-08":1434.5832665791972}},"per_game_tracks":{"highest":{"GB2-01":38.001139620161496,"GB2-03":35.706944523905,"GB2-04":68.37465172530936,"GB2-05":80.52103910064591,"GB2-06":90.24764585966038,"GB2-08":35.39909625370884},"medium":{"GB2-01":58.99108950548842,"GB2-02":28.41673240515275,"GB2-03":56.26320303032371,"GB2-04":34.207432320938985,"GB2-05":70.6997686167247,"GB2-06":79.84257508312278,"GB2-07":44.20700574081687,"GB2-08":22.04868244275925},"none":{"GB2-01":37.007186117752184,"GB2-02":26.059066298254493,"GB2-03":51.32372030022173,"GB2-04":29.815219490526346,"GB2-05":49.41155335314362,"GB2-06":32.84809500658452,"GB2-07":58.83351636895526,"GB2-08":24.01162765730244}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#f5f9ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":52.82794751572005,"medium":49.33456114316592,"none":38.663748074092574},"reasoning_agg":{"highest":{"max":90.24764585966038,"mean":52.82794751572005,"min":35.39909625370884},"medium":{"max":79.84257508312278,"mean":49.33456114316592,"min":22.04868244275925},"none":{"max":58.83351636895526,"mean":38.663748074092574,"min":24.01162765730244}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Minimal"},"score_diagnostics":{"ceiling_score":90.24764585966038,"expected_score":47.84999489456859,"reasoning_variance":14.164199441627474,"reliability_score":72.04193494142044,"uncertainty_avg":27.95806505857956,"uncertainty_penalty":0.9079093169090697},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":90.24764585966038,"expected_score":49.47862921312579,"reliability_score":67.73692128511578,"uncertainty_avg":32.26307871488422,"uncertainty_penalty":-3.3493183025942557},"medium":{"ceiling_score":79.84257508312278,"expected_score":47.036443653058015,"reliability_score":82.13674317592992,"uncertainty_avg":17.863256824070085,"uncertainty_penalty":-2.298117490107906},"none":{"ceiling_score":58.83351636895526,"expected_score":40.80351815276788,"reliability_score":66.69866793298664,"uncertainty_avg":33.30133206701336,"uncertainty_penalty":2.139770078675305}}},{"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":10.45624},"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":53.13134650196622,"highest":65.790492448475,"medium":45.26724769418371,"none":47.38943024530097},"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":"2026-07-27T16:02:24Z","match_totals_all":{"draws":337,"losses":391,"wins":572},"match_totals_tracks":{"highest":{"draws":59,"losses":123,"wins":240},"medium":{"draws":166,"losses":121,"wins":143},"none":{"draws":112,"losses":147,"wins":189}},"model_slug":"claude-opus-4-8","overall":{"max":77.20302117516688,"mean":46.65832605641348,"min":26.35973023478462},"per_game":{"GB2-01":59.81280359013286,"GB2-02":90.09571894996164,"GB2-04":52.43603009561291,"GB2-05":50.53327801033048,"GB2-06":79.72428872775545,"GB2-07":62.90248060999168,"GB2-08":65.02884715553996},"per_game_all":{"GB2-01":54.151575207533654,"GB2-02":48.42929093176605,"GB2-04":38.13028786436855,"GB2-05":44.72426798075538,"GB2-06":70.58581163967436,"GB2-07":64.64172115988028,"GB2-08":51.25647072978526},"per_game_match_totals_all":{"GB2-01":{"draws":31,"losses":61,"wins":76},"GB2-02":{"draws":115,"losses":13,"wins":40},"GB2-03":{"draws":23,"losses":10,"wins":7},"GB2-04":{"draws":112,"losses":25,"wins":35},"GB2-05":{"draws":0,"losses":99,"wins":91},"GB2-06":{"draws":7,"losses":68,"wins":107},"GB2-07":{"draws":0,"losses":65,"wins":113},"GB2-08":{"draws":49,"losses":50,"wins":103}},"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":41,"losses":3,"wins":2},"GB2-03":{"draws":23,"losses":10,"wins":7},"GB2-04":{"draws":43,"losses":7,"wins":4},"GB2-05":{"draws":0,"losses":28,"wins":32},"GB2-06":{"draws":1,"losses":21,"wins":36},"GB2-07":{"draws":0,"losses":20,"wins":38},"GB2-08":{"draws":49,"losses":9,"wins":4}},"none":{"GB2-01":{"draws":16,"losses":19,"wins":23},"GB2-02":{"draws":54,"losses":7,"wins":3},"GB2-04":{"draws":39,"losses":8,"wins":5},"GB2-05":{"draws":0,"losses":36,"wins":30},"GB2-06":{"draws":3,"losses":31,"wins":34},"GB2-07":{"draws":0,"losses":25,"wins":41},"GB2-08":{"draws":0,"losses":21,"wins":53}}},"per_game_raw_elo_all":{"GB2-01":1550.5927961352047,"GB2-02":1563.8988055687958,"GB2-04":1510.2770842455377,"GB2-05":1489.5007710234395,"GB2-06":1632.9694373086074,"GB2-07":1631.0034343606112,"GB2-08":1596.714212367043},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1593.5380641852346,"GB2-02":1737.1613209336665,"GB2-04":1578.4078028250656,"GB2-05":1539.0151173817317,"GB2-06":1703.484096247477,"GB2-07":1619.730475331812,"GB2-08":1686.1260261745642},"medium":{"GB2-01":1484.8070614799876,"GB2-02":1476.4547971192335,"GB2-03":1460.7826005116174,"GB2-04":1469.453330167729,"GB2-05":1526.9858286719375,"GB2-06":1683.650875040015,"GB2-07":1658.4015620035889,"GB2-08":1446.6514940291925},"none":{"GB2-01":1573.4332627403917,"GB2-02":1478.0802986534875,"GB2-04":1482.9701197438192,"GB2-05":1402.501367016649,"GB2-06":1511.7733406383302,"GB2-07":1614.8782657464328,"GB2-08":1657.365116897373}},"per_game_tracks":{"highest":{"GB2-01":59.81280359013286,"GB2-02":90.09571894996164,"GB2-04":52.43603009561291,"GB2-05":50.53327801033048,"GB2-06":79.72428872775545,"GB2-07":62.90248060999168,"GB2-08":65.02884715553996},"medium":{"GB2-01":45.42169278538346,"GB2-02":26.35973023478462,"GB2-03":38.6391638686108,"GB2-04":29.732078673060073,"GB2-05":48.94334155048709,"GB2-06":77.20302117516688,"GB2-07":68.09254323204925,"GB2-08":27.74641003392749},"none":{"GB2-01":57.22022924708464,"GB2-02":28.832423610551896,"GB2-04":32.22275482443267,"GB2-05":34.69618438144857,"GB2-06":54.83012501610077,"GB2-07":62.93013963759991,"GB2-08":60.99415499988833}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":48.87418004544679,"medium":45.26724769418371,"none":45.83355042960994},"reasoning_agg":{"highest":{"max":50.53327801033048,"mean":48.87418004544679,"min":50.53327801033048},"medium":{"max":77.20302117516688,"mean":45.26724769418371,"min":26.35973023478462},"none":{"max":62.93013963759991,"mean":45.83355042960994,"min":28.832423610551896}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Thinking field omitted"},"score_diagnostics":{"ceiling_score":77.20302117516688,"expected_score":51.24341573254043,"reasoning_variance":3.606932351263083,"reliability_score":79.45733223521039,"uncertainty_avg":20.54266776478961,"uncertainty_penalty":4.585089676126948},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":50.53327801033048,"expected_score":58.295794529289985,"reliability_score":79.74681046695575,"uncertainty_avg":20.253189533044246,"uncertainty_penalty":9.421614483843193},"medium":{"ceiling_score":77.20302117516688,"expected_score":39.938340878061766,"reliability_score":75.70986566299223,"uncertainty_avg":24.290134337007768,"uncertainty_penalty":-5.328906816121943},"none":{"ceiling_score":62.93013963759991,"expected_score":52.01665334533915,"reliability_score":81.48007106035527,"uncertainty_avg":18.51992893964473,"uncertainty_penalty":6.183102915729208}}},{"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":16.779512399999994},"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":44.99651102300968,"highest":45.49729859307633,"medium":41.85198748682493,"none":50.227743592144975},"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":"2026-07-27T16:01:47Z","match_totals_all":{"draws":1077,"losses":868,"wins":1221},"match_totals_tracks":{"highest":{"draws":412,"losses":407,"wins":528},"medium":{"draws":360,"losses":204,"wins":249},"none":{"draws":305,"losses":257,"wins":444}},"model_slug":"moonshotai-kimi-k3","overall":{"max":68.20962819187783,"mean":46.62028157243777,"min":21.27615981022488},"per_game":{"GB2-01":52.45198302770152,"GB2-02":27.32744061084774,"GB2-04":46.17117874326892,"GB2-05":46.80140024106329,"GB2-06":69.79293959997881,"GB2-07":53.42069139868415,"GB2-08":22.515456529989933},"per_game_all":{"GB2-01":51.97809602431108,"GB2-02":24.89404994607338,"GB2-04":37.081740477142475,"GB2-05":48.33804744602324,"GB2-06":68.4242652625414,"GB2-07":49.11342643680305,"GB2-08":35.14595156817308},"per_game_match_totals_all":{"GB2-01":{"draws":183,"losses":122,"wins":165},"GB2-02":{"draws":385,"losses":50,"wins":29},"GB2-03":{"draws":49,"losses":53,"wins":96},"GB2-04":{"draws":230,"losses":90,"wins":125},"GB2-05":{"draws":0,"losses":131,"wins":186},"GB2-06":{"draws":32,"losses":105,"wins":227},"GB2-07":{"draws":0,"losses":223,"wins":275},"GB2-08":{"draws":198,"losses":94,"wins":118}},"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":104,"losses":9,"wins":3},"GB2-03":{"draws":20,"losses":29,"wins":35},"GB2-04":{"draws":78,"losses":29,"wins":20},"GB2-05":{"draws":0,"losses":20,"wins":18},"GB2-06":{"draws":12,"losses":30,"wins":68},"GB2-07":{"draws":0,"losses":44,"wins":64},"GB2-08":{"draws":81,"losses":28,"wins":19}},"none":{"GB2-01":{"draws":67,"losses":22,"wins":35},"GB2-02":{"draws":112,"losses":12,"wins":6},"GB2-03":{"draws":29,"losses":24,"wins":61},"GB2-04":{"draws":75,"losses":20,"wins":25},"GB2-05":{"draws":0,"losses":40,"wins":88},"GB2-06":{"draws":8,"losses":40,"wins":78},"GB2-07":{"draws":0,"losses":70,"wins":62},"GB2-08":{"draws":14,"losses":29,"wins":89}}},"per_game_raw_elo_all":{"GB2-01":1544.7143778156315,"GB2-02":1490.071065269467,"GB2-04":1521.5657824628277,"GB2-05":1562.3110648487861,"GB2-06":1631.3039078810473,"GB2-07":1534.6004927215533,"GB2-08":1511.664841976568},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1546.68828391194,"GB2-02":1487.8761702774934,"GB2-04":1567.0760172985163,"GB2-05":1523.7035184605436,"GB2-06":1645.9657064331486,"GB2-07":1552.293623643294,"GB2-08":1427.93041194247},"medium":{"GB2-01":1521.586354924754,"GB2-02":1490.363891896275,"GB2-03":1536.3650099625975,"GB2-04":1473.5120601317499,"GB2-05":1515.6250464267923,"GB2-06":1629.524073532141,"GB2-07":1573.2842653226814,"GB2-08":1472.7862356855082},"none":{"GB2-01":1565.8684946102,"GB2-02":1491.9731336346329,"GB2-03":1598.3300278167235,"GB2-04":1524.109269958217,"GB2-05":1647.6046296590218,"GB2-06":1618.4219436778521,"GB2-07":1478.2235891986847,"GB2-08":1634.2778783017259}},"per_game_tracks":{"highest":{"GB2-01":52.45198302770152,"GB2-02":27.32744061084774,"GB2-04":46.17117874326892,"GB2-05":46.80140024106329,"GB2-06":69.79293959997881,"GB2-07":53.42069139868415,"GB2-08":22.515456529989933},"medium":{"GB2-01":48.451524507986484,"GB2-02":21.27615981022488,"GB2-03":48.7391225197325,"GB2-04":26.225821636295716,"GB2-05":36.28745751743145,"GB2-06":68.20962819187783,"GB2-07":55.41621180403329,"GB2-08":30.20997390701733},"none":{"GB2-01":55.03078053724524,"GB2-02":26.07854941714752,"GB2-03":61.45308478035796,"GB2-04":38.848221051862794,"GB2-05":61.925284579574985,"GB2-06":67.27022799576758,"GB2-07":38.50337610769172,"GB2-08":52.712424267511985}},"provider_color":"#7C3AED","provider_company":"Moonshot","provider_key":"moonshotai","provider_text_color":"#faf5ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":47.668751755366614,"medium":41.96434936980171,"none":50.22774359214498},"reasoning_agg":{"highest":{"max":53.42069139868415,"mean":47.668751755366614,"min":46.17117874326892},"medium":{"max":68.20962819187783,"mean":41.96434936980171,"min":21.27615981022488},"none":{"max":67.27022799576758,"mean":50.22774359214498,"min":26.07854941714752}},"reasoning_labels":{"highest":"Max","medium":"High","none":"Low"},"score_diagnostics":{"ceiling_score":68.20962819187783,"expected_score":46.01135796669401,"reasoning_variance":8.263394222343273,"reliability_score":58.41081074856402,"uncertainty_avg":41.58918925143598,"uncertainty_penalty":-0.6089236057437617},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":53.42069139868415,"expected_score":35.236436642733864,"reliability_score":61.71989076530139,"uncertainty_avg":38.28010923469861,"uncertainty_penalty":-12.43231511263275},"medium":{"ceiling_score":68.20962819187783,"expected_score":41.99433256413192,"reliability_score":52.8314927041495,"uncertainty_avg":47.1685072958505,"uncertainty_penalty":0.02998319433021379},"none":{"ceiling_score":67.27022799576758,"expected_score":64.89837709355848,"reliability_score":60.14961291699917,"uncertainty_avg":39.85038708300083,"uncertainty_penalty":14.670633501413498}}},{"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":65.32801249999999},"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":1.33952},"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":0.6063374999999999}},"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":46.58354697462011,"highest":54.919234658332655,"medium":42.35164383250624,"none":42.47976243302143},"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":"2026-07-27T16:02:13Z","match_totals_all":{"draws":521,"losses":452,"wins":501},"match_totals_tracks":{"highest":{"draws":97,"losses":169,"wins":230},"medium":{"draws":189,"losses":121,"wins":134},"none":{"draws":235,"losses":162,"wins":137}},"model_slug":"gpt-5-6-terra","overall":{"max":72.0322843616957,"mean":46.583546974620106,"min":27.543654388822937},"per_game":{"GB2-01":44.20979035442635,"GB2-02":45.45287871885732,"GB2-03":53.67575600395128,"GB2-04":48.412604814752626,"GB2-05":60.024239354593,"GB2-06":71.69384651100232,"GB2-07":72.0322843616957,"GB2-08":43.85247714738262},"per_game_all":{"GB2-01":49.66776096793791,"GB2-02":34.77992719131261,"GB2-03":48.895878203186506,"GB2-04":42.83631276375874,"GB2-05":55.94463347151781,"GB2-06":52.810104418407356,"GB2-07":52.36895353197446,"GB2-08":35.36480524886549},"per_game_match_totals_all":{"GB2-01":{"draws":53,"losses":65,"wins":56},"GB2-02":{"draws":152,"losses":15,"wins":15},"GB2-03":{"draws":59,"losses":42,"wins":37},"GB2-04":{"draws":149,"losses":18,"wins":31},"GB2-05":{"draws":0,"losses":79,"wins":113},"GB2-06":{"draws":10,"losses":90,"wins":106},"GB2-07":{"draws":0,"losses":89,"wins":99},"GB2-08":{"draws":98,"losses":54,"wins":44}},"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":26,"wins":42},"GB2-08":{"draws":10,"losses":31,"wins":27}},"medium":{"GB2-01":{"draws":20,"losses":18,"wins":18},"GB2-02":{"draws":52,"losses":2,"wins":0},"GB2-03":{"draws":24,"losses":8,"wins":6},"GB2-04":{"draws":51,"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":29},"GB2-08":{"draws":33,"losses":14,"wins":13}},"none":{"GB2-01":{"draws":21,"losses":24,"wins":19},"GB2-02":{"draws":63,"losses":3,"wins":2},"GB2-03":{"draws":24,"losses":21,"wins":13},"GB2-04":{"draws":71,"losses":1,"wins":4},"GB2-05":{"draws":0,"losses":26,"wins":38},"GB2-06":{"draws":1,"losses":42,"wins":29},"GB2-07":{"draws":0,"losses":36,"wins":28},"GB2-08":{"draws":55,"losses":9,"wins":4}}},"per_game_raw_elo_all":{"GB2-01":1514.967150413977,"GB2-02":1504.4809688975013,"GB2-03":1518.2704797363804,"GB2-04":1530.420019796081,"GB2-05":1585.452481631685,"GB2-06":1496.7215254694765,"GB2-07":1533.783323635212,"GB2-08":1494.6777207966704},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1474.4008078994289,"GB2-02":1549.3008269640052,"GB2-03":1548.6158310169712,"GB2-04":1561.4093381266223,"GB2-05":1618.9193174279271,"GB2-06":1635.2207187307338,"GB2-07":1685.24753254842,"GB2-08":1548.5237946011143},"medium":{"GB2-01":1501.322471283357,"GB2-02":1487.5622315860544,"GB2-03":1503.8716525415657,"GB2-04":1509.8215591763649,"GB2-05":1552.729583417106,"GB2-06":1498.4965294796054,"GB2-07":1421.3527923761658,"GB2-08":1492.409453460546},"none":{"GB2-01":1569.1781720591457,"GB2-02":1476.5798481424442,"GB2-03":1502.323955650604,"GB2-04":1520.0291620852558,"GB2-05":1584.708544050022,"GB2-06":1356.4473281980904,"GB2-07":1494.7496459810498,"GB2-08":1443.099914328351}},"per_game_tracks":{"highest":{"GB2-01":44.20979035442635,"GB2-02":45.45287871885732,"GB2-03":53.67575600395128,"GB2-04":48.412604814752626,"GB2-05":60.024239354593,"GB2-06":71.69384651100232,"GB2-07":72.0322843616957,"GB2-08":43.85247714738262},"medium":{"GB2-01":47.80453019713377,"GB2-02":30.06424289135372,"GB2-03":45.62802340349199,"GB2-04":38.630719839920246,"GB2-05":51.946312445904134,"GB2-06":52.41858338546655,"GB2-07":37.622454286388646,"GB2-08":34.69828421039091},"none":{"GB2-01":56.98896235225361,"GB2-02":28.82265996372679,"GB2-03":47.38385520211626,"GB2-04":41.465613636603344,"GB2-05":55.863348614056285,"GB2-06":34.31788335875319,"GB2-07":47.45212194783904,"GB2-08":27.543654388822937}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":54.919234658332655,"medium":42.35164383250624,"none":42.47976243302143},"reasoning_agg":{"highest":{"max":72.0322843616957,"mean":54.919234658332655,"min":43.85247714738262},"medium":{"max":52.41858338546655,"mean":42.35164383250624,"min":30.06424289135372},"none":{"max":56.98896235225361,"mean":42.47976243302143,"min":27.543654388822937}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"score_diagnostics":{"ceiling_score":72.0322843616957,"expected_score":41.923895834864524,"reasoning_variance":12.567590825826414,"reliability_score":79.88055092631483,"uncertainty_avg":20.11944907368517,"uncertainty_penalty":-4.6596511397555815},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":72.0322843616957,"expected_score":42.63470155126256,"reliability_score":80.04808230694482,"uncertainty_avg":19.951917693055183,"uncertainty_penalty":-12.284533107070096},"medium":{"ceiling_score":52.41858338546655,"expected_score":38.44741433123528,"reliability_score":76.72272950798444,"uncertainty_avg":23.277270492015568,"uncertainty_penalty":-3.9042295012709616},"none":{"ceiling_score":56.98896235225361,"expected_score":44.68957162209572,"reliability_score":82.87084096401524,"uncertainty_avg":17.12915903598476,"uncertainty_penalty":2.209809189074292}}},{"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":41.533353004955416,"medium":52.23257256057505},"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":"2026-07-27T16:02:24Z","match_totals_all":{"draws":276,"losses":244,"wins":306},"match_totals_tracks":{"highest":{"draws":113,"losses":132,"wins":123},"medium":{"draws":163,"losses":112,"wins":183}},"model_slug":"google-gemini-3-5-flash","overall":{"max":89.30637072728769,"mean":45.441856340894674,"min":18.014153696699164},"per_game":{"GB2-03":45.0058977081419,"GB2-04":18.637247385879313,"GB2-05":44.11609569421241,"GB2-06":68.09932142027597,"GB2-07":55.327402124523715,"GB2-08":18.014153696699164},"per_game_match_totals_all":{"GB2-01":{"draws":0,"losses":9,"wins":47},"GB2-02":{"draws":47,"losses":2,"wins":7},"GB2-03":{"draws":49,"losses":15,"wins":30},"GB2-04":{"draws":49,"losses":36,"wins":25},"GB2-05":{"draws":0,"losses":71,"wins":67},"GB2-06":{"draws":20,"losses":28,"wins":68},"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":31,"wins":33},"GB2-06":{"draws":8,"losses":19,"wins":37},"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":47,"losses":2,"wins":7},"GB2-03":{"draws":14,"losses":13,"wins":23},"GB2-04":{"draws":33,"losses":8,"wins":13},"GB2-05":{"draws":0,"losses":40,"wins":34},"GB2-06":{"draws":12,"losses":9,"wins":31},"GB2-07":{"draws":0,"losses":26,"wins":28},"GB2-08":{"draws":57,"losses":5,"wins":0}}},"per_game_raw_elo_tracks":{"highest":{"GB2-03":1520.4987104220186,"GB2-04":1434.6129486635432,"GB2-05":1504.9038956193685,"GB2-06":1633.2514891902983,"GB2-07":1574.584014782258,"GB2-08":1399.1765488406536},"medium":{"GB2-01":1823.1594383472432,"GB2-02":1497.501056091277,"GB2-03":1585.7951447614212,"GB2-04":1537.8145480172825,"GB2-05":1471.8580015094933,"GB2-06":1734.2297854950075,"GB2-07":1477.2974094270803,"GB2-08":1399.4738925482284}},"per_game_tracks":{"highest":{"GB2-03":45.0058977081419,"GB2-04":18.637247385879313,"GB2-05":44.11609569421241,"GB2-06":68.09932142027597,"GB2-07":55.327402124523715,"GB2-08":18.014153696699164},"medium":{"GB2-01":89.30637072728769,"GB2-02":32.664876400707286,"GB2-03":60.77578508926699,"GB2-04":43.34401724523379,"GB2-05":43.09912275717949,"GB2-06":83.55834325082338,"GB2-07":44.66391737325167,"GB2-08":20.44814764085012}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#f5f9ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":38.6511401212143,"medium":52.23257256057504},"reasoning_agg":{"highest":{"max":68.09932142027597,"mean":38.6511401212143,"min":18.014153696699164},"medium":{"max":89.30637072728769,"mean":52.23257256057504,"min":20.44814764085012}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Setting not tested"},"score_diagnostics":{"ceiling_score":89.30637072728769,"reasoning_variance":13.581432439360746},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":68.09932142027597,"expected_score":30.377716180715414,"reliability_score":53.437145451826716,"uncertainty_avg":46.562854548173284,"uncertainty_penalty":-8.273423940498883},"medium":{"ceiling_score":89.30637072728769,"expected_score":54.93811870451392,"reliability_score":77.91042498390856,"uncertainty_avg":22.089575016091448,"uncertainty_penalty":2.705546143938875}}},{"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":0.7288237500000001},"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":41.85260378513726,"none":46.070153276495105},"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":"2026-07-27T16:01:47Z","match_totals_all":{"draws":325,"losses":279,"wins":282},"match_totals_tracks":{"medium":{"draws":162,"losses":137,"wins":141},"none":{"draws":163,"losses":142,"wins":141}},"model_slug":"qwen-qwen3-7-max","overall":{"max":80.99600365638999,"mean":42.51804778866547,"min":29.188858982099404},"per_game_match_totals_all":{"GB2-01":{"draws":45,"losses":43,"wins":46},"GB2-02":{"draws":109,"losses":3,"wins":6},"GB2-03":{"draws":43,"losses":7,"wins":4},"GB2-04":{"draws":33,"losses":10,"wins":9},"GB2-05":{"draws":0,"losses":68,"wins":60},"GB2-06":{"draws":9,"losses":67,"wins":52},"GB2-07":{"draws":0,"losses":44,"wins":92},"GB2-08":{"draws":86,"losses":37,"wins":13}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":24,"losses":25,"wins":15},"GB2-02":{"draws":59,"losses":2,"wins":3},"GB2-04":{"draws":33,"losses":10,"wins":9},"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":21,"losses":18,"wins":31},"GB2-02":{"draws":50,"losses":1,"wins":3},"GB2-03":{"draws":43,"losses":7,"wins":4},"GB2-05":{"draws":0,"losses":36,"wins":32},"GB2-06":{"draws":0,"losses":36,"wins":20},"GB2-07":{"draws":0,"losses":22,"wins":46},"GB2-08":{"draws":49,"losses":22,"wins":5}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1412.8200847740486,"GB2-02":1499.9783044216706,"GB2-04":1506.5128329594559,"GB2-05":1530.4398301501867,"GB2-06":1518.7647648288262,"GB2-07":1667.7266168626888,"GB2-08":1479.3879047496516},"none":{"GB2-01":1586.388491274526,"GB2-02":1502.383120170803,"GB2-03":1440.381307433771,"GB2-05":1535.2272824362703,"GB2-06":1341.8150715027673,"GB2-07":1755.2492100095503,"GB2-08":1456.1357275132184}},"per_game_tracks":{"medium":{"GB2-01":34.23244384036473,"GB2-02":29.188858982099404,"GB2-04":32.49114002888361,"GB2-05":46.887127379709426,"GB2-06":53.406674111573565,"GB2-07":67.28650528900698,"GB2-08":29.475476864323102},"none":{"GB2-01":59.484582777796334,"GB2-02":33.60246582139271,"GB2-03":36.64090722117748,"GB2-05":50.261687320285,"GB2-06":31.547572564793132,"GB2-07":80.99600365638999,"GB2-08":29.95785357363107}},"provider_color":"#FF6A00","provider_company":"Alibaba","provider_key":"qwen","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":40.47850789231176,"none":44.557587685019186},"reasoning_agg":{"medium":{"max":67.28650528900698,"mean":40.47850789231176,"min":29.188858982099404},"none":{"max":80.99600365638999,"mean":44.557587685019186,"min":29.95785357363107}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"score_diagnostics":{"ceiling_score":80.99600365638999,"reasoning_variance":4.079079792707425},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":67.28650528900698,"expected_score":43.40998730540572,"reliability_score":55.41730716242453,"uncertainty_avg":44.58269283757547,"uncertainty_penalty":2.9314794130939603},"none":{"ceiling_score":80.99600365638999,"expected_score":45.36495769960243,"reliability_score":81.21116934697409,"uncertainty_avg":18.78883065302592,"uncertainty_penalty":0.8073700145832419}}},{"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":42.15278157179898,"medium":43.07706583204088},"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":"2026-07-27T16:02:24Z","match_totals_all":{"draws":311,"losses":310,"wins":316},"match_totals_tracks":{"highest":{"draws":168,"losses":174,"wins":183},"medium":{"draws":143,"losses":136,"wins":133}},"model_slug":"gpt-5","overall":{"max":62.786908880400794,"mean":41.90777511519566,"min":24.57930679395035},"per_game":{"GB2-01":44.5724430344671,"GB2-02":27.542272343102017,"GB2-03":39.7702372055603,"GB2-04":28.996130934586745,"GB2-05":56.44226639021666,"GB2-06":62.786908880400794,"GB2-07":52.53268699210788,"GB2-08":24.57930679395035},"per_game_match_totals_all":{"GB2-01":{"draws":26,"losses":56,"wins":42},"GB2-02":{"draws":50,"losses":10,"wins":4},"GB2-03":{"draws":43,"losses":28,"wins":16},"GB2-04":{"draws":87,"losses":15,"wins":20},"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":93,"losses":26,"wins":17}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":9,"losses":31,"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":44,"losses":15,"wins":9}},"medium":{"GB2-01":{"draws":17,"losses":25,"wins":14},"GB2-03":{"draws":26,"losses":11,"wins":5},"GB2-04":{"draws":44,"losses":8,"wins":16},"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":1491.2237959131999,"GB2-02":1493.57787505147,"GB2-03":1487.6707577765233,"GB2-04":1487.450385706255,"GB2-05":1604.9630027424323,"GB2-06":1590.9904173149403,"GB2-07":1546.8649438145444,"GB2-08":1444.7730988237663},"medium":{"GB2-01":1358.9198897376532,"GB2-03":1434.6445964503675,"GB2-04":1551.1716734247516,"GB2-05":1570.3013243910782,"GB2-06":1499.5581163462753,"GB2-07":1570.8705167678413,"GB2-08":1438.5140773232674}},"per_game_tracks":{"highest":{"GB2-01":44.5724430344671,"GB2-02":27.542272343102017,"GB2-03":39.7702372055603,"GB2-04":28.996130934586745,"GB2-05":56.44226639021666,"GB2-06":62.786908880400794,"GB2-07":52.53268699210788,"GB2-08":24.57930679395035},"medium":{"GB2-01":29.44129093251917,"GB2-03":34.485660760472555,"GB2-04":47.15488856869603,"GB2-05":53.89561753299053,"GB2-06":52.43282213007789,"GB2-07":57.29494455453205,"GB2-08":26.83423634499792}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":42.15278157179898,"medium":41.66276865859235},"reasoning_agg":{"highest":{"max":62.786908880400794,"mean":42.15278157179898,"min":24.57930679395035},"medium":{"max":57.29494455453205,"mean":41.66276865859235,"min":26.83423634499792}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Setting not tested"},"score_diagnostics":{"ceiling_score":62.786908880400794,"reasoning_variance":0.490012913206634},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":62.786908880400794,"expected_score":30.033116684044785,"reliability_score":56.20026462140017,"uncertainty_avg":43.79973537859983,"uncertainty_penalty":-12.119664887754197},"medium":{"ceiling_score":57.29494455453205,"expected_score":41.77371742811262,"reliability_score":78.54129713996964,"uncertainty_avg":21.458702860030353,"uncertainty_penalty":0.11094876952027022}}},{"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":4.168735999999999},"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":42.344260318525365,"highest":45.05500396335154,"medium":39.868348593847124,"none":41.73044836931285},"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":"2026-07-27T16:02:21Z","match_totals_all":{"draws":477,"losses":453,"wins":462},"match_totals_tracks":{"highest":{"draws":195,"losses":219,"wins":212},"medium":{"draws":144,"losses":134,"wins":148},"none":{"draws":138,"losses":100,"wins":102}},"model_slug":"claude-sonnet-5","overall":{"max":59.06172320072071,"mean":41.78161722772243,"min":25.620538806917818},"per_game":{"GB2-01":59.06172320072071,"GB2-02":39.748923171140326,"GB2-03":41.63731750642038,"GB2-04":43.2849917916824,"GB2-05":52.35911215449047,"GB2-06":55.76800622889098,"GB2-07":37.12643857527608,"GB2-08":31.45351907819096},"per_game_all":{"GB2-01":51.88688642825243,"GB2-02":32.00540381021478,"GB2-04":38.698287197265984,"GB2-05":46.042982612200056,"GB2-06":53.20555463389977,"GB2-07":46.36701703131005,"GB2-08":28.203690516534493},"per_game_match_totals_all":{"GB2-01":{"draws":35,"losses":54,"wins":95},"GB2-02":{"draws":126,"losses":16,"wins":8},"GB2-03":{"draws":59,"losses":59,"wins":44},"GB2-04":{"draws":111,"losses":17,"wins":24},"GB2-05":{"draws":0,"losses":92,"wins":94},"GB2-06":{"draws":15,"losses":87,"wins":94},"GB2-07":{"draws":0,"losses":89,"wins":87},"GB2-08":{"draws":131,"losses":39,"wins":16}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":15,"losses":19,"wins":44},"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":41},"GB2-07":{"draws":0,"losses":39,"wins":27},"GB2-08":{"draws":42,"losses":28,"wins":10}},"medium":{"GB2-01":{"draws":8,"losses":26,"wins":28},"GB2-02":{"draws":52,"losses":3,"wins":1},"GB2-04":{"draws":36,"losses":7,"wins":9},"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":32,"losses":2,"wins":4},"GB2-05":{"draws":0,"losses":27,"wins":21},"GB2-06":{"draws":2,"losses":22,"wins":20},"GB2-07":{"draws":0,"losses":20,"wins":24},"GB2-08":{"draws":44,"losses":2,"wins":0}}},"per_game_raw_elo_all":{"GB2-01":1531.674637809985,"GB2-02":1498.4286500417686,"GB2-04":1517.010582236181,"GB2-05":1501.947773437476,"GB2-06":1501.812770572628,"GB2-07":1489.1163627145736,"GB2-08":1450.5472586804742},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1580.6415648788145,"GB2-02":1527.1746719119114,"GB2-03":1477.8677869593967,"GB2-04":1533.9773873174586,"GB2-05":1550.6378956784858,"GB2-06":1514.0458901456975,"GB2-07":1413.3656681646023,"GB2-08":1464.6642579295235},"medium":{"GB2-01":1452.0417343596705,"GB2-02":1489.0475371244402,"GB2-04":1492.460996966201,"GB2-05":1521.6286930837043,"GB2-06":1477.208213223521,"GB2-07":1489.3871953975538,"GB2-08":1442.873384161387},"none":{"GB2-01":1562.340614191469,"GB2-02":1479.0637410889549,"GB2-03":1485.2660520172667,"GB2-04":1524.5933624248837,"GB2-05":1433.5767315502376,"GB2-06":1514.184208348665,"GB2-07":1564.596224581565,"GB2-08":1444.104133950512}},"per_game_tracks":{"highest":{"GB2-01":59.06172320072071,"GB2-02":39.748923171140326,"GB2-03":41.63731750642038,"GB2-04":43.2849917916824,"GB2-05":52.35911215449047,"GB2-06":55.76800622889098,"GB2-07":37.12643857527608,"GB2-08":31.45351907819096},"medium":{"GB2-01":41.78310808513646,"GB2-02":30.6467494525862,"GB2-04":34.11255787082396,"GB2-05":48.414031779727786,"GB2-06":50.22582047612717,"GB2-07":46.86100001987165,"GB2-08":27.035172472656587},"none":{"GB2-01":54.81582799890011,"GB2-02":25.620538806917818,"GB2-03":42.495274622791904,"GB2-04":38.697311929291594,"GB2-05":37.35580390238191,"GB2-06":53.62283719668116,"GB2-07":55.113612498782416,"GB2-08":26.12237999875593}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":45.05500396335153,"medium":38.55939935050291,"none":41.73044836931286},"reasoning_agg":{"highest":{"max":59.06172320072071,"mean":45.05500396335153,"min":31.45351907819096},"medium":{"max":50.22582047612717,"mean":38.55939935050291,"min":27.035172472656587},"none":{"max":55.113612498782416,"mean":41.73044836931286,"min":25.620538806917818}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Thinking disabled"},"score_diagnostics":{"ceiling_score":59.06172320072071,"expected_score":37.26607331270736,"reasoning_variance":6.495604612848624,"reliability_score":77.6730744252369,"uncertainty_avg":22.326925574763088,"uncertainty_penalty":-4.515543915015066},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":59.06172320072071,"expected_score":29.174481747182412,"reliability_score":82.43576909618726,"uncertainty_avg":17.564230903812742,"uncertainty_penalty":-15.880522216169119},"medium":{"ceiling_score":50.22582047612717,"expected_score":35.81059502593853,"reliability_score":80.00840768788224,"uncertainty_avg":19.991592312117763,"uncertainty_penalty":-2.748804324564375},"none":{"ceiling_score":55.113612498782416,"expected_score":46.32643046607348,"reliability_score":67.72998804560895,"uncertainty_avg":32.27001195439105,"uncertainty_penalty":4.595982096760622}}},{"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":1.35999},"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":45.553045919928635,"highest":45.06171397988977,"medium":44.151619765977394,"none":37.5280618812843},"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":"2026-07-27T15:54:23Z","match_totals_all":{"draws":214,"losses":370,"wins":400},"match_totals_tracks":{"highest":{"draws":12,"losses":136,"wins":142},"medium":{"draws":99,"losses":132,"wins":135},"none":{"draws":103,"losses":102,"wins":123}},"model_slug":"o3","overall":{"max":86.61766309589059,"mean":41.225829250873645,"min":18.13272808568275},"per_game":{"GB2-05":43.73585500348754,"GB2-06":49.03659155745648,"GB2-07":36.12527583054917,"GB2-08":51.34913352806587},"per_game_all":{"GB2-05":43.86587040535153,"GB2-06":64.32686704432193,"GB2-07":40.938969851290885,"GB2-08":33.0804763787502},"per_game_match_totals_all":{"GB2-01":{"draws":17,"losses":39,"wins":44},"GB2-02":{"draws":34,"losses":1,"wins":1},"GB2-03":{"draws":21,"losses":11,"wins":4},"GB2-04":{"draws":62,"losses":16,"wins":10},"GB2-05":{"draws":0,"losses":85,"wins":105},"GB2-06":{"draws":21,"losses":55,"wins":90},"GB2-07":{"draws":0,"losses":100,"wins":86},"GB2-08":{"draws":59,"losses":63,"wins":60}},"per_game_match_totals_tracks":{"highest":{"GB2-05":{"draws":0,"losses":39,"wins":39},"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":10,"losses":18,"wins":18},"GB2-02":{"draws":34,"losses":1,"wins":1},"GB2-03":{"draws":21,"losses":11,"wins":4},"GB2-04":{"draws":18,"losses":9,"wins":7},"GB2-05":{"draws":0,"losses":14,"wins":30},"GB2-06":{"draws":1,"losses":4,"wins":31},"GB2-07":{"draws":0,"losses":30,"wins":24},"GB2-08":{"draws":19,"losses":15,"wins":8}}},"per_game_raw_elo_all":{"GB2-05":1518.2806712772617,"GB2-06":1596.1324115003838,"GB2-07":1465.4050623598785,"GB2-08":1517.562833653703},"per_game_raw_elo_tracks":{"highest":{"GB2-05":1495.1170634631212,"GB2-06":1486.8121397572054,"GB2-07":1424.6260556799098,"GB2-08":1613.734946206889},"medium":{"GB2-01":1522.6714120111717,"GB2-04":1459.8799045162689,"GB2-05":1502.312238039986,"GB2-06":1533.5732183679058,"GB2-07":1539.179287904116,"GB2-08":1458.1375092603982},"none":{"GB2-01":1468.7292262906526,"GB2-02":1477.5847832126149,"GB2-03":1463.2608906471414,"GB2-04":1475.8102858634056,"GB2-05":1557.412712328678,"GB2-06":1768.0118763760397,"GB2-07":1432.4098434956095,"GB2-08":1480.816045493821}},"per_game_tracks":{"highest":{"GB2-05":43.73585500348754,"GB2-06":49.03659155745648,"GB2-07":36.12527583054917,"GB2-08":51.34913352806587},"medium":{"GB2-01":50.4344292839315,"GB2-04":27.82583876113024,"GB2-05":46.42219609913933,"GB2-06":57.32634647961873,"GB2-07":53.14134044954261,"GB2-08":29.75956752250197},"none":{"GB2-01":42.909739239921585,"GB2-02":24.85962983613944,"GB2-03":24.440225048579066,"GB2-04":28.274656356852365,"GB2-05":41.43956011342773,"GB2-06":86.61766309589059,"GB2-07":33.55029327378088,"GB2-08":18.13272808568275}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":45.06171397988976,"medium":41.087711891446865,"none":37.5280618812843},"reasoning_agg":{"highest":{"max":51.34913352806587,"mean":45.06171397988976,"min":36.12527583054917},"medium":{"max":57.32634647961873,"mean":41.087711891446865,"min":27.82583876113024},"none":{"max":86.61766309589059,"mean":37.5280618812843,"min":18.13272808568275}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"score_diagnostics":{"ceiling_score":86.61766309589059,"expected_score":45.75565771015015,"reasoning_variance":7.533652098605458,"reliability_score":61.401620731142984,"uncertainty_avg":38.598379268857016,"uncertainty_penalty":4.529828459276509},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":51.34913352806587,"expected_score":34.542957958067305,"reliability_score":61.39793233456503,"uncertainty_avg":38.60206766543497,"uncertainty_penalty":-10.518756021822455},"medium":{"ceiling_score":57.32634647961873,"expected_score":40.58474031584029,"reliability_score":80.05776192087703,"uncertainty_avg":19.942238079122973,"uncertainty_penalty":-0.5029715756065727},"none":{"ceiling_score":86.61766309589059,"expected_score":45.361657352927516,"reliability_score":48.095130975830195,"uncertainty_avg":51.904869024169805,"uncertainty_penalty":7.833595471643214}}},{"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":0.19953128278324997,"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":0.19953128278324997,"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":43.11836226723412,"highest":44.97800115820529,"medium":44.3261421410315,"none":40.05094350246561},"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":1029,"losses":1025,"wins":1025},"match_totals_tracks":{"highest":{"draws":428,"losses":392,"wins":377},"medium":{"draws":259,"losses":198,"wins":237},"none":{"draws":342,"losses":435,"wins":411}},"model_slug":"z-ai-glm-5-2","overall":{"max":70.22812208032087,"mean":40.83054720506445,"min":23.923663197046043},"per_game":{"GB2-01":47.62917908688148,"GB2-02":29.39591170776535,"GB2-03":44.7143796127683,"GB2-04":31.86936940191663,"GB2-05":48.517867682604326,"GB2-06":69.153570024744,"GB2-07":57.31929094075836,"GB2-08":31.224440808203862},"per_game_all":{"GB2-01":44.489731852739794,"GB2-02":26.444900610229734,"GB2-03":40.70930073815723,"GB2-04":33.28116003685984,"GB2-05":48.04881824335674,"GB2-06":60.93043966797634,"GB2-07":57.80317499095987,"GB2-08":33.23937199759349},"per_game_match_totals_all":{"GB2-01":{"draws":129,"losses":136,"wins":131},"GB2-02":{"draws":287,"losses":29,"wins":13},"GB2-03":{"draws":105,"losses":63,"wins":50},"GB2-04":{"draws":231,"losses":71,"wins":60},"GB2-05":{"draws":0,"losses":256,"wins":242},"GB2-06":{"draws":32,"losses":135,"wins":141},"GB2-07":{"draws":0,"losses":210,"wins":280},"GB2-08":{"draws":245,"losses":125,"wins":108}},"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":37,"losses":25,"wins":30},"GB2-02":{"draws":38,"losses":2,"wins":0},"GB2-03":{"draws":19,"losses":6,"wins":5},"GB2-04":{"draws":37,"losses":20,"wins":17},"GB2-05":{"draws":0,"losses":44,"wins":52},"GB2-06":{"draws":13,"losses":27,"wins":46},"GB2-07":{"draws":0,"losses":55,"wins":81},"GB2-08":{"draws":115,"losses":19,"wins":6}},"none":{"GB2-01":{"draws":24,"losses":83,"wins":77},"GB2-02":{"draws":103,"losses":8,"wins":3},"GB2-03":{"draws":48,"losses":26,"wins":18},"GB2-04":{"draws":112,"losses":23,"wins":23},"GB2-05":{"draws":0,"losses":102,"wins":90},"GB2-06":{"draws":13,"losses":91,"wins":64},"GB2-07":{"draws":0,"losses":63,"wins":77},"GB2-08":{"draws":42,"losses":39,"wins":59}}},"per_game_raw_elo_all":{"GB2-01":1478.6247252761461,"GB2-02":1477.959345178706,"GB2-03":1477.316381805419,"GB2-04":1492.719262305338,"GB2-05":1522.0311899997614,"GB2-06":1567.831330943427,"GB2-07":1580.6425330262207,"GB2-08":1486.7078904867137},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1498.216784303636,"GB2-02":1482.7873247436503,"GB2-03":1491.5728005893707,"GB2-04":1476.4789629339475,"GB2-05":1519.623822330184,"GB2-06":1625.082997776762,"GB2-07":1569.4603703334396,"GB2-08":1467.680872206851},"medium":{"GB2-01":1458.7618017769018,"GB2-02":1470.374121179378,"GB2-03":1484.357755308563,"GB2-04":1493.2693853856194,"GB2-05":1591.472525230101,"GB2-06":1639.527767943735,"GB2-07":1618.0640499121846,"GB2-08":1453.8942718475291},"none":{"GB2-01":1478.8955897479009,"GB2-02":1480.716589613089,"GB2-03":1456.0185895183233,"GB2-04":1508.409438596447,"GB2-05":1454.9972224389992,"GB2-06":1438.883227109784,"GB2-07":1554.4031788330378,"GB2-08":1538.5485274057612}},"per_game_tracks":{"highest":{"GB2-01":47.62917908688148,"GB2-02":29.39591170776535,"GB2-03":44.7143796127683,"GB2-04":31.86936940191663,"GB2-05":48.517867682604326,"GB2-06":69.153570024744,"GB2-07":57.31929094075836,"GB2-08":31.224440808203862},"medium":{"GB2-01":41.62441000493686,"GB2-02":23.923663197046043,"GB2-03":41.03053983455878,"GB2-04":32.263089858934286,"GB2-05":55.77411458095119,"GB2-06":70.22812208032087,"GB2-07":62.066265662847066,"GB2-08":27.698931908656842},"none":{"GB2-01":44.215606466401034,"GB2-02":26.01512692587781,"GB2-03":36.38298276714462,"GB2-04":35.711020849728605,"GB2-05":39.8544724665147,"GB2-06":43.40962689886413,"GB2-07":54.02396836927419,"GB2-08":40.79474327591976}},"provider_color":"#2563EB","provider_company":"Zhipu","provider_key":"z-ai","provider_text_color":"#f8fbff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":38.11455597169624,"medium":44.32614214103149,"none":40.05094350246561},"reasoning_agg":{"highest":{"max":57.31929094075836,"mean":38.11455597169624,"min":29.39591170776535},"medium":{"max":70.22812208032087,"mean":44.32614214103149,"min":23.923663197046043},"none":{"max":54.02396836927419,"mean":40.05094350246561,"min":26.01512692587781}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Reasoning disabled"},"score_diagnostics":{"ceiling_score":70.22812208032087,"expected_score":38.48569207993292,"reasoning_variance":6.2115861693352485,"reliability_score":71.32357192745393,"uncertainty_avg":28.676428072546074,"uncertainty_penalty":-2.344855125131531},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":57.31929094075836,"expected_score":29.81569442055959,"reliability_score":79.96124781069804,"uncertainty_avg":20.038752189301967,"uncertainty_penalty":-8.29886155113665},"medium":{"ceiling_score":70.22812208032087,"expected_score":41.481882530134456,"reliability_score":66.89058681204891,"uncertainty_avg":33.10941318795109,"uncertainty_penalty":-2.8442596108970335},"none":{"ceiling_score":54.02396836927419,"expected_score":44.1594992891047,"reliability_score":67.11888115961483,"uncertainty_avg":32.88111884038516,"uncertainty_penalty":4.108555786639094}}},{"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":0.7872815620000002},"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":45.85533896437726,"none":40.04782157796235},"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":"2026-07-27T15:54:21Z","match_totals_all":{"draws":249,"losses":305,"wins":304},"match_totals_tracks":{"highest":{"draws":90,"losses":144,"wins":150},"none":{"draws":159,"losses":161,"wins":154}},"model_slug":"deepseek-deepseek-v4-pro","overall":{"max":76.6585459712308,"mean":40.70309058567017,"min":20.61584059577335},"per_game":{"GB2-01":45.66102087130642,"GB2-04":23.27152769675579,"GB2-05":76.6585459712308,"GB2-06":42.10102860564115,"GB2-07":60.13352254421294,"GB2-08":27.30638809711645},"per_game_match_totals_all":{"GB2-01":{"draws":40,"losses":52,"wins":54},"GB2-02":{"draws":51,"losses":2,"wins":1},"GB2-03":{"draws":15,"losses":30,"wins":9},"GB2-04":{"draws":22,"losses":19,"wins":7},"GB2-05":{"draws":0,"losses":71,"wins":87},"GB2-06":{"draws":8,"losses":46,"wins":68},"GB2-07":{"draws":0,"losses":67,"wins":69},"GB2-08":{"draws":113,"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":28,"losses":30,"wins":26},"GB2-02":{"draws":51,"losses":2,"wins":1},"GB2-03":{"draws":15,"losses":30,"wins":9},"GB2-05":{"draws":0,"losses":48,"wins":38},"GB2-06":{"draws":6,"losses":12,"wins":42},"GB2-07":{"draws":0,"losses":31,"wins":35},"GB2-08":{"draws":59,"losses":8,"wins":3}}},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1482.114031725191,"GB2-04":1440.214332474687,"GB2-05":1760.1833865422625,"GB2-06":1418.4552403692137,"GB2-07":1591.641725509094,"GB2-08":1440.883097011328},"none":{"GB2-01":1490.425377493292,"GB2-02":1493.1855742024472,"GB2-03":1345.207385463267,"GB2-05":1403.244405392198,"GB2-06":1674.832336171311,"GB2-07":1443.3127110418286,"GB2-08":1445.9523521591466}},"per_game_tracks":{"highest":{"GB2-01":45.66102087130642,"GB2-04":23.27152769675579,"GB2-05":76.6585459712308,"GB2-06":42.10102860564115,"GB2-07":60.13352254421294,"GB2-08":27.30638809711645},"none":{"GB2-01":47.636647445449704,"GB2-02":31.406715690809293,"GB2-03":20.61584059577335,"GB2-05":35.48079904046824,"GB2-06":76.1429991599217,"GB2-07":40.96115933902756,"GB2-08":28.090589774286613}},"provider_color":"#4C8BF5","provider_company":"DeepSeek","provider_key":"deepseek","provider_text_color":"#f6f9ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":42.67320125602331,"none":38.73297991531701},"reasoning_agg":{"highest":{"max":76.6585459712308,"mean":42.67320125602331,"min":23.27152769675579},"none":{"max":76.1429991599217,"mean":38.73297991531701,"min":20.61584059577335}},"reasoning_labels":{"highest":"XHigh","medium":"Setting not tested","none":"Reasoning disabled"},"score_diagnostics":{"ceiling_score":76.6585459712308,"reasoning_variance":3.9402213407063016},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":76.6585459712308,"expected_score":31.383786366296647,"reliability_score":81.31408858070593,"uncertainty_avg":18.685911419294076,"uncertainty_penalty":-11.289414889726665},"none":{"ceiling_score":76.1429991599217,"expected_score":34.09188075910752,"reliability_score":82.73279160807208,"uncertainty_avg":17.267208391927923,"uncertainty_penalty":-4.641099156209492}}},{"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":28.806541000000003},"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":29.297331000000007},"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":40.3080362215951,"highest":50.41505589263369,"medium":46.919757117419735,"none":23.58929565473188},"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":"2026-07-27T15:57:30Z","match_totals_all":{"draws":542,"losses":502,"wins":379},"match_totals_tracks":{"highest":{"draws":132,"losses":155,"wins":185},"medium":{"draws":206,"losses":127,"wins":129},"none":{"draws":204,"losses":220,"wins":65}},"model_slug":"gpt-5-6-luna","overall":{"max":76.4748305783871,"mean":40.3080362215951,"min":0.0},"per_game":{"GB2-01":66.15810496914253,"GB2-02":28.146372762679754,"GB2-03":30.63120574976151,"GB2-04":39.29062220793382,"GB2-05":55.00415603353663,"GB2-06":76.4748305783871,"GB2-07":63.912194201697034,"GB2-08":43.70296063793118},"per_game_all":{"GB2-01":53.57498059599849,"GB2-02":29.967341591742827,"GB2-03":38.88301503807237,"GB2-04":38.126904990441425,"GB2-05":36.13439835410838,"GB2-06":50.312141692263054,"GB2-07":41.91747355768148,"GB2-08":33.54803395245279},"per_game_match_totals_all":{"GB2-01":{"draws":28,"losses":76,"wins":79},"GB2-02":{"draws":178,"losses":6,"wins":0},"GB2-03":{"draws":68,"losses":37,"wins":27},"GB2-04":{"draws":142,"losses":29,"wins":21},"GB2-05":{"draws":0,"losses":117,"wins":65},"GB2-06":{"draws":19,"losses":85,"wins":66},"GB2-07":{"draws":0,"losses":110,"wins":80},"GB2-08":{"draws":107,"losses":42,"wins":41}},"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":29,"wins":32}},"medium":{"GB2-01":{"draws":8,"losses":23,"wins":31},"GB2-02":{"draws":52,"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":40,"wins":32},"GB2-08":{"draws":49,"losses":6,"wins":7}},"none":{"GB2-01":{"draws":20,"losses":35,"wins":12},"GB2-02":{"draws":62,"losses":0,"wins":0},"GB2-03":{"draws":19,"losses":13,"wins":14},"GB2-04":{"draws":50,"losses":13,"wins":7},"GB2-05":{"draws":0,"losses":57,"wins":5},"GB2-06":{"draws":0,"losses":46,"wins":10},"GB2-07":{"draws":0,"losses":49,"wins":15},"GB2-08":{"draws":53,"losses":7,"wins":2}}},"per_game_raw_elo_all":{"GB2-01":1544.0357820658955,"GB2-02":1484.157261287686,"GB2-03":1459.4818431667393,"GB2-04":1507.3711912900553,"GB2-05":1417.029398619609,"GB2-06":1482.3812811747819,"GB2-07":1452.0353309906986,"GB2-08":1483.645327683532},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1644.604801686931,"GB2-02":1473.0639451591423,"GB2-03":1409.099303746516,"GB2-04":1514.736546987583,"GB2-05":1576.596774461676,"GB2-06":1679.089981134785,"GB2-07":1627.6157786139568,"GB2-08":1548.27072293001},"medium":{"GB2-01":1633.9498843243437,"GB2-02":1491.189585591546,"GB2-03":1488.4273983408475,"GB2-04":1512.8853854171534,"GB2-05":1567.9046996706184,"GB2-06":1593.8608666300522,"GB2-07":1496.630215711361,"GB2-08":1463.521515251263},"none":{"GB2-01":1353.552660186412,"GB2-02":1488.2182531123694,"GB2-03":1480.9188274128549,"GB2-04":1494.4916414654292,"GB2-05":1106.586721726533,"GB2-06":1174.1929957595082,"GB2-07":1231.8599986467784,"GB2-08":1439.1437448693234}},"per_game_tracks":{"highest":{"GB2-01":66.15810496914253,"GB2-02":28.146372762679754,"GB2-03":30.63120574976151,"GB2-04":39.29062220793382,"GB2-05":55.00415603353663,"GB2-06":76.4748305783871,"GB2-07":63.912194201697034,"GB2-08":43.70296063793118},"medium":{"GB2-01":65.24070868286577,"GB2-02":30.68951048376554,"GB2-03":43.29390245547429,"GB2-04":39.08519776719661,"GB2-05":53.39903902878851,"GB2-06":65.24239570415726,"GB2-07":48.05114074851961,"GB2-08":30.356162068590265},"none":{"GB2-01":29.32612813598716,"GB2-02":31.0661415287832,"GB2-03":42.723936908981315,"GB2-04":36.004894996193826,"GB2-05":0.0,"GB2-06":9.219198794244829,"GB2-07":13.7890857228278,"GB2-08":26.58497915083693}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":50.415055892633696,"medium":46.919757117419735,"none":23.589295654731878},"reasoning_agg":{"highest":{"max":76.4748305783871,"mean":50.415055892633696,"min":28.146372762679754},"medium":{"max":65.24239570415726,"mean":46.919757117419735,"min":30.356162068590265},"none":{"max":42.723936908981315,"mean":23.589295654731878,"min":0.0}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"score_diagnostics":{"ceiling_score":76.4748305783871,"expected_score":33.83958526202075,"reasoning_variance":26.825760237901818,"reliability_score":78.89824272268544,"uncertainty_avg":21.101757277314565,"uncertainty_penalty":-6.468450959574355},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":76.4748305783871,"expected_score":36.71213785262377,"reliability_score":78.80924333408828,"uncertainty_avg":21.19075666591172,"uncertainty_penalty":-13.702918040009926},"medium":{"ceiling_score":65.24239570415726,"expected_score":45.0902065771607,"reliability_score":77.90194815524217,"uncertainty_avg":22.098051844757826,"uncertainty_penalty":-1.829550540259035},"none":{"ceiling_score":42.723936908981315,"expected_score":19.71641135627776,"reliability_score":79.98353667872584,"uncertainty_avg":20.016463321274152,"uncertainty_penalty":-3.8728842984541174}}},{"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":43.10999191243746,"none":41.81697003012698},"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":"2026-07-27T16:02:00Z","match_totals_all":{"draws":199,"losses":307,"wins":280},"match_totals_tracks":{"medium":{"draws":86,"losses":156,"wins":136},"none":{"draws":113,"losses":151,"wins":144}},"model_slug":"xiaomi-mimo-v2-5-pro","overall":{"max":67.54305795364324,"mean":40.17723329403148,"min":25.340296080038364},"per_game_match_totals_all":{"GB2-01":{"draws":30,"losses":48,"wins":46},"GB2-02":{"draws":56,"losses":4,"wins":4},"GB2-03":{"draws":31,"losses":9,"wins":10},"GB2-04":{"draws":22,"losses":19,"wins":17},"GB2-05":{"draws":0,"losses":87,"wins":63},"GB2-06":{"draws":2,"losses":71,"wins":65},"GB2-07":{"draws":0,"losses":63,"wins":73},"GB2-08":{"draws":58,"losses":6,"wins":2}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":4,"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":33,"wins":31},"GB2-07":{"draws":0,"losses":41,"wins":35},"GB2-08":{"draws":58,"losses":6,"wins":2}},"none":{"GB2-01":{"draws":26,"losses":30,"wins":24},"GB2-02":{"draws":56,"losses":4,"wins":4},"GB2-03":{"draws":31,"losses":9,"wins":10},"GB2-05":{"draws":0,"losses":48,"wins":34},"GB2-06":{"draws":0,"losses":38,"wins":34},"GB2-07":{"draws":0,"losses":22,"wins":38}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1616.385247984007,"GB2-04":1518.9868494776583,"GB2-05":1408.96843152589,"GB2-06":1559.7759859246476,"GB2-07":1482.253043117009,"GB2-08":1449.324273248414},"none":{"GB2-01":1431.0064719759512,"GB2-02":1477.3293696473902,"GB2-03":1453.2674122393996,"GB2-05":1349.7941697138317,"GB2-06":1453.7533405191086,"GB2-07":1653.249574240341}},"per_game_tracks":{"medium":{"GB2-01":61.78504534403884,"GB2-04":35.78712902503984,"GB2-05":33.2543519338834,"GB2-06":58.498007875599185,"GB2-07":43.995121216025154,"GB2-08":25.340296080038364},"none":{"GB2-01":39.837923897204504,"GB2-02":28.65315269754207,"GB2-03":38.461208791388664,"GB2-05":29.12678637185235,"GB2-06":47.279690469131054,"GB2-07":67.54305795364324}},"provider_color":"#FF6900","provider_company":"Xiaomi","provider_key":"xiaomi","provider_text_color":"#fff7f1","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":40.11836794956651,"none":40.23609863849646},"reasoning_agg":{"medium":{"max":61.78504534403884,"mean":40.11836794956651,"min":25.340296080038364},"none":{"max":67.54305795364324,"mean":40.23609863849646,"min":28.65315269754207}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"score_diagnostics":{"ceiling_score":67.54305795364324,"reasoning_variance":0.11773068892994587},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":61.78504534403884,"expected_score":46.8000300778265,"reliability_score":60.05377318909919,"uncertainty_avg":39.94622681090081,"uncertainty_penalty":6.681662128259987},"none":{"ceiling_score":67.54305795364324,"expected_score":39.25725312867161,"reliability_score":82.91532156484688,"uncertainty_avg":17.084678435153123,"uncertainty_penalty":-0.9788455098248505}}},{"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":0.29749325,"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":5.7973514999999995},"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":39.354631107915054,"highest":45.42224026511567,"medium":42.08117047359361,"none":33.806669222950596},"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":"2026-07-27T16:06:56Z","match_totals_all":{"draws":1334,"losses":1268,"wins":1081},"match_totals_tracks":{"highest":{"draws":207,"losses":271,"wins":290},"medium":{"draws":496,"losses":448,"wins":407},"none":{"draws":631,"losses":549,"wins":384}},"model_slug":"gpt-5-4-mini","overall":{"max":66.08919562986975,"mean":39.98893967882885,"min":21.486420364689437},"per_game":{"GB2-01":52.16535532101704,"GB2-02":28.939619265532322,"GB2-04":31.510166457816872,"GB2-05":46.232953795131394,"GB2-06":58.3837110637506,"GB2-07":66.08919562986975,"GB2-08":34.63468032269175},"per_game_all":{"GB2-01":44.23992587128248,"GB2-02":30.609105068117874,"GB2-04":36.66861683710209,"GB2-05":37.66297899768979,"GB2-06":52.58597067386847,"GB2-07":44.72059176417546,"GB2-08":28.9952285431692},"per_game_match_totals_all":{"GB2-01":{"draws":108,"losses":202,"wins":164},"GB2-02":{"draws":424,"losses":22,"wins":10},"GB2-03":{"draws":173,"losses":51,"wins":68},"GB2-04":{"draws":294,"losses":53,"wins":77},"GB2-05":{"draws":0,"losses":287,"wins":233},"GB2-06":{"draws":23,"losses":212,"wins":223},"GB2-07":{"draws":0,"losses":288,"wins":225},"GB2-08":{"draws":312,"losses":153,"wins":81}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":6,"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":69},"GB2-06":{"draws":8,"losses":55,"wins":57},"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":151,"losses":10,"wins":3},"GB2-03":{"draws":77,"losses":28,"wins":31},"GB2-04":{"draws":119,"losses":18,"wins":41},"GB2-05":{"draws":0,"losses":95,"wins":77},"GB2-06":{"draws":5,"losses":52,"wins":67},"GB2-07":{"draws":0,"losses":106,"wins":89},"GB2-08":{"draws":112,"losses":51,"wins":25}},"none":{"GB2-01":{"draws":70,"losses":95,"wins":55},"GB2-02":{"draws":168,"losses":4,"wins":4},"GB2-03":{"draws":96,"losses":23,"wins":37},"GB2-04":{"draws":139,"losses":23,"wins":28},"GB2-05":{"draws":0,"losses":115,"wins":87},"GB2-06":{"draws":10,"losses":105,"wins":99},"GB2-07":{"draws":0,"losses":132,"wins":60},"GB2-08":{"draws":148,"losses":52,"wins":14}}},"per_game_raw_elo_all":{"GB2-01":1469.8067712963887,"GB2-02":1488.438883769483,"GB2-04":1501.918349206073,"GB2-05":1428.2900141996242,"GB2-06":1496.548102098275,"GB2-07":1473.4628737760895,"GB2-08":1452.4770912715096},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1533.3730974136329,"GB2-02":1481.01344851071,"GB2-04":1477.4284617057842,"GB2-05":1499.29536649102,"GB2-06":1541.531656885091,"GB2-07":1640.6855421123205,"GB2-08":1487.812720862631},"medium":{"GB2-01":1468.206308236593,"GB2-02":1485.6343566374824,"GB2-03":1514.2563755535427,"GB2-04":1550.5090589843633,"GB2-05":1422.8007026347743,"GB2-06":1542.4551680393024,"GB2-07":1487.7194140114843,"GB2-08":1439.4570082099108},"none":{"GB2-01":1407.8409082389398,"GB2-02":1498.668846160256,"GB2-03":1523.103686313155,"GB2-04":1477.8175269280712,"GB2-05":1362.7739734730787,"GB2-06":1405.6574813704308,"GB2-07":1291.983665204464,"GB2-08":1430.161544741987}},"per_game_tracks":{"highest":{"GB2-01":52.16535532101704,"GB2-02":28.939619265532322,"GB2-04":31.510166457816872,"GB2-05":46.232953795131394,"GB2-06":58.3837110637506,"GB2-07":66.08919562986975,"GB2-08":34.63468032269175},"medium":{"GB2-01":43.96692548864581,"GB2-02":29.662876822386636,"GB2-03":48.22471380142931,"GB2-04":46.31882962012266,"GB2-05":36.65467092606256,"GB2-06":58.57756631923615,"GB2-07":46.586159297967185,"GB2-08":26.657621512898544},"none":{"GB2-01":36.58749680418459,"GB2-02":33.22481911643467,"GB2-03":50.38643236051798,"GB2-04":32.17685443336674,"GB2-05":30.101312271875415,"GB2-06":40.796634638618634,"GB2-07":21.486420364689437,"GB2-08":25.69338379391731}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":46.85603201539518,"medium":39.304117798140794,"none":33.80666922295059},"reasoning_agg":{"highest":{"max":66.08919562986975,"mean":46.85603201539518,"min":28.939619265532322},"medium":{"max":48.22471380142931,"mean":39.304117798140794,"min":26.657621512898544},"none":{"max":50.38643236051798,"mean":33.80666922295059,"min":21.486420364689437}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"score_diagnostics":{"ceiling_score":66.08919562986975,"expected_score":33.21263656768273,"reasoning_variance":13.04936279244459,"reliability_score":81.24832297839609,"uncertainty_avg":18.751677021603914,"uncertainty_penalty":-6.77630311114612},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":66.08919562986975,"expected_score":31.059334050187342,"reliability_score":81.01374471046655,"uncertainty_avg":18.98625528953345,"uncertainty_penalty":-15.796697965207837},"medium":{"ceiling_score":48.22471380142931,"expected_score":39.66522396272845,"reliability_score":78.64293494497834,"uncertainty_avg":21.357065055021668,"uncertainty_penalty":0.3611061645876532},"none":{"ceiling_score":50.38643236051798,"expected_score":32.84048977403437,"reliability_score":81.86612652561948,"uncertainty_avg":18.13387347438053,"uncertainty_penalty":-0.9661794489162219}}},{"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":0.030659259999999997}},"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":33.48506928946015,"none":41.57626413313103},"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":"2026-07-27T15:51:17Z","match_totals_all":{"draws":478,"losses":407,"wins":353},"match_totals_tracks":{"medium":{"draws":223,"losses":140,"wins":93},"none":{"draws":255,"losses":267,"wins":260}},"model_slug":"poolside-laguna-s-2-1","overall":{"max":58.47714496936588,"mean":37.91561209107624,"min":23.58388507203711},"per_game_match_totals_all":{"GB2-01":{"draws":36,"losses":72,"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":118},"GB2-06":{"draws":4,"losses":58,"wins":42},"GB2-07":{"draws":0,"losses":67,"wins":67},"GB2-08":{"draws":191,"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":55,"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":80},"GB2-06":{"draws":2,"losses":33,"wins":29},"GB2-07":{"draws":0,"losses":67,"wins":67},"GB2-08":{"draws":119,"losses":23,"wins":4}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1527.954612695839,"GB2-02":1487.3621960045764,"GB2-03":1466.5254254199208,"GB2-04":1430.5662249585166,"GB2-05":1460.5662528868663,"GB2-06":1336.1063201840943,"GB2-08":1447.9991933165616},"none":{"GB2-01":1579.2591240187812,"GB2-02":1477.5865175875335,"GB2-03":1473.6623509478843,"GB2-05":1552.8298949184382,"GB2-06":1345.579754559503,"GB2-07":1540.5834431296867,"GB2-08":1415.85097822939}},"per_game_tracks":{"medium":{"GB2-01":50.015291423254,"GB2-02":27.97926320645363,"GB2-03":40.239662184794696,"GB2-04":20.58250517714516,"GB2-05":39.968487196864096,"GB2-06":29.523236321771144,"GB2-08":26.087039515938308},"none":{"GB2-01":58.47714496936588,"GB2-02":28.71454218394329,"GB2-03":41.985067425141104,"GB2-05":52.31323520003257,"GB2-06":32.49761345604342,"GB2-07":53.462360625353874,"GB2-08":23.58388507203711}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":31.604546286081508,"none":44.226677896070974},"reasoning_agg":{"medium":{"max":40.239662184794696,"mean":31.604546286081508,"min":26.087039515938308},"none":{"max":58.47714496936588,"mean":44.226677896070974,"min":23.58388507203711}},"reasoning_labels":{"highest":"Setting not tested","medium":"Enabled","none":"None"},"score_diagnostics":{"ceiling_score":58.47714496936588,"reasoning_variance":12.622131609989466},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":40.239662184794696,"expected_score":21.330550225574427,"reliability_score":66.72878950597988,"uncertainty_avg":33.27121049402013,"uncertainty_penalty":-10.27399606050708},"none":{"ceiling_score":58.47714496936588,"expected_score":38.38666820183113,"reliability_score":81.95666694529703,"uncertainty_avg":18.043333054702963,"uncertainty_penalty":-5.840009694239846}}},{"display_name":"GPT 4.1","economics":{"none":37.70475670619771},"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":"2026-07-27T15:59:10Z","match_totals_all":{"draws":102,"losses":132,"wins":108},"match_totals_tracks":{"none":{"draws":102,"losses":132,"wins":108}},"model_slug":"gpt-4-1","overall":{"max":56.36684029870736,"mean":37.70475670619771,"min":22.30259680139711},"per_game_match_totals_all":{"GB2-01":{"draws":1,"losses":24,"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":29,"wins":19},"GB2-06":{"draws":8,"losses":16,"wins":20},"GB2-07":{"draws":0,"losses":20,"wins":26},"GB2-08":{"draws":29,"losses":14,"wins":7}},"per_game_match_totals_tracks":{"none":{"GB2-01":{"draws":1,"losses":24,"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":29,"wins":19},"GB2-06":{"draws":8,"losses":16,"wins":20},"GB2-07":{"draws":0,"losses":20,"wins":26},"GB2-08":{"draws":29,"losses":14,"wins":7}}},"per_game_raw_elo_tracks":{"none":{"GB2-01":1573.0858652952545,"GB2-02":1462.3741079493293,"GB2-03":1528.356600835827,"GB2-04":1459.143974925331,"GB2-05":1339.63995352344,"GB2-06":1506.0471700351973,"GB2-07":1507.3262272831655,"GB2-08":1417.0774072462827}},"per_game_tracks":{"none":{"GB2-01":56.36684029870736,"GB2-02":22.69204681390362,"GB2-03":48.43891826866166,"GB2-04":24.956096391857447,"GB2-05":26.39821775319491,"GB2-06":52.53892965023924,"GB2-07":47.944407671620375,"GB2-08":22.30259680139711}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"none":37.70475670619771},"reasoning_agg":{"none":{"max":56.36684029870736,"mean":37.70475670619771,"min":22.30259680139711}},"reasoning_labels":{"highest":"Setting not tested","medium":"Setting not tested","none":"None"},"score_diagnostics":{"ceiling_score":56.36684029870736},"score_diagnostics_by_reasoning":{"none":{"ceiling_score":56.36684029870736,"expected_score":38.31186539400975,"reliability_score":67.41289473573855,"uncertainty_avg":32.587105264261446,"uncertainty_penalty":0.6071086878120369}}},{"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":37.94084492826345,"highest":37.20768319617477,"medium":34.76846744526695,"none":41.846384143348615},"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":810,"losses":773,"wins":640},"match_totals_tracks":{"highest":{"draws":232,"losses":230,"wins":188},"medium":{"draws":350,"losses":341,"wins":263},"none":{"draws":228,"losses":202,"wins":189}},"model_slug":"google-gemini-3-5-flash-lite","overall":{"max":65.72298874215366,"mean":37.09699938126408,"min":14.659377314192781},"per_game":{"GB2-01":44.65575530999811,"GB2-02":28.548198358769575,"GB2-03":48.42582526757698,"GB2-04":25.068514273806112,"GB2-05":26.62168789866385,"GB2-06":54.39524382491415,"GB2-07":44.8546337721922,"GB2-08":25.09160686347721},"per_game_all":{"GB2-01":47.02124902801896,"GB2-02":28.52508022195423,"GB2-03":51.01975415720889,"GB2-04":32.92804133312089,"GB2-05":24.076206214948556,"GB2-06":53.1227983907982,"GB2-07":42.78234626840154,"GB2-08":24.051283811656315},"per_game_match_totals_all":{"GB2-01":{"draws":68,"losses":123,"wins":103},"GB2-02":{"draws":269,"losses":16,"wins":9},"GB2-03":{"draws":65,"losses":75,"wins":88},"GB2-04":{"draws":213,"losses":45,"wins":33},"GB2-05":{"draws":0,"losses":187,"wins":109},"GB2-06":{"draws":10,"losses":135,"wins":145},"GB2-07":{"draws":0,"losses":151,"wins":147},"GB2-08":{"draws":185,"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":57,"wins":42},"GB2-02":{"draws":120,"losses":4,"wins":4},"GB2-03":{"draws":38,"losses":32,"wins":32},"GB2-04":{"draws":102,"losses":15,"wins":11},"GB2-05":{"draws":0,"losses":70,"wins":66},"GB2-06":{"draws":2,"losses":72,"wins":54},"GB2-07":{"draws":0,"losses":79,"wins":51},"GB2-08":{"draws":57,"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":1499.8482616247745,"GB2-02":1484.6760562924546,"GB2-03":1530.6066389510963,"GB2-04":1489.3840122054396,"GB2-05":1320.293887977038,"GB2-06":1508.741159379392,"GB2-07":1465.839567231662,"GB2-08":1429.6219308771051},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1485.6576382024014,"GB2-02":1487.683594336881,"GB2-03":1518.9062245881858,"GB2-04":1454.5657189380322,"GB2-05":1346.8823575046931,"GB2-06":1522.088754825532,"GB2-07":1487.320314512178,"GB2-08":1441.564493870363},"medium":{"GB2-01":1502.0632638630816,"GB2-02":1486.279944881233,"GB2-03":1518.547181905224,"GB2-04":1488.0281178076189,"GB2-05":1369.6669903963675,"GB2-06":1408.5160558304942,"GB2-07":1262.5711153106781,"GB2-08":1428.8659054082534},"none":{"GB2-01":1511.8238828088404,"GB2-02":1480.0646296592502,"GB2-03":1554.3665103598798,"GB2-04":1525.558199870668,"GB2-05":1244.3323160300529,"GB2-06":1595.6186674821492,"GB2-07":1647.62727187213,"GB2-08":1418.4353933526995}},"per_game_tracks":{"highest":{"GB2-01":44.65575530999811,"GB2-02":28.548198358769575,"GB2-03":48.42582526757698,"GB2-04":25.068514273806112,"GB2-05":26.62168789866385,"GB2-06":54.39524382491415,"GB2-07":44.8546337721922,"GB2-08":25.09160686347721},"medium":{"GB2-01":48.37802087647134,"GB2-02":30.789942968134213,"GB2-03":49.5426251223461,"GB2-04":34.290379711385775,"GB2-05":30.947553431989036,"GB2-06":40.88114678411723,"GB2-07":17.769416290858764,"GB2-08":25.548654376833127},"none":{"GB2-01":48.02997089758741,"GB2-02":26.237099338958906,"GB2-03":55.09081208170358,"GB2-04":39.42523001417078,"GB2-05":14.659377314192781,"GB2-06":64.09200456336322,"GB2-07":65.72298874215366,"GB2-08":21.513590194658597}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#f5f9ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":37.20768319617477,"medium":34.76846744526695,"none":39.3148475023505},"reasoning_agg":{"highest":{"max":54.39524382491415,"mean":37.20768319617477,"min":25.068514273806112},"medium":{"max":49.5426251223461,"mean":34.76846744526695,"min":17.769416290858764},"none":{"max":65.72298874215366,"mean":39.3148475023505,"min":14.659377314192781}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Minimal"},"score_diagnostics":{"ceiling_score":65.72298874215366,"expected_score":31.744793784273057,"reasoning_variance":4.546380057083553,"reliability_score":71.6054857496051,"uncertainty_avg":28.394514250394902,"uncertainty_penalty":-5.35220559699102},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":54.39524382491415,"expected_score":21.64600189091762,"reliability_score":66.21496760265678,"uncertainty_avg":33.785032397343215,"uncertainty_penalty":-15.56168130525715},"medium":{"ceiling_score":49.5426251223461,"expected_score":25.91596835314532,"reliability_score":81.5897782513552,"uncertainty_avg":18.410221748644798,"uncertainty_penalty":-8.85249909212163},"none":{"ceiling_score":65.72298874215366,"expected_score":47.67241110875622,"reliability_score":67.01171139480331,"uncertainty_avg":32.988288605196686,"uncertainty_penalty":8.35756360640572}}},{"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":0.4852846}},"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":0.4852846},"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":36.88241645259815},"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":"2026-07-27T16:02:24Z","match_totals_all":{"draws":183,"losses":168,"wins":153},"match_totals_tracks":{"medium":{"draws":183,"losses":168,"wins":153}},"model_slug":"x-ai-grok-build-0-1","overall":{"max":53.736898671389504,"mean":36.88241645259816,"min":26.158778229592482},"per_game_match_totals_all":{"GB2-01":{"draws":15,"losses":24,"wins":33},"GB2-02":{"draws":54,"losses":2,"wins":2},"GB2-03":{"draws":22,"losses":15,"wins":13},"GB2-04":{"draws":42,"losses":5,"wins":5},"GB2-05":{"draws":0,"losses":34,"wins":38},"GB2-06":{"draws":0,"losses":39,"wins":31},"GB2-07":{"draws":0,"losses":42,"wins":28},"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":54,"losses":2,"wins":2},"GB2-03":{"draws":22,"losses":15,"wins":13},"GB2-04":{"draws":42,"losses":5,"wins":5},"GB2-05":{"draws":0,"losses":34,"wins":38},"GB2-06":{"draws":0,"losses":39,"wins":31},"GB2-07":{"draws":0,"losses":42,"wins":28},"GB2-08":{"draws":50,"losses":7,"wins":3}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1527.3692703367008,"GB2-02":1495.7843591523279,"GB2-03":1484.8977257302613,"GB2-04":1493.2435997285627,"GB2-05":1582.696901925296,"GB2-06":1426.7071891289527,"GB2-07":1356.0992001492057,"GB2-08":1457.9480224880604}},"per_game_tracks":{"medium":{"GB2-01":49.478057624072626,"GB2-02":27.461582006857626,"GB2-03":39.82116655919238,"GB2-04":29.880664924292944,"GB2-05":53.736898671389504,"GB2-06":41.030212939740636,"GB2-07":27.491970665647038,"GB2-08":26.158778229592482}},"provider_color":"#9CA3AF","provider_company":"xAI","provider_key":"x-ai","provider_text_color":"#0b1120","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":36.88241645259816},"reasoning_agg":{"medium":{"max":53.736898671389504,"mean":36.88241645259816,"min":26.158778229592482}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Setting not tested"},"score_diagnostics":{"ceiling_score":53.736898671389504},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":53.736898671389504,"expected_score":34.27502548088002,"reliability_score":55.16115385418642,"uncertainty_avg":44.83884614581358,"uncertainty_penalty":-2.6073909717181394}}},{"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":0.633501456},"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":0.7838332080000001},"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":35.487017467099164,"none":37.41134189718981},"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":"2026-07-27T15:59:13Z","match_totals_all":{"draws":440,"losses":549,"wins":411},"match_totals_tracks":{"medium":{"draws":126,"losses":198,"wins":162},"none":{"draws":314,"losses":351,"wins":249}},"model_slug":"meituan-longcat-2-0","overall":{"max":52.54958566492595,"mean":36.30835591436927,"min":19.492397682235918},"per_game_match_totals_all":{"GB2-01":{"draws":49,"losses":73,"wins":52},"GB2-02":{"draws":101,"losses":2,"wins":1},"GB2-03":{"draws":59,"losses":45,"wins":36},"GB2-04":{"draws":86,"losses":34,"wins":20},"GB2-05":{"draws":0,"losses":145,"wins":79},"GB2-06":{"draws":17,"losses":109,"wins":90},"GB2-07":{"draws":0,"losses":101,"wins":73},"GB2-08":{"draws":128,"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":50,"wins":43},"GB2-02":{"draws":63,"losses":1,"wins":0},"GB2-03":{"draws":46,"losses":32,"wins":22},"GB2-04":{"draws":36,"losses":13,"wins":15},"GB2-05":{"draws":0,"losses":101,"wins":43},"GB2-06":{"draws":13,"losses":68,"wins":53},"GB2-07":{"draws":0,"losses":71,"wins":63},"GB2-08":{"draws":115,"losses":15,"wins":10}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1351.444300552325,"GB2-02":1489.219893880294,"GB2-03":1485.8495357628185,"GB2-04":1428.206661663024,"GB2-05":1445.1478710815124,"GB2-06":1494.2599469181591,"GB2-07":1338.689982844879,"GB2-08":1607.9619175578798},"none":{"GB2-01":1479.1795477973847,"GB2-02":1480.4728086634052,"GB2-03":1435.666473249807,"GB2-04":1565.1896956500836,"GB2-05":1302.099984749541,"GB2-06":1495.0097462451129,"GB2-07":1422.8610596627066,"GB2-08":1426.3637798159552}},"per_game_tracks":{"medium":{"GB2-01":27.253758174484467,"GB2-02":28.422755456149947,"GB2-03":42.85985057751497,"GB2-04":19.492397682235918,"GB2-05":38.08421464409825,"GB2-06":50.68826178338193,"GB2-07":25.82251025654144,"GB2-08":51.272391162386356},"none":{"GB2-01":45.521519400812174,"GB2-02":29.40359272291873,"GB2-03":35.4921765950404,"GB2-04":49.655504012060575,"GB2-05":23.22225700698019,"GB2-06":52.54958566492595,"GB2-07":38.3880018617899,"GB2-08":25.05809791299054}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":37.1165385675198,"none":35.50017326121874},"reasoning_agg":{"medium":{"max":51.272391162386356,"mean":37.1165385675198,"min":19.492397682235918},"none":{"max":52.54958566492595,"mean":35.50017326121874,"min":23.22225700698019}},"reasoning_labels":{"highest":"Setting not tested","medium":"Enabled","none":"None"},"score_diagnostics":{"ceiling_score":52.54958566492595,"reasoning_variance":1.6163653063010557},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":51.272391162386356,"expected_score":26.060004817986986,"reliability_score":65.9648407093373,"uncertainty_avg":34.03515929066271,"uncertainty_penalty":-11.05653374953281},"none":{"ceiling_score":52.54958566492595,"expected_score":38.77680414023456,"reliability_score":82.00764498766817,"uncertainty_avg":17.992355012331828,"uncertainty_penalty":3.276630879015819}}},{"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":1.2830031540000002}},"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":1.2830031540000002},"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":38.34111208929003},"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":"2026-07-27T16:02:21Z","match_totals_all":{"draws":97,"losses":140,"wins":131},"match_totals_tracks":{"medium":{"draws":97,"losses":140,"wins":131}},"model_slug":"moonshotai-kimi-k2-7-code","overall":{"max":48.456236804374136,"mean":35.680425213671555,"min":23.668410863923103},"per_game_match_totals_all":{"GB2-01":{"draws":2,"losses":29,"wins":31},"GB2-02":{"draws":50,"losses":8,"wins":4},"GB2-04":{"draws":40,"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":31,"wins":28}},"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":40,"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":31,"wins":28}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1494.5618038162802,"GB2-02":1477.5720084631907,"GB2-04":1476.8766306909733,"GB2-05":1544.9007927839396,"GB2-07":1498.0077416215331,"GB2-08":1551.5977769607723}},"per_game_tracks":{"medium":{"GB2-01":44.64312313421955,"GB2-02":23.668410863923103,"GB2-04":26.590043215791468,"GB2-05":48.456236804374136,"GB2-07":45.68324115546186,"GB2-08":41.00561736197007}},"provider_color":"#7C3AED","provider_company":"Moonshot","provider_key":"moonshotai","provider_text_color":"#faf5ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":35.680425213671555},"reasoning_agg":{"medium":{"max":48.456236804374136,"mean":35.680425213671555,"min":23.668410863923103}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Setting not tested"},"score_diagnostics":{"ceiling_score":48.456236804374136},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":48.456236804374136,"expected_score":39.13058976904527,"reliability_score":54.534410417082206,"uncertainty_avg":45.465589582917794,"uncertainty_penalty":3.4501645553737177}}},{"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":0.025206018750000003,"min":0.016582062499999998,"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":0.025206018750000003,"min":0.0058062875,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":130},"run_count":81,"token_priced_attempt_count":130,"total":6.1442372999999995},"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":38.14958011301108,"highest":43.19756474345375,"medium":34.86719206815991,"none":36.38398352741958},"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":"2026-07-27T16:02:00Z","match_totals_all":{"draws":1373,"losses":1604,"wins":1138},"match_totals_tracks":{"highest":{"draws":320,"losses":340,"wins":301},"medium":{"draws":415,"losses":675,"wins":418},"none":{"draws":638,"losses":589,"wins":419}},"model_slug":"gpt-5-4-nano","overall":{"max":55.56433079370909,"mean":34.492095492125856,"min":19.102936607312394},"per_game":{"GB2-01":26.53737468779395,"GB2-02":29.985200935164713,"GB2-03":33.39410414668713,"GB2-04":27.735143570454902,"GB2-05":59.786700401424746,"GB2-06":78.42707203303546,"GB2-07":47.348675608269964,"GB2-08":42.36624656479914},"per_game_all":{"GB2-01":27.432961758912587,"GB2-02":28.983173466372296,"GB2-03":34.42438289015909,"GB2-04":35.77489866933561,"GB2-05":41.38357716652192,"GB2-06":64.66540611427789,"GB2-07":34.8840170751072,"GB2-08":37.64822376340206},"per_game_match_totals_all":{"GB2-01":{"draws":167,"losses":323,"wins":126},"GB2-02":{"draws":485,"losses":40,"wins":12},"GB2-03":{"draws":103,"losses":105,"wins":68},"GB2-04":{"draws":210,"losses":86,"wins":80},"GB2-05":{"draws":0,"losses":349,"wins":252},"GB2-06":{"draws":24,"losses":222,"wins":258},"GB2-07":{"draws":0,"losses":330,"wins":177},"GB2-08":{"draws":384,"losses":149,"wins":165}},"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":62,"wins":75},"GB2-06":{"draws":5,"losses":19,"wins":32},"GB2-07":{"draws":0,"losses":71,"wins":57},"GB2-08":{"draws":107,"losses":44,"wins":65}},"medium":{"GB2-01":{"draws":51,"losses":138,"wins":39},"GB2-02":{"draws":153,"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":126,"wins":117},"GB2-07":{"draws":0,"losses":175,"wins":58},"GB2-08":{"draws":93,"losses":48,"wins":49}},"none":{"GB2-01":{"draws":78,"losses":121,"wins":71},"GB2-02":{"draws":216,"losses":15,"wins":3},"GB2-03":{"draws":66,"losses":67,"wins":47},"GB2-04":{"draws":92,"losses":22,"wins":12},"GB2-05":{"draws":0,"losses":146,"wins":64},"GB2-06":{"draws":2,"losses":77,"wins":109},"GB2-07":{"draws":0,"losses":84,"wins":62},"GB2-08":{"draws":184,"losses":57,"wins":51}}},"per_game_raw_elo_all":{"GB2-01":1341.2408562528703,"GB2-02":1480.3188519873574,"GB2-03":1428.5498961945016,"GB2-04":1496.0994753456607,"GB2-05":1459.4475593638224,"GB2-06":1588.3703982977856,"GB2-07":1396.4426640162426,"GB2-08":1508.0233379084123},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1335.0645693107563,"GB2-02":1481.5867943828466,"GB2-03":1424.3051991222185,"GB2-04":1456.4129665430028,"GB2-05":1616.7103540889234,"GB2-06":1693.7457177478934,"GB2-07":1493.9594139977835,"GB2-08":1537.60438067143},"medium":{"GB2-01":1278.340560614945,"GB2-02":1480.4503257520255,"GB2-03":1410.3860603587646,"GB2-04":1546.1890238694712,"GB2-05":1432.5578285667934,"GB2-06":1518.7401226956479,"GB2-07":1303.7821921760747,"GB2-08":1513.115041857068},"none":{"GB2-01":1410.3174388329098,"GB2-02":1478.9194358272002,"GB2-03":1450.9584291025221,"GB2-04":1485.696435624508,"GB2-05":1329.07449543575,"GB2-06":1552.6253544498152,"GB2-07":1391.5863858748698,"GB2-08":1473.3505911967395}},"per_game_tracks":{"highest":{"GB2-01":26.53737468779395,"GB2-02":29.985200935164713,"GB2-03":33.39410414668713,"GB2-04":27.735143570454902,"GB2-05":59.786700401424746,"GB2-06":78.42707203303546,"GB2-07":47.348675608269964,"GB2-08":42.36624656479914},"medium":{"GB2-01":19.102936607312394,"GB2-02":28.51048338744381,"GB2-03":31.050446121101896,"GB2-04":45.84036755746706,"GB2-05":38.084940854795306,"GB2-06":55.56433079370909,"GB2-07":22.682571481279417,"GB2-08":38.10145974217034},"none":{"GB2-01":36.65857398163143,"GB2-02":28.45383607650836,"GB2-03":38.828598402688236,"GB2-04":33.74918488008487,"GB2-05":26.279090243345703,"GB2-06":60.00481551608911,"GB2-07":34.620804135772225,"GB2-08":32.476964983236684}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":41.061099449205294,"medium":31.8322782244249,"none":30.58290880274737},"reasoning_agg":{"highest":{"max":42.36624656479914,"mean":41.061099449205294,"min":42.36624656479914},"medium":{"max":55.56433079370909,"mean":31.8322782244249,"min":19.102936607312394},"none":{"max":36.65857398163143,"mean":30.58290880274737,"min":28.45383607650836}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"score_diagnostics":{"ceiling_score":55.56433079370909,"expected_score":30.388854475410312,"reasoning_variance":10.478190646457925,"reliability_score":80.59097030667746,"uncertainty_avg":19.409029693322537,"uncertainty_penalty":-4.103241016715543},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":42.36624656479914,"expected_score":27.529343511285003,"reliability_score":80.39984288367646,"uncertainty_avg":19.600157116323544,"uncertainty_penalty":-13.531755937920291},"medium":{"ceiling_score":55.56433079370909,"expected_score":29.05377026790566,"reliability_score":79.01419979254085,"uncertainty_avg":20.98580020745915,"uncertainty_penalty":-2.778507956519242},"none":{"ceiling_score":36.65857398163143,"expected_score":34.583449647040275,"reliability_score":82.35886824381508,"uncertainty_avg":17.641131756184915,"uncertainty_penalty":4.000540844292907}}},{"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":0.0022439992166666664,"min":0.00169122,"recorded_attempt_count":35,"run_count":24,"total":0.06653988079999999}},"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":0.00169122,"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":32.25618895336439,"highest":31.789261679901056,"medium":32.56840820109461,"none":37.927080269567156},"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":"2026-07-27T16:02:23Z","match_totals_all":{"draws":856,"losses":773,"wins":605},"match_totals_tracks":{"highest":{"draws":141,"losses":44,"wins":25},"medium":{"draws":381,"losses":317,"wins":236},"none":{"draws":334,"losses":412,"wins":344}},"model_slug":"xiaomi-mimo-v2-5","overall":{"max":51.785443642756896,"mean":33.709260009850475,"min":21.77927935287923},"per_game":{"GB2-01":21.77927935287923,"GB2-02":26.675502781911693,"GB2-04":33.302708753199845,"GB2-06":51.785443642756896,"GB2-08":25.403373868757644},"per_game_all":{"GB2-01":36.478748127198934,"GB2-02":26.282853810138505,"GB2-04":31.369187946025267,"GB2-06":44.15947774863587,"GB2-08":22.990677134823397},"per_game_match_totals_all":{"GB2-01":{"draws":102,"losses":169,"wins":133},"GB2-02":{"draws":251,"losses":15,"wins":8},"GB2-03":{"draws":30,"losses":9,"wins":11},"GB2-04":{"draws":256,"losses":43,"wins":27},"GB2-05":{"draws":0,"losses":172,"wins":168},"GB2-06":{"draws":9,"losses":155,"wins":118},"GB2-07":{"draws":0,"losses":142,"wins":120},"GB2-08":{"draws":208,"losses":68,"wins":20}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":33,"losses":11,"wins":0},"GB2-02":{"draws":33,"losses":3,"wins":2},"GB2-04":{"draws":30,"losses":6,"wins":4},"GB2-06":{"draws":6,"losses":19,"wins":17},"GB2-08":{"draws":39,"losses":5,"wins":2}},"medium":{"GB2-01":{"draws":15,"losses":69,"wins":56},"GB2-02":{"draws":161,"losses":9,"wins":6},"GB2-04":{"draws":136,"losses":30,"wins":10},"GB2-05":{"draws":0,"losses":69,"wins":67},"GB2-06":{"draws":3,"losses":37,"wins":18},"GB2-07":{"draws":0,"losses":63,"wins":63},"GB2-08":{"draws":66,"losses":40,"wins":16}},"none":{"GB2-01":{"draws":54,"losses":89,"wins":77},"GB2-02":{"draws":57,"losses":3,"wins":0},"GB2-03":{"draws":30,"losses":9,"wins":11},"GB2-04":{"draws":90,"losses":7,"wins":13},"GB2-05":{"draws":0,"losses":103,"wins":101},"GB2-06":{"draws":0,"losses":99,"wins":83},"GB2-07":{"draws":0,"losses":79,"wins":57},"GB2-08":{"draws":103,"losses":23,"wins":2}}},"per_game_raw_elo_all":{"GB2-01":1418.17298105174,"GB2-02":1480.4393249115385,"GB2-04":1486.6442627787626,"GB2-06":1445.315252955762,"GB2-08":1425.32325426476},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1306.1499854705874,"GB2-02":1483.4827683360977,"GB2-04":1495.9190911735002,"GB2-06":1501.76159895558,"GB2-08":1439.4563174105635},"medium":{"GB2-01":1456.7687348778354,"GB2-02":1489.6601257834463,"GB2-04":1467.5819924358773,"GB2-05":1463.8208589793223,"GB2-06":1375.5529020758545,"GB2-07":1463.9620516903908,"GB2-08":1431.5413044631157},"none":{"GB2-01":1491.600222806797,"GB2-02":1468.175080615072,"GB2-03":1530.1875388618716,"GB2-04":1496.4317047269096,"GB2-05":1451.2102640235487,"GB2-06":1458.631257835851,"GB2-07":1389.3110822405565,"GB2-08":1404.9721409206004}},"per_game_tracks":{"highest":{"GB2-01":21.77927935287923,"GB2-02":26.675502781911693,"GB2-04":33.302708753199845,"GB2-06":51.785443642756896,"GB2-08":25.403373868757644},"medium":{"GB2-01":40.27037605502182,"GB2-02":26.08750560023417,"GB2-04":25.616057609593227,"GB2-05":39.642986122725766,"GB2-06":33.33434993833325,"GB2-07":40.87578726019612,"GB2-08":22.15179482155793},"none":{"GB2-01":47.38658897369575,"GB2-02":26.085553048269652,"GB2-03":51.412762414887055,"GB2-04":35.188797475282726,"GB2-05":40.46122645082023,"GB2-06":47.35863966481747,"GB2-07":34.10621141460972,"GB2-08":21.416862714154618}},"provider_color":"#FF6900","provider_company":"Xiaomi","provider_key":"xiaomi","provider_text_color":"#fff7f1","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":31.789261679901063,"medium":27.992319252943243,"none":41.34619909670711},"reasoning_agg":{"highest":{"max":51.785443642756896,"mean":31.789261679901063,"min":21.77927935287923},"medium":{"max":39.642986122725766,"mean":27.992319252943243,"min":25.616057609593227},"none":{"max":47.38658897369575,"mean":41.34619909670711,"min":40.46122645082023}},"reasoning_labels":{"highest":"Highest","medium":"Reasoning enabled","none":"Reasoning disabled"},"score_diagnostics":{"ceiling_score":51.785443642756896,"expected_score":21.820655088999718,"reasoning_variance":13.353879843763867,"reliability_score":67.54260212039092,"uncertainty_avg":32.457397879609076,"uncertainty_penalty":-11.888604920850756},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":51.785443642756896,"expected_score":14.872145984786448,"reliability_score":67.37633239758216,"uncertainty_avg":32.62366760241784,"uncertainty_penalty":-16.917115695114617},"medium":{"ceiling_score":39.642986122725766,"expected_score":28.058482226505838,"reliability_score":55.357231386751174,"uncertainty_avg":44.642768613248826,"uncertainty_penalty":0.06616297356259437},"none":{"ceiling_score":47.38658897369575,"expected_score":37.79947807882712,"reliability_score":80.54328460201677,"uncertainty_avg":19.45671539798323,"uncertainty_penalty":-3.546721017879989}}},{"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":2.8948644100000003},"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":0.8573406100000001},"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":0.4210408500000001}},"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":37.96129997249137,"highest":32.984548508298495,"medium":37.519921081609276,"none":39.000833473630465},"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":"2026-07-27T15:31:04Z","match_totals_all":{"draws":513,"losses":678,"wins":475},"match_totals_tracks":{"highest":{"draws":73,"losses":80,"wins":47},"medium":{"draws":188,"losses":291,"wins":237},"none":{"draws":252,"losses":307,"wins":191}},"model_slug":"thinkingmachines-inkling","overall":{"max":56.06167167227131,"mean":33.634319078319784,"min":21.717457965632377},"per_game":{"GB2-02":22.858580155536725,"GB2-05":31.68905148984333,"GB2-06":56.06167167227131,"GB2-07":32.59598125820875,"GB2-08":21.717457965632377},"per_game_all":{"GB2-02":28.55463468634443,"GB2-05":34.42903492759131,"GB2-06":44.11659007992208,"GB2-07":38.54035569165094,"GB2-08":44.16588447694807},"per_game_match_totals_all":{"GB2-01":{"draws":94,"losses":99,"wins":57},"GB2-02":{"draws":164,"losses":9,"wins":1},"GB2-03":{"draws":46,"losses":26,"wins":26},"GB2-04":{"draws":172,"losses":40,"wins":20},"GB2-05":{"draws":0,"losses":191,"wins":129},"GB2-06":{"draws":4,"losses":92,"wins":74},"GB2-07":{"draws":0,"losses":136,"wins":106},"GB2-08":{"draws":33,"losses":85,"wins":62}},"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":35,"losses":49,"wins":40},"GB2-02":{"draws":63,"losses":5,"wins":0},"GB2-04":{"draws":90,"losses":18,"wins":10},"GB2-05":{"draws":0,"losses":78,"wins":58},"GB2-06":{"draws":0,"losses":37,"wins":27},"GB2-07":{"draws":0,"losses":65,"wins":69},"GB2-08":{"draws":0,"losses":39,"wins":33}},"none":{"GB2-01":{"draws":59,"losses":50,"wins":17},"GB2-02":{"draws":64,"losses":1,"wins":1},"GB2-03":{"draws":46,"losses":26,"wins":26},"GB2-04":{"draws":82,"losses":22,"wins":10},"GB2-05":{"draws":0,"losses":87,"wins":57},"GB2-06":{"draws":0,"losses":39,"wins":27},"GB2-07":{"draws":0,"losses":44,"wins":24},"GB2-08":{"draws":1,"losses":38,"wins":29}}},"per_game_raw_elo_all":{"GB2-02":1480.466678690252,"GB2-05":1403.828542480496,"GB2-06":1436.8414578464224,"GB2-07":1428.595274465046,"GB2-08":1554.8754901093134},"per_game_raw_elo_tracks":{"highest":{"GB2-02":1465.91270724254,"GB2-05":1390.323659481682,"GB2-06":1535.3338889332665,"GB2-07":1391.587035593027,"GB2-08":1419.7532402504671},"medium":{"GB2-01":1379.854093299657,"GB2-02":1476.6106392697473,"GB2-04":1471.0544037106085,"GB2-05":1370.3104206683065,"GB2-06":1353.884883080069,"GB2-07":1539.7826896034899,"GB2-08":1605.3208067268397},"none":{"GB2-01":1334.163404047537,"GB2-02":1498.8766895584683,"GB2-03":1522.9087960092234,"GB2-04":1471.7594087580565,"GB2-05":1450.8515472914996,"GB2-06":1421.3056015259317,"GB2-07":1354.4160981986215,"GB2-08":1639.5524233506335}},"per_game_tracks":{"highest":{"GB2-02":22.858580155536725,"GB2-05":31.68905148984333,"GB2-06":56.06167167227131,"GB2-07":32.59598125820875,"GB2-08":21.717457965632377},"medium":{"GB2-01":32.474295630021714,"GB2-02":28.830010796441194,"GB2-04":30.50702629256417,"GB2-05":31.02260862106261,"GB2-06":33.60391173446151,"GB2-07":53.355787870899725,"GB2-08":52.84580662581403},"none":{"GB2-01":26.63272439732407,"GB2-02":33.97531310705538,"GB2-03":50.09192000149523,"GB2-04":30.443391993025433,"GB2-05":40.575444671868,"GB2-06":42.684186833033415,"GB2-07":29.66929794584434,"GB2-08":57.934388839397826}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":32.984548508298495,"medium":33.54570838202333,"none":34.37270034463752},"reasoning_agg":{"highest":{"max":56.06167167227131,"mean":32.984548508298495,"min":21.717457965632377},"medium":{"max":53.355787870899725,"mean":33.54570838202333,"min":30.50702629256417},"none":{"max":50.09192000149523,"mean":34.37270034463752,"min":26.63272439732407}},"reasoning_labels":{"highest":"Max","medium":"Medium","none":"None"},"score_diagnostics":{"ceiling_score":56.06167167227131,"expected_score":31.39312589646255,"reasoning_variance":1.388151836339027,"reliability_score":77.541248610448,"uncertainty_avg":22.458751389552006,"uncertainty_penalty":-2.241193181857234},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":56.06167167227131,"expected_score":18.896688407921257,"reliability_score":65.66311905569697,"uncertainty_avg":34.33688094430304,"uncertainty_penalty":-14.087860100377238},"medium":{"ceiling_score":53.355787870899725,"expected_score":28.67046377346867,"reliability_score":82.43978262215337,"uncertainty_avg":17.560217377846623,"uncertainty_penalty":-4.8752446085546595},"none":{"ceiling_score":50.09192000149523,"expected_score":42.19922627836161,"reliability_score":81.23249220944109,"uncertainty_avg":18.767507790558906,"uncertainty_penalty":7.826525933724085}}},{"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":0.7875583199999998},"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":28.98620958231826,"none":41.53728100912679},"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":"2026-07-27T15:57:38Z","match_totals_all":{"draws":264,"losses":326,"wins":244},"match_totals_tracks":{"medium":{"draws":159,"losses":183,"wins":88},"none":{"draws":105,"losses":143,"wins":156}},"model_slug":"minimax-minimax-m3","overall":{"max":53.01828026826074,"mean":33.344667990638854,"min":13.449884255838182},"per_game_match_totals_all":{"GB2-01":{"draws":19,"losses":65,"wins":56},"GB2-02":{"draws":117,"losses":6,"wins":1},"GB2-03":{"draws":24,"losses":14,"wins":28},"GB2-04":{"draws":43,"losses":3,"wins":2},"GB2-05":{"draws":0,"losses":92,"wins":42},"GB2-06":{"draws":0,"losses":40,"wins":20},"GB2-07":{"draws":0,"losses":63,"wins":61},"GB2-08":{"draws":61,"losses":43,"wins":34}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":4,"losses":42,"wins":24},"GB2-02":{"draws":58,"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":40,"wins":20},"GB2-07":{"draws":0,"losses":32,"wins":30},"GB2-08":{"draws":54,"losses":10,"wins":4}},"none":{"GB2-01":{"draws":15,"losses":23,"wins":32},"GB2-02":{"draws":59,"losses":1,"wins":0},"GB2-03":{"draws":24,"losses":14,"wins":28},"GB2-05":{"draws":0,"losses":41,"wins":35},"GB2-07":{"draws":0,"losses":31,"wins":31},"GB2-08":{"draws":7,"losses":33,"wins":30}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1403.6757984989108,"GB2-02":1472.4432660242555,"GB2-04":1496.9783565501152,"GB2-05":1244.799664295561,"GB2-06":1361.9567117344586,"GB2-07":1497.4607367338917,"GB2-08":1457.791824430241},"none":{"GB2-01":1497.8471484037084,"GB2-02":1474.9611713998297,"GB2-03":1532.5793891002238,"GB2-05":1461.8308552065046,"GB2-07":1436.3423615846004,"GB2-08":1513.6287669745502}},"per_game_tracks":{"medium":{"GB2-01":33.44544070850067,"GB2-02":22.61535944594515,"GB2-04":29.86715418711666,"GB2-05":13.449884255838182,"GB2-06":31.703202638038128,"GB2-07":45.067797325096485,"GB2-08":26.754628515692527},"none":{"GB2-01":48.06691150878728,"GB2-02":27.705611244015376,"GB2-03":53.01828026826074,"GB2-05":41.99990230008747,"GB2-07":39.873011049349245,"GB2-08":38.55996968426065}},"provider_color":"#00BFA5","provider_company":"MiniMax","provider_key":"minimax","provider_text_color":"#f2fffc","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":28.034540440294958,"none":38.654795540982754},"reasoning_agg":{"medium":{"max":45.067797325096485,"mean":28.034540440294958,"min":13.449884255838182},"none":{"max":53.01828026826074,"mean":38.654795540982754,"min":27.705611244015376}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"score_diagnostics":{"ceiling_score":53.01828026826074,"reasoning_variance":10.620255100687796},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":45.067797325096485,"expected_score":23.580366241502563,"reliability_score":54.17150796716235,"uncertainty_avg":45.82849203283765,"uncertainty_penalty":-4.454174198792394},"none":{"ceiling_score":53.01828026826074,"expected_score":41.331246683525684,"reliability_score":83.12405082855398,"uncertainty_avg":16.875949171446017,"uncertainty_penalty":2.6764511425429305}}},{"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":0.43500895999999994},"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":0.08145696}},"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":0.5164659200000001},"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":41.32728149210222,"none":31.12439860535781},"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":"2026-07-27T15:58:41Z","match_totals_all":{"draws":262,"losses":285,"wins":229},"match_totals_tracks":{"medium":{"draws":146,"losses":122,"wins":134},"none":{"draws":116,"losses":163,"wins":95}},"model_slug":"qwen-qwen3-7-plus","overall":{"max":59.51052506806163,"mean":33.22196163051123,"min":17.078759313374523},"per_game_match_totals_all":{"GB2-01":{"draws":28,"losses":65,"wins":45},"GB2-02":{"draws":125,"losses":2,"wins":1},"GB2-04":{"draws":40,"losses":3,"wins":3},"GB2-05":{"draws":0,"losses":69,"wins":73},"GB2-06":{"draws":11,"losses":67,"wins":46},"GB2-07":{"draws":0,"losses":75,"wins":61},"GB2-08":{"draws":58,"losses":4,"wins":0}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":10,"losses":29,"wins":29},"GB2-02":{"draws":67,"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":58,"losses":4,"wins":0}},"none":{"GB2-01":{"draws":18,"losses":36,"wins":16},"GB2-02":{"draws":58,"losses":0,"wins":0},"GB2-04":{"draws":40,"losses":3,"wins":3},"GB2-05":{"draws":0,"losses":38,"wins":34},"GB2-06":{"draws":0,"losses":47,"wins":17},"GB2-07":{"draws":0,"losses":39,"wins":25}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1509.0945784086714,"GB2-02":1495.5827653330884,"GB2-05":1509.600072103669,"GB2-06":1570.7099847887985,"GB2-07":1460.8552075834623,"GB2-08":1461.6488483482228},"none":{"GB2-01":1372.448577341908,"GB2-02":1495.3686744490708,"GB2-04":1507.7518112619032,"GB2-05":1414.093697253425,"GB2-06":1346.5858526769046,"GB2-07":1257.5505253206957}},"per_game_tracks":{"medium":{"GB2-01":46.82185440133597,"GB2-02":28.89812236139288,"GB2-05":44.921853226556,"GB2-06":59.51052506806163,"GB2-07":40.89162392193896,"GB2-08":26.919709973327855},"none":{"GB2-01":31.896390308583022,"GB2-02":32.37203516308192,"GB2-04":36.47987858051721,"GB2-05":36.28769585919104,"GB2-06":32.63163240739917,"GB2-07":17.078759313374523}},"provider_color":"#FF6A00","provider_company":"Alibaba","provider_key":"qwen","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":38.45936897003059,"none":27.98455429099188},"reasoning_agg":{"medium":{"max":59.51052506806163,"mean":38.45936897003059,"min":26.919709973327855},"none":{"max":36.47987858051721,"mean":27.98455429099188,"min":17.078759313374523}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"score_diagnostics":{"ceiling_score":59.51052506806163,"reasoning_variance":10.474814679038708},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":59.51052506806163,"expected_score":39.4491130519773,"reliability_score":57.67422138130981,"uncertainty_avg":42.32577861869019,"uncertainty_penalty":0.9897440819467107},"none":{"ceiling_score":36.47987858051721,"expected_score":30.867493049452648,"reliability_score":80.42977627727906,"uncertainty_avg":19.570223722720936,"uncertainty_penalty":2.8829387584607673}}},{"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":0.14255357568},"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":33.928065688588816,"highest":35.74611777940509,"medium":34.19606995047676,"none":34.02334672619829},"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":"2026-07-27T16:02:00Z","match_totals_all":{"draws":916,"losses":1003,"wins":627},"match_totals_tracks":{"highest":{"draws":182,"losses":312,"wins":206},"medium":{"draws":228,"losses":236,"wins":136},"none":{"draws":506,"losses":455,"wins":285}},"model_slug":"deepseek-deepseek-v4-flash","overall":{"max":51.468109335875496,"mean":33.11867834257186,"min":23.975023785065247},"per_game":{"GB2-01":41.327363323089216,"GB2-02":29.692155158998496,"GB2-05":37.15666178716489,"GB2-06":30.620679713560136,"GB2-07":49.93322035186378,"GB2-08":25.746626341753977},"per_game_all":{"GB2-01":44.03530454624548,"GB2-02":28.795900034974593,"GB2-05":35.835928407027176,"GB2-06":27.35351459798622,"GB2-07":41.850391714616514,"GB2-08":25.697354830682926},"per_game_match_totals_all":{"GB2-01":{"draws":86,"losses":114,"wins":86},"GB2-02":{"draws":293,"losses":16,"wins":7},"GB2-03":{"draws":61,"losses":49,"wins":42},"GB2-04":{"draws":183,"losses":26,"wins":7},"GB2-05":{"draws":0,"losses":271,"wins":181},"GB2-06":{"draws":2,"losses":223,"wins":103},"GB2-07":{"draws":0,"losses":246,"wins":184},"GB2-08":{"draws":291,"losses":58,"wins":17}},"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":56},"GB2-06":{"draws":0,"losses":89,"wins":39},"GB2-07":{"draws":0,"losses":62,"wins":62},"GB2-08":{"draws":48,"losses":14,"wins":4}},"medium":{"GB2-01":{"draws":30,"losses":38,"wins":22},"GB2-02":{"draws":70,"losses":6,"wins":0},"GB2-03":{"draws":9,"losses":9,"wins":12},"GB2-04":{"draws":34,"losses":4,"wins":2},"GB2-05":{"draws":0,"losses":56,"wins":40},"GB2-06":{"draws":2,"losses":55,"wins":29},"GB2-07":{"draws":0,"losses":60,"wins":30},"GB2-08":{"draws":83,"losses":8,"wins":1}},"none":{"GB2-01":{"draws":26,"losses":23,"wins":25},"GB2-02":{"draws":119,"losses":2,"wins":1},"GB2-03":{"draws":52,"losses":40,"wins":30},"GB2-04":{"draws":149,"losses":22,"wins":5},"GB2-05":{"draws":0,"losses":129,"wins":85},"GB2-06":{"draws":0,"losses":79,"wins":35},"GB2-07":{"draws":0,"losses":124,"wins":92},"GB2-08":{"draws":160,"losses":36,"wins":12}}},"per_game_raw_elo_all":{"GB2-01":1471.1051450400012,"GB2-02":1483.9481369531334,"GB2-05":1413.9296682422346,"GB2-06":1311.5397157547238,"GB2-07":1453.4737576893306,"GB2-08":1434.6547713179386},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1448.9172858681118,"GB2-02":1483.7128017422178,"GB2-05":1421.8705390548175,"GB2-06":1331.5600157396711,"GB2-07":1514.9260778582047,"GB2-08":1432.1969593602666},"medium":{"GB2-01":1480.9593531656378,"GB2-02":1472.171016892196,"GB2-03":1546.3471653061004,"GB2-04":1474.9614593543852,"GB2-05":1387.2963219883493,"GB2-06":1323.2973248119208,"GB2-07":1434.5096246302887,"GB2-08":1443.2618465194205},"none":{"GB2-01":1483.438796086254,"GB2-02":1495.9605922249866,"GB2-03":1467.0922260747213,"GB2-04":1455.8644480597122,"GB2-05":1432.6221436835365,"GB2-06":1279.76180671258,"GB2-07":1410.985570579499,"GB2-08":1428.5055080741283}},"per_game_tracks":{"highest":{"GB2-01":41.327363323089216,"GB2-02":29.692155158998496,"GB2-05":37.15666178716489,"GB2-06":30.620679713560136,"GB2-07":49.93322035186378,"GB2-08":25.746626341753977},"medium":{"GB2-01":44.40416072069643,"GB2-02":23.975023785065247,"GB2-03":51.468109335875496,"GB2-04":29.129670210091273,"GB2-05":31.957262612735185,"GB2-06":28.104126773830203,"GB2-07":38.53812602283009,"GB2-08":25.99208014269019},"none":{"GB2-01":46.374389594950806,"GB2-02":32.72052116086004,"GB2-03":41.56307486091444,"GB2-04":27.36600328835098,"GB2-05":38.39386082118144,"GB2-06":23.335737306568312,"GB2-07":37.07982876915568,"GB2-08":25.35335800760461}},"provider_color":"#4C8BF5","provider_company":"DeepSeek","provider_key":"deepseek","provider_text_color":"#f6f9ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":34.9298304006065,"medium":34.19606995047676,"none":30.230134676632332},"reasoning_agg":{"highest":{"max":49.93322035186378,"mean":34.9298304006065,"min":29.692155158998496},"medium":{"max":51.468109335875496,"mean":34.19606995047676,"min":23.975023785065247},"none":{"max":38.39386082118144,"mean":30.230134676632332,"min":25.35335800760461}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Reasoning disabled"},"score_diagnostics":{"ceiling_score":51.468109335875496,"expected_score":22.697964191329792,"reasoning_variance":4.699695723974166,"reliability_score":77.90140341506309,"uncertainty_avg":22.09859658493691,"uncertainty_penalty":-10.42071415124207},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":49.93322035186378,"expected_score":17.696907834624554,"reliability_score":81.54985925894773,"uncertainty_avg":18.450140741052262,"uncertainty_penalty":-17.232922565981944},"medium":{"ceiling_score":51.468109335875496,"expected_score":25.884658799030593,"reliability_score":66.85309834439491,"uncertainty_avg":33.14690165560509,"uncertainty_penalty":-8.311411151446169},"none":{"ceiling_score":38.39386082118144,"expected_score":30.965292726065922,"reliability_score":81.9571410452468,"uncertainty_avg":18.042858954753196,"uncertainty_penalty":0.7351580494335899}}},{"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":0.93629233},"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":39.856797137810645,"highest":31.017555673697313,"medium":41.07034239208697,"none":36.51873040253819},"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":"2026-07-27T15:58:43Z","match_totals_all":{"draws":236,"losses":368,"wins":240},"match_totals_tracks":{"highest":{"draws":59,"losses":179,"wins":92},"medium":{"draws":94,"losses":66,"wins":58},"none":{"draws":83,"losses":123,"wins":90}},"model_slug":"stepfun-step-3-7-flash","overall":{"max":54.04373188325387,"mean":32.47819970422248,"min":19.57553453515884},"per_game":{"GB2-01":19.747298274267855,"GB2-05":41.14537153635741,"GB2-06":40.244509748458896,"GB2-07":29.094119565026098,"GB2-08":24.85647924437633},"per_game_all":{"GB2-05":43.10757367918146,"GB2-06":36.60602059643983},"per_game_match_totals_all":{"GB2-01":{"draws":18,"losses":71,"wins":31},"GB2-02":{"draws":51,"losses":4,"wins":1},"GB2-03":{"draws":21,"losses":10,"wins":9},"GB2-04":{"draws":58,"losses":6,"wins":14},"GB2-05":{"draws":0,"losses":83,"wins":81},"GB2-06":{"draws":2,"losses":97,"wins":57},"GB2-07":{"draws":0,"losses":74,"wins":44},"GB2-08":{"draws":86,"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":51,"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":35,"wins":20}},"none":{"GB2-01":{"draws":14,"losses":26,"wins":18},"GB2-03":{"draws":21,"losses":10,"wins":9},"GB2-04":{"draws":16,"losses":3,"wins":9},"GB2-05":{"draws":0,"losses":24,"wins":18},"GB2-06":{"draws":0,"losses":25,"wins":13},"GB2-07":{"draws":0,"losses":27,"wins":23},"GB2-08":{"draws":32,"losses":8,"wins":0}}},"per_game_raw_elo_all":{"GB2-05":1486.7909013212545,"GB2-06":1389.6090107168404},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1301.5005645283745,"GB2-05":1478.0856341696644,"GB2-06":1425.4926583834322,"GB2-07":1369.7166239031599,"GB2-08":1444.5283788982229},"medium":{"GB2-02":1495.901542637513,"GB2-04":1527.025896067843,"GB2-05":1572.4768033532573,"GB2-06":1384.0385830541572},"none":{"GB2-01":1474.9655056194315,"GB2-03":1526.648010167357,"GB2-04":1539.8999918600214,"GB2-05":1409.8102664408416,"GB2-06":1359.2957907129323,"GB2-07":1408.2743046740543,"GB2-08":1405.907367827263}},"per_game_tracks":{"highest":{"GB2-01":19.747298274267855,"GB2-05":41.14537153635741,"GB2-06":40.244509748458896,"GB2-07":29.094119565026098,"GB2-08":24.85647924437633},"medium":{"GB2-02":32.28302107896658,"GB2-04":40.78259187031759,"GB2-05":54.04373188325387,"GB2-06":37.17202473580983},"none":{"GB2-01":44.52251713937394,"GB2-03":49.72936122718848,"GB2-04":39.70878194898091,"GB2-05":34.13361761793311,"GB2-06":32.401527305050784,"GB2-07":35.55977304408127,"GB2-08":19.57553453515884}},"provider_color":"#F59E0B","provider_company":"StepFun","provider_key":"stepfun","provider_text_color":"#1f1300","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":27.578940302135955,"medium":34.5359036907486,"none":35.31975511978292},"reasoning_agg":{"highest":{"max":41.14537153635741,"mean":27.578940302135955,"min":19.747298274267855},"medium":{"max":54.04373188325387,"mean":34.5359036907486,"min":32.28302107896658},"none":{"max":49.72936122718848,"mean":35.31975511978292,"min":19.57553453515884}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"score_diagnostics":{"ceiling_score":54.04373188325387,"expected_score":32.90299119504721,"reasoning_variance":7.740814817646964,"reliability_score":66.34420999505114,"uncertainty_avg":33.655790004948855,"uncertainty_penalty":0.4247914908247239},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":41.14537153635741,"expected_score":16.51689544076508,"reliability_score":57.20722402456279,"uncertainty_avg":42.79277597543721,"uncertainty_penalty":-11.062044861370875},"medium":{"ceiling_score":54.04373188325387,"expected_score":40.40482256280891,"reliability_score":76.57653555971073,"uncertainty_avg":23.423464440289266,"uncertainty_penalty":5.868918872060313},"none":{"ceiling_score":49.72936122718848,"expected_score":43.08262687186084,"reliability_score":66.54382103745851,"uncertainty_avg":33.45617896254148,"uncertainty_penalty":7.7628717520779205}}},{"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":0.029176983000000004},"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":32.55989674512322,"none":39.08501586962298},"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":"2026-07-27T15:55:05Z","match_totals_all":{"draws":330,"losses":328,"wins":262},"match_totals_tracks":{"highest":{"draws":130,"losses":209,"wins":147},"none":{"draws":200,"losses":119,"wins":115}},"model_slug":"tencent-hy3-preview","overall":{"max":72.6465473220185,"mean":32.01014225656428,"min":17.993252641418948},"per_game":{"GB2-01":51.81286686979948,"GB2-02":20.82093118555568,"GB2-04":17.993252641418948,"GB2-05":51.2770740935357,"GB2-06":28.544824407056506,"GB2-07":31.031275607799287,"GB2-08":26.439052410696952},"per_game_match_totals_all":{"GB2-01":{"draws":24,"losses":46,"wins":74},"GB2-02":{"draws":126,"losses":13,"wins":1},"GB2-03":{"draws":24,"losses":20,"wins":26},"GB2-04":{"draws":70,"losses":15,"wins":11},"GB2-05":{"draws":0,"losses":89,"wins":77},"GB2-06":{"draws":0,"losses":54,"wins":20},"GB2-07":{"draws":0,"losses":44,"wins":28},"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":44,"wins":28},"GB2-08":{"draws":21,"losses":33,"wins":24}},"none":{"GB2-01":{"draws":15,"losses":15,"wins":46},"GB2-02":{"draws":62,"losses":6,"wins":0},"GB2-03":{"draws":24,"losses":20,"wins":26},"GB2-04":{"draws":34,"losses":6,"wins":10},"GB2-05":{"draws":0,"losses":58,"wins":32},"GB2-08":{"draws":65,"losses":14,"wins":1}}},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1547.3715719552615,"GB2-02":1460.9581933522327,"GB2-04":1439.5853927038256,"GB2-05":1560.8716690403694,"GB2-06":1331.332669440063,"GB2-07":1382.7298482608094,"GB2-08":1451.793708185056},"none":{"GB2-01":1686.569380601013,"GB2-02":1465.8989139702087,"GB2-03":1437.0101184596929,"GB2-04":1521.129620533277,"GB2-05":1354.5945266252224,"GB2-08":1448.1797497732612}},"per_game_tracks":{"highest":{"GB2-01":51.81286686979948,"GB2-02":20.82093118555568,"GB2-04":17.993252641418948,"GB2-05":51.2770740935357,"GB2-06":28.544824407056506,"GB2-07":31.031275607799287,"GB2-08":26.439052410696952},"none":{"GB2-01":72.6465473220185,"GB2-02":26.272777344588157,"GB2-03":37.16178607693494,"GB2-04":39.60853817575416,"GB2-05":29.9170413033881,"GB2-08":28.903404995054014}},"provider_color":"#12B7F5","provider_company":"Tencent","provider_key":"tencent","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":27.64757882677474,"none":36.37270568635381},"reasoning_agg":{"highest":{"max":51.81286686979948,"mean":27.64757882677474,"min":17.993252641418948},"none":{"max":72.6465473220185,"mean":36.37270568635381,"min":26.272777344588157}},"reasoning_labels":{"highest":"High","medium":"Setting not tested","none":"None"},"score_diagnostics":{"ceiling_score":72.6465473220185,"reasoning_variance":8.72512685957907},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":51.81286686979948,"expected_score":17.237788590059708,"reliability_score":58.57598198974495,"uncertainty_avg":41.42401801025505,"uncertainty_penalty":-10.409790236715033},"none":{"ceiling_score":72.6465473220185,"expected_score":38.298564610478145,"reliability_score":84.6673167874253,"uncertainty_avg":15.3326832125747,"uncertainty_penalty":1.9258589241243342}}},{"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":0.101332462},"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":31.020399913862235,"highest":33.71387606868023,"medium":33.40505179177216,"none":31.59151533816022},"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":"2026-07-27T16:02:23Z","match_totals_all":{"draws":451,"losses":343,"wins":244},"match_totals_tracks":{"highest":{"draws":150,"losses":104,"wins":80},"medium":{"draws":180,"losses":116,"wins":84},"none":{"draws":121,"losses":123,"wins":80}},"model_slug":"openai-gpt-oss-120b","overall":{"max":61.50686447534633,"mean":31.292055103935187,"min":11.042241208882738},"per_game":{"GB2-02":18.82577587485795,"GB2-04":27.837372334700223,"GB2-06":61.50686447534633,"GB2-07":34.91319206814089,"GB2-08":25.48617559035576},"per_game_all":{"GB2-02":25.784317412864237,"GB2-04":23.245476820935554,"GB2-06":48.576273000589474,"GB2-08":26.475532421059665},"per_game_match_totals_all":{"GB2-01":{"draws":29,"losses":40,"wins":29},"GB2-02":{"draws":144,"losses":11,"wins":1},"GB2-03":{"draws":52,"losses":19,"wins":11},"GB2-04":{"draws":85,"losses":30,"wins":15},"GB2-05":{"draws":0,"losses":51,"wins":53},"GB2-06":{"draws":5,"losses":103,"wins":86},"GB2-07":{"draws":0,"losses":64,"wins":38},"GB2-08":{"draws":136,"losses":25,"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":50,"losses":3,"wins":1},"GB2-03":{"draws":28,"losses":11,"wins":7},"GB2-04":{"draws":38,"losses":4,"wins":4},"GB2-05":{"draws":0,"losses":29,"wins":33},"GB2-06":{"draws":1,"losses":37,"wins":20},"GB2-08":{"draws":45,"losses":10,"wins":3}},"none":{"GB2-01":{"draws":11,"losses":18,"wins":13},"GB2-02":{"draws":41,"losses":1,"wins":0},"GB2-03":{"draws":24,"losses":8,"wins":4},"GB2-04":{"draws":11,"losses":12,"wins":1},"GB2-05":{"draws":0,"losses":22,"wins":20},"GB2-06":{"draws":1,"losses":33,"wins":24},"GB2-07":{"draws":0,"losses":24,"wins":16},"GB2-08":{"draws":33,"losses":5,"wins":2}}},"per_game_raw_elo_all":{"GB2-02":1477.9951864686682,"GB2-04":1453.1547054645926,"GB2-06":1473.710207153236,"GB2-08":1448.1344500633613},"per_game_raw_elo_tracks":{"highest":{"GB2-02":1458.505213110513,"GB2-04":1478.2980270082412,"GB2-06":1580.710166277599,"GB2-07":1419.2392931700497,"GB2-08":1447.3808697764316},"medium":{"GB2-01":1405.3393264056997,"GB2-02":1485.1407076693067,"GB2-03":1431.1372881816976,"GB2-04":1479.5119436507632,"GB2-05":1444.0802873129855,"GB2-06":1362.013744309396,"GB2-08":1462.8759114421637},"none":{"GB2-01":1401.3232146087823,"GB2-02":1490.3396386261843,"GB2-03":1467.5326664526883,"GB2-04":1401.6541457347726,"GB2-05":1403.3905933062547,"GB2-06":1478.406710872713,"GB2-07":1389.7423245669345,"GB2-08":1434.1465689714887}},"per_game_tracks":{"highest":{"GB2-02":18.82577587485795,"GB2-04":27.837372334700223,"GB2-06":61.50686447534633,"GB2-07":34.91319206814089,"GB2-08":25.48617559035576},"medium":{"GB2-01":35.427216277491794,"GB2-02":29.486147225977007,"GB2-03":34.34188785207999,"GB2-04":30.856816919223707,"GB2-05":39.3681250027,"GB2-06":34.35881917136978,"GB2-08":29.996350093562853},"none":{"GB2-01":33.87536426896172,"GB2-02":29.041029137757743,"GB2-03":39.2217430159087,"GB2-04":11.042241208882738,"GB2-05":33.3847722466155,"GB2-06":49.8631353550523,"GB2-07":32.35976589284266,"GB2-08":23.944071579260378}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":29.976345822769012,"medium":32.308304150876324,"none":31.591515338160217},"reasoning_agg":{"highest":{"max":61.50686447534633,"mean":29.976345822769012,"min":18.82577587485795},"medium":{"max":39.3681250027,"mean":32.308304150876324,"min":29.486147225977007},"none":{"max":49.8631353550523,"mean":31.591515338160217,"min":11.042241208882738}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"score_diagnostics":{"ceiling_score":61.50686447534633,"expected_score":20.59382574969612,"reasoning_variance":2.331958328107312,"reliability_score":65.73628195549608,"uncertainty_avg":34.26371804450392,"uncertainty_penalty":-10.698229354239068},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":61.50686447534633,"expected_score":20.8188188693715,"reliability_score":56.50507191835876,"uncertainty_avg":43.49492808164124,"uncertainty_penalty":-9.157526953397511},"medium":{"ceiling_score":39.3681250027,"expected_score":22.288899712198006,"reliability_score":76.22220208383342,"uncertainty_avg":23.777797916166577,"uncertainty_penalty":-10.019404438678318},"none":{"ceiling_score":49.8631353550523,"expected_score":27.795246627185605,"reliability_score":64.72305418367455,"uncertainty_avg":35.27694581632546,"uncertainty_penalty":-3.796268710974612}}},{"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":36.40192171448114,"none":32.14193352522236},"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":"2026-07-27T15:58:42Z","match_totals_all":{"draws":153,"losses":262,"wins":191},"match_totals_tracks":{"medium":{"draws":47,"losses":110,"wins":83},"none":{"draws":106,"losses":152,"wins":108}},"model_slug":"google-gemma-4-31b-it","overall":{"max":44.39699646208931,"mean":31.288086375992073,"min":22.18853644184757},"per_game_match_totals_all":{"GB2-01":{"draws":18,"losses":26,"wins":32},"GB2-04":{"draws":88,"losses":13,"wins":9},"GB2-05":{"draws":0,"losses":72,"wins":52},"GB2-06":{"draws":2,"losses":74,"wins":42},"GB2-07":{"draws":0,"losses":67,"wins":55},"GB2-08":{"draws":45,"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":40,"wins":18},"GB2-07":{"draws":0,"losses":30,"wins":32}},"none":{"GB2-01":{"draws":18,"losses":26,"wins":32},"GB2-04":{"draws":43,"losses":5,"wins":4},"GB2-05":{"draws":0,"losses":40,"wins":24},"GB2-06":{"draws":0,"losses":34,"wins":24},"GB2-07":{"draws":0,"losses":37,"wins":23},"GB2-08":{"draws":45,"losses":10,"wins":1}}},"per_game_raw_elo_tracks":{"medium":{"GB2-04":1485.9817668716055,"GB2-05":1503.0329976276387,"GB2-06":1374.3434018681119,"GB2-07":1453.2959606735676},"none":{"GB2-01":1467.5007886172232,"GB2-04":1489.2296172501635,"GB2-05":1296.022394286137,"GB2-06":1390.6201022386813,"GB2-07":1350.8159516092887,"GB2-08":1436.727549023724}},"per_game_tracks":{"medium":{"GB2-04":29.166360289073122,"GB2-05":43.730006809943795,"GB2-06":33.35319203148646,"GB2-07":39.35812772742118},"none":{"GB2-01":44.39699646208931,"GB2-04":33.4691324962955,"GB2-05":22.18853644184757,"GB2-06":38.16937604000977,"GB2-07":28.816413152201964,"GB2-08":25.811146558890066}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#f5f9ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":31.64935029638511,"none":30.926822455599037},"reasoning_agg":{"medium":{"max":43.730006809943795,"mean":31.64935029638511,"min":29.166360289073122},"none":{"max":44.39699646208931,"mean":30.926822455599037,"min":22.18853644184757}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"score_diagnostics":{"ceiling_score":44.39699646208931,"reasoning_variance":0.7225278407860714},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":43.730006809943795,"expected_score":35.15384146767791,"reliability_score":53.56732431335594,"uncertainty_avg":46.43267568664406,"uncertainty_penalty":3.5044911712927984},"none":{"ceiling_score":44.39699646208931,"expected_score":31.26127351370477,"reliability_score":79.91375819852003,"uncertainty_avg":20.086241801479975,"uncertainty_penalty":0.3344510581057314}}},{"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":27.867639901120743,"none":37.66403487978772},"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":"2026-07-27T16:02:00Z","match_totals_all":{"draws":230,"losses":311,"wins":197},"match_totals_tracks":{"medium":{"draws":49,"losses":172,"wins":79},"none":{"draws":181,"losses":139,"wins":118}},"model_slug":"nex-agi-nex-n2-pro","overall":{"max":69.71683172233598,"mean":31.2211300005294,"min":1.8004338185596558},"per_game_match_totals_all":{"GB2-02":{"draws":47,"losses":5,"wins":2},"GB2-03":{"draws":61,"losses":25,"wins":14},"GB2-04":{"draws":51,"losses":3,"wins":2},"GB2-05":{"draws":0,"losses":90,"wins":60},"GB2-06":{"draws":9,"losses":84,"wins":41},"GB2-07":{"draws":0,"losses":57,"wins":73},"GB2-08":{"draws":62,"losses":47,"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":41,"wins":20},"GB2-07":{"draws":0,"losses":35,"wins":27},"GB2-08":{"draws":12,"losses":40,"wins":4}},"none":{"GB2-02":{"draws":47,"losses":5,"wins":2},"GB2-03":{"draws":31,"losses":13,"wins":6},"GB2-04":{"draws":51,"losses":3,"wins":2},"GB2-05":{"draws":0,"losses":46,"wins":40},"GB2-06":{"draws":2,"losses":43,"wins":21},"GB2-07":{"draws":0,"losses":22,"wins":46},"GB2-08":{"draws":50,"losses":7,"wins":1}}},"per_game_raw_elo_tracks":{"medium":{"GB2-03":1486.0826808498505,"GB2-05":1360.074507007328,"GB2-06":1352.265412750451,"GB2-07":1450.3195981523795,"GB2-08":1303.3511651122055},"none":{"GB2-02":1471.4715871938947,"GB2-03":1423.1096514863327,"GB2-04":1491.0471982021531,"GB2-05":1467.516113452013,"GB2-06":1329.3201234614855,"GB2-07":1667.1651313142668,"GB2-08":1441.5298755363042}},"per_game_tracks":{"medium":{"GB2-03":40.20162634486448,"GB2-05":27.32514751690616,"GB2-06":30.979620323137993,"GB2-07":39.03137150213544,"GB2-08":1.8004338185596558},"none":{"GB2-02":26.222888398882304,"GB2-03":33.38334591324993,"GB2-04":34.22189995892514,"GB2-05":42.97799867637564,"GB2-06":30.43111022257915,"GB2-07":69.71683172233598,"GB2-08":26.69416926616589}},"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":24.778225121271074,"none":37.66403487978772},"reasoning_agg":{"medium":{"max":40.20162634486448,"mean":24.778225121271074,"min":1.8004338185596558},"none":{"max":69.71683172233598,"mean":37.66403487978772,"min":26.222888398882304}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"score_diagnostics":{"ceiling_score":69.71683172233598,"reasoning_variance":12.885809758516647},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":40.20162634486448,"expected_score":18.255658610805476,"reliability_score":53.355705500961044,"uncertainty_avg":46.644294499038956,"uncertainty_penalty":-6.522566510465598},"none":{"ceiling_score":69.71683172233598,"expected_score":37.886765469979366,"reliability_score":80.3730943922406,"uncertainty_avg":19.626905607759397,"uncertainty_penalty":0.2227305901916452}}},{"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":0.46841705000000006},"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":39.112187867238255,"highest":30.576379686069668,"medium":33.91999537453004,"none":35.68218931552467},"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":"2026-07-27T15:57:36Z","match_totals_all":{"draws":506,"losses":417,"wins":270},"match_totals_tracks":{"highest":{"draws":294,"losses":193,"wins":106},"medium":{"draws":114,"losses":110,"wins":78},"none":{"draws":98,"losses":114,"wins":86}},"model_slug":"nvidia-nemotron-3-ultra-550b-a55b","overall":{"max":60.49902848103273,"mean":29.579426535796316,"min":5.6844327646508575},"per_game":{"GB2-01":31.28492958888438,"GB2-02":25.35927855243578,"GB2-04":24.588513823342623,"GB2-05":32.441158944802936,"GB2-06":45.237594115915286,"GB2-08":24.546803091037},"per_game_all":{"GB2-01":44.958619817724845,"GB2-06":46.66191163704803,"GB2-08":25.71603214694191},"per_game_match_totals_all":{"GB2-01":{"draws":43,"losses":72,"wins":55},"GB2-02":{"draws":167,"losses":12,"wins":3},"GB2-03":{"draws":18,"losses":9,"wins":3},"GB2-04":{"draws":79,"losses":15,"wins":8},"GB2-05":{"draws":0,"losses":106,"wins":80},"GB2-06":{"draws":8,"losses":85,"wins":78},"GB2-07":{"draws":0,"losses":79,"wins":27},"GB2-08":{"draws":191,"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":89,"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":26},"GB2-02":{"draws":54,"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":29,"losses":6,"wins":5},"GB2-05":{"draws":0,"losses":17,"wins":33},"GB2-06":{"draws":0,"losses":26,"wins":18},"GB2-07":{"draws":0,"losses":34,"wins":10},"GB2-08":{"draws":40,"losses":5,"wins":1}}},"per_game_raw_elo_all":{"GB2-01":1486.4220997763712,"GB2-06":1462.058512403664,"GB2-08":1442.3995153492624},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1392.190176438217,"GB2-02":1484.9285932914202,"GB2-04":1460.4221707921552,"GB2-05":1402.3047231017686,"GB2-06":1460.8609860751917,"GB2-08":1442.0502690810122},"medium":{"GB2-01":1514.38343795476,"GB2-02":1478.792058417232,"GB2-06":1556.571475807063,"GB2-07":1169.348522168338,"GB2-08":1432.7695118803483},"none":{"GB2-01":1552.6926849361364,"GB2-03":1419.179191434123,"GB2-04":1495.9339395098796,"GB2-05":1540.701516438078,"GB2-06":1368.7430753287372,"GB2-07":1299.8016849909914,"GB2-08":1452.3787650864267}},"per_game_tracks":{"highest":{"GB2-01":31.28492958888438,"GB2-02":25.35927855243578,"GB2-04":24.588513823342623,"GB2-05":32.441158944802936,"GB2-06":45.237594115915286,"GB2-08":24.546803091037},"medium":{"GB2-01":50.01923123018594,"GB2-02":28.19843674091044,"GB2-06":60.49902848103273,"GB2-07":5.6844327646508575,"GB2-08":25.19884765587022},"none":{"GB2-01":53.57169863410424,"GB2-03":30.055991271142776,"GB2-04":33.30566532198333,"GB2-05":49.983757275316115,"GB2-06":34.249112314196054,"GB2-07":21.20665469801167,"GB2-08":27.40244569391851}},"provider_color":"#76B900","provider_company":"NVIDIA","provider_key":"nvidia","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":23.771600760331932,"medium":29.284489531532348,"none":35.68218931552467},"reasoning_agg":{"highest":{"max":32.441158944802936,"mean":23.771600760331932,"min":24.546803091037},"medium":{"max":60.49902848103273,"mean":29.284489531532348,"min":5.6844327646508575},"none":{"max":53.57169863410424,"mean":35.68218931552467,"min":21.20665469801167}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Reasoning disabled"},"score_diagnostics":{"ceiling_score":60.49902848103273,"expected_score":29.480899543020445,"reasoning_variance":11.910588555192735,"reliability_score":69.09259770316645,"uncertainty_avg":30.907402296833553,"uncertainty_penalty":-0.09852699277587007},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":32.441158944802936,"expected_score":15.314942632261086,"reliability_score":56.78416519891102,"uncertainty_avg":43.21583480108898,"uncertainty_penalty":-8.456658128070845},"medium":{"ceiling_score":60.49902848103273,"expected_score":25.580947108110088,"reliability_score":79.84477688912011,"uncertainty_avg":20.15522311087988,"uncertainty_penalty":-3.7035424234222596},"none":{"ceiling_score":53.57169863410424,"expected_score":37.86507158791403,"reliability_score":67.40102433456897,"uncertainty_avg":32.598975665431034,"uncertainty_penalty":2.1828822723893637}}},{"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":28.305522382399136,"none":29.01342976630495},"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":"2026-07-27T15:59:11Z","match_totals_all":{"draws":389,"losses":353,"wins":158},"match_totals_tracks":{"medium":{"draws":84,"losses":130,"wins":68},"none":{"draws":305,"losses":223,"wins":90}},"model_slug":"inclusionai-ling-3-0-flash","overall":{"max":44.48159231995547,"mean":27.92327960793142,"min":18.886821253244385},"per_game_match_totals_all":{"GB2-01":{"draws":49,"losses":75,"wins":42},"GB2-02":{"draws":93,"losses":7,"wins":2},"GB2-03":{"draws":38,"losses":45,"wins":17},"GB2-04":{"draws":92,"losses":10,"wins":2},"GB2-06":{"draws":4,"losses":148,"wins":56},"GB2-07":{"draws":0,"losses":45,"wins":35},"GB2-08":{"draws":113,"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":38},"GB2-02":{"draws":60,"losses":2,"wins":0},"GB2-03":{"draws":38,"losses":45,"wins":17},"GB2-04":{"draws":56,"losses":5,"wins":1},"GB2-06":{"draws":3,"losses":95,"wins":30},"GB2-08":{"draws":113,"losses":23,"wins":4}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1301.2264010041774,"GB2-02":1466.7957048023695,"GB2-04":1449.9467799653128,"GB2-06":1342.3506475607678,"GB2-07":1471.9282613982693},"none":{"GB2-01":1472.5771573742084,"GB2-02":1472.6963835500655,"GB2-03":1388.0705798788917,"GB2-04":1475.5058004589516,"GB2-06":1243.4193512828674,"GB2-08":1420.9833201414342}},"per_game_tracks":{"medium":{"GB2-01":20.778009667965605,"GB2-02":23.06938008129636,"GB2-04":24.44151957954682,"GB2-06":30.355022200771856,"GB2-07":42.88368038241504},"none":{"GB2-01":44.48159231995547,"GB2-02":27.360571887099717,"GB2-03":27.48358424139654,"GB2-04":31.642255258124266,"GB2-06":18.886821253244385,"GB2-08":24.225753638009312}},"provider_color":"#1677FF","provider_company":"InclusionAI","provider_key":"inclusionai","provider_text_color":"#f8fbff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":30.266509720644656,"none":25.58004949521818},"reasoning_agg":{"medium":{"max":42.88368038241504,"mean":30.266509720644656,"min":30.355022200771856},"none":{"max":44.48159231995547,"mean":25.58004949521818,"min":18.886821253244385}},"reasoning_labels":{"highest":"Setting not tested","medium":"Enabled","none":"None"},"score_diagnostics":{"ceiling_score":44.48159231995547,"reasoning_variance":4.686460225426476},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":42.88368038241504,"expected_score":14.399164304668517,"reliability_score":66.0306382112971,"uncertainty_avg":33.9693617887029,"uncertainty_penalty":-15.86734541597614},"none":{"ceiling_score":44.48159231995547,"expected_score":18.80316249074347,"reliability_score":80.43266074785542,"uncertainty_avg":19.567339252144578,"uncertainty_penalty":-6.776887004474709}}},{"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":32.46627609691285,"none":27.452125767440133},"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":"2026-07-27T16:02:12Z","match_totals_all":{"draws":228,"losses":308,"wins":162},"match_totals_tracks":{"medium":{"draws":112,"losses":144,"wins":98},"none":{"draws":116,"losses":164,"wins":64}},"model_slug":"cohere-north-mini-code","overall":{"max":43.2871495944819,"mean":25.20969046694418,"min":19.585628377608835},"per_game_match_totals_all":{"GB2-01":{"draws":65,"losses":58,"wins":17},"GB2-03":{"draws":23,"losses":19,"wins":8},"GB2-04":{"draws":37,"losses":7,"wins":4},"GB2-05":{"draws":0,"losses":31,"wins":37},"GB2-06":{"draws":1,"losses":41,"wins":18},"GB2-07":{"draws":0,"losses":130,"wins":74},"GB2-08":{"draws":102,"losses":22,"wins":4}},"per_game_match_totals_tracks":{"medium":{"GB2-03":{"draws":23,"losses":19,"wins":8},"GB2-04":{"draws":37,"losses":7,"wins":4},"GB2-05":{"draws":0,"losses":31,"wins":37},"GB2-06":{"draws":1,"losses":41,"wins":18},"GB2-07":{"draws":0,"losses":33,"wins":31},"GB2-08":{"draws":51,"losses":13,"wins":0}},"none":{"GB2-01":{"draws":65,"losses":58,"wins":17},"GB2-07":{"draws":0,"losses":97,"wins":43},"GB2-08":{"draws":51,"losses":9,"wins":4}}},"per_game_raw_elo_tracks":{"medium":{"GB2-03":1435.8441074111074,"GB2-04":1484.0486581975179,"GB2-05":1469.4451277035857,"GB2-06":1369.2096633702972,"GB2-07":1482.628492568711,"GB2-08":1413.1341743107275},"none":{"GB2-01":1338.5463193317332,"GB2-07":1329.1995227607263,"GB2-08":1449.4863124214994}},"per_game_tracks":{"medium":{"GB2-03":31.68336617958372,"GB2-04":27.292620478258247,"GB2-05":40.279547984289245,"GB2-06":32.66934396725515,"GB2-07":43.2871495944819,"GB2-08":19.585628377608835},"none":{"GB2-01":27.522770043194065,"GB2-07":26.527781627163414,"GB2-08":28.305825631962907}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":30.21327429273744,"none":20.206106641150914},"reasoning_agg":{"medium":{"max":43.2871495944819,"mean":30.21327429273744,"min":19.585628377608835},"none":{"max":27.522770043194065,"mean":20.206106641150914,"min":26.527781627163414}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"score_diagnostics":{"ceiling_score":43.2871495944819,"reasoning_variance":10.007167651586528},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":43.2871495944819,"expected_score":27.789765150841856,"reliability_score":52.255038833100514,"uncertainty_avg":47.744961166899486,"uncertainty_penalty":-2.423509141895586},"none":{"ceiling_score":27.522770043194065,"expected_score":15.58169841098767,"reliability_score":83.51226657507605,"uncertainty_avg":16.487733424923945,"uncertainty_penalty":-4.624408230163244}}},{"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":0.07321124999999999}},"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":0.28445375000000006},"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":24.339855677781387,"highest":27.04212337597506,"medium":29.49097663317166,"none":23.538864797348662},"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":"2026-07-27T15:54:40Z","match_totals_all":{"draws":256,"losses":444,"wins":213},"match_totals_tracks":{"highest":{"draws":106,"losses":169,"wins":64},"medium":{"draws":92,"losses":164,"wins":100},"none":{"draws":58,"losses":111,"wins":49}},"model_slug":"google-gemini-3-1-flash-lite","overall":{"max":41.996828952531544,"mean":25.00917885115301,"min":0.0},"per_game":{"GB2-04":26.30965713552444,"GB2-05":16.251044990851373,"GB2-06":30.791817765880385,"GB2-07":37.72719101235718,"GB2-08":24.13090597526191},"per_game_all":{"GB2-05":20.828021333947053,"GB2-06":37.54521433096439,"GB2-07":14.646331368432714},"per_game_match_totals_all":{"GB2-01":{"draws":52,"losses":33,"wins":19},"GB2-02":{"draws":34,"losses":3,"wins":1},"GB2-04":{"draws":75,"losses":8,"wins":7},"GB2-05":{"draws":0,"losses":123,"wins":53},"GB2-06":{"draws":1,"losses":104,"wins":68},"GB2-07":{"draws":0,"losses":136,"wins":38},"GB2-08":{"draws":94,"losses":37,"wins":27}},"per_game_match_totals_tracks":{"highest":{"GB2-04":{"draws":37,"losses":6,"wins":3},"GB2-05":{"draws":0,"losses":54,"wins":10},"GB2-06":{"draws":0,"losses":50,"wins":23},"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":38,"losses":2,"wins":4},"GB2-05":{"draws":0,"losses":37,"wins":27},"GB2-06":{"draws":0,"losses":35,"wins":23},"GB2-07":{"draws":0,"losses":46,"wins":10},"GB2-08":{"draws":25,"losses":28,"wins":23}},"none":{"GB2-01":{"draws":23,"losses":17,"wins":6},"GB2-02":{"draws":34,"losses":3,"wins":1},"GB2-05":{"draws":0,"losses":32,"wins":16},"GB2-06":{"draws":1,"losses":19,"wins":22},"GB2-07":{"draws":0,"losses":40,"wins":4}}},"per_game_raw_elo_all":{"GB2-05":1293.8359281436758,"GB2-06":1393.3368583062681,"GB2-07":1248.1124519433158},"per_game_raw_elo_tracks":{"highest":{"GB2-04":1481.351636088787,"GB2-05":1266.0234481385794,"GB2-06":1348.51918938241,"GB2-07":1434.0948620707277,"GB2-08":1434.7246740268902},"medium":{"GB2-01":1455.3793905117934,"GB2-04":1496.4002724512168,"GB2-05":1318.8709361070892,"GB2-06":1407.6659693492472,"GB2-07":1176.0530232290791,"GB2-08":1453.0417625819548},"none":{"GB2-01":1337.399703918666,"GB2-02":1492.955126495349,"GB2-05":1296.6134001853593,"GB2-06":1423.8254161871469,"GB2-07":1134.1894705301404}},"per_game_tracks":{"highest":{"GB2-04":26.30965713552444,"GB2-05":16.251044990851373,"GB2-06":30.791817765880385,"GB2-07":37.72719101235718,"GB2-08":24.13090597526191},"medium":{"GB2-01":41.996828952531544,"GB2-04":33.96421938799026,"GB2-05":24.85378503399073,"GB2-06":40.43999875124963,"GB2-07":6.21180309294096,"GB2-08":29.47922458032685},"none":{"GB2-01":25.974404110127313,"GB2-02":28.936859423853782,"GB2-05":21.379233976999053,"GB2-06":41.40382647576317,"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":24.044225601614347,"medium":27.44444615449602,"none":23.538864797348662},"reasoning_agg":{"highest":{"max":37.72719101235718,"mean":24.044225601614347,"min":16.251044990851373},"medium":{"max":41.996828952531544,"mean":27.44444615449602,"min":6.21180309294096},"none":{"max":41.40382647576317,"mean":23.538864797348662,"min":0.0}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Reasoning disabled"},"score_diagnostics":{"ceiling_score":41.996828952531544,"expected_score":14.510973843478297,"reasoning_variance":3.9055813571473585,"reliability_score":69.69145024861942,"uncertainty_avg":30.308549751380582,"uncertainty_penalty":-10.498205007674713},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":37.72719101235718,"expected_score":10.855116530051788,"reliability_score":57.33946852650763,"uncertainty_avg":42.66053147349237,"uncertainty_penalty":-13.189109071562559},"medium":{"ceiling_score":41.996828952531544,"expected_score":23.622402514383523,"reliability_score":78.75853606525129,"uncertainty_avg":21.241463934748708,"uncertainty_penalty":-3.822043640112497},"none":{"ceiling_score":41.40382647576317,"expected_score":17.696300578616462,"reliability_score":68.70799430072849,"uncertainty_avg":31.292005699271517,"uncertainty_penalty":-5.8425642187322}}},{"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":1.7932034999999995},"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":21.868711903025034,"none":32.67062590477188},"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":"2026-07-27T16:02:00Z","match_totals_all":{"draws":83,"losses":325,"wins":151},"match_totals_tracks":{"highest":{"draws":19,"losses":195,"wins":64},"none":{"draws":64,"losses":130,"wins":87}},"model_slug":"mistralai-mistral-medium-3-5","overall":{"max":38.2909369413615,"mean":22.66417035276561,"min":15.499927748138223},"per_game":{"GB2-01":24.776628277424983,"GB2-05":18.284916786321382,"GB2-06":28.913374800215543,"GB2-07":15.499927748138223},"per_game_match_totals_all":{"GB2-01":{"draws":25,"losses":77,"wins":35},"GB2-05":{"draws":0,"losses":105,"wins":57},"GB2-06":{"draws":5,"losses":79,"wins":48},"GB2-07":{"draws":0,"losses":59,"wins":11},"GB2-08":{"draws":53,"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":40,"wins":21},"GB2-05":{"draws":0,"losses":51,"wins":41},"GB2-06":{"draws":5,"losses":34,"wins":25},"GB2-08":{"draws":53,"losses":5,"wins":0}}},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1336.60640070509,"GB2-05":1279.784860201679,"GB2-06":1336.670844139026,"GB2-07":1262.4479943480187},"none":{"GB2-01":1404.142971092423,"GB2-05":1425.928615167466,"GB2-06":1330.3542233252822,"GB2-08":1437.5092940470956}},"per_game_tracks":{"highest":{"GB2-01":24.776628277424983,"GB2-05":18.284916786321382,"GB2-06":28.913374800215543,"GB2-07":15.499927748138223},"none":{"GB2-01":35.8499002021569,"GB2-05":38.2909369413615,"GB2-06":30.469471573505537,"GB2-08":26.072194902063597}},"provider_color":"#FF7000","provider_company":"Mistral","provider_key":"mistral","provider_text_color":"#fff8f3","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":17.8557284981134,"none":27.472612207417818},"reasoning_agg":{"highest":{"max":28.913374800215543,"mean":17.8557284981134,"min":15.499927748138223},"none":{"max":38.2909369413615,"mean":27.472612207417818,"min":26.072194902063597}},"reasoning_labels":{"highest":"High","medium":"Setting not tested","none":"None"},"score_diagnostics":{"ceiling_score":38.2909369413615,"reasoning_variance":9.616883709304417},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":28.913374800215543,"expected_score":2.2618109255188754,"reliability_score":59.9575543016399,"uncertainty_avg":40.0424456983601,"uncertainty_penalty":-15.593917572594524},"none":{"ceiling_score":38.2909369413615,"expected_score":23.73908269989362,"reliability_score":83.85167155484484,"uncertainty_avg":16.148328445155165,"uncertainty_penalty":-3.7335295075241994}}}],"public_release_id":"gb2-20260727-4d94e2ae1be2","results_cut_id":"gb2-20260727-4d94e2ae1be2","snapshot_id":"20260727_194501","suite_line_id":"gamebench2","suite_version":"2-known8-r3","version_display":"2026-07-27 19:45 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":20,"losses":32,"wins":34},"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":9,"losses":6,"wins":23},"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":1,"losses":1,"wins":2},"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":2,"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":15,"losses":2,"wins":7},"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":13,"losses":5,"wins":16},"gpt-5.4-nano":{"draws":13,"losses":9,"wins":18},"gpt-5.5":{"draws":7,"losses":3,"wins":2},"gpt-5.6-luna":{"draws":9,"losses":1,"wins":6},"gpt-5.6-sol":{"draws":6,"losses":9,"wins":3},"gpt-5.6-terra":{"draws":9,"losses":6,"wins":7},"meituan/longcat-2.0":{"draws":4,"losses":1,"wins":3},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":4},"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":3},"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":12,"losses":6,"wins":12},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":7,"wins":3},"z-ai/glm-5.2":{"draws":2,"losses":8,"wins":12}},"claude-opus-4-8":{"claude-fable-5":{"draws":2,"losses":15,"wins":13},"claude-opus-4-5":{"draws":5,"losses":7,"wins":24},"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":13,"wins":22},"cohere/north-mini-code":{"draws":5,"losses":2,"wins":5},"deepseek/deepseek-v4-flash":{"draws":15,"losses":9,"wins":26},"deepseek/deepseek-v4-pro":{"draws":9,"losses":10,"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":8},"google/gemini-3.6-flash":{"draws":4,"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":24,"losses":20,"wins":34},"gpt-5.4-nano":{"draws":20,"losses":20,"wins":44},"gpt-5.5":{"draws":10,"losses":23,"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},"inclusionai/ling-3.0-flash":{"draws":1,"losses":0,"wins":1},"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":25,"losses":28,"wins":27},"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":8,"wins":17},"openai/gpt-oss-120b":{"draws":8,"losses":6,"wins":8},"poolside/laguna-s-2.1":{"draws":0,"losses":1,"wins":5},"qwen/qwen3.7-max":{"draws":2,"losses":9,"wins":11},"qwen/qwen3.7-plus":{"draws":6,"losses":5,"wins":15},"stepfun/step-3.7-flash":{"draws":0,"losses":4,"wins":6},"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":41,"wins":29},"x-ai/grok-build-0.1":{"draws":6,"losses":6,"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":24,"wins":35}},"claude-opus-5":{"claude-fable-5":{"draws":20,"losses":34,"wins":32},"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":14,"losses":5,"wins":45},"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":4,"losses":2,"wins":10},"gpt-5.4":{"draws":12,"losses":26,"wins":34},"gpt-5.4-mini":{"draws":6,"losses":7,"wins":31},"gpt-5.4-nano":{"draws":9,"losses":12,"wins":47},"gpt-5.5":{"draws":7,"losses":19,"wins":28},"gpt-5.6-luna":{"draws":1,"losses":4,"wins":13},"gpt-5.6-sol":{"draws":16,"losses":18,"wins":44},"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":4},"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":6,"wins":18},"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":27,"losses":39,"wins":134},"x-ai/grok-build-0.1":{"draws":4,"losses":2,"wins":2},"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":16,"losses":11,"wins":63}},"claude-sonnet-5":{"claude-fable-5":{"draws":6,"losses":16,"wins":0},"claude-opus-4-5":{"draws":20,"losses":14,"wins":18},"claude-opus-4-8":{"draws":13,"losses":22,"wins":13},"claude-opus-5":{"draws":14,"losses":45,"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":25,"losses":12,"wins":23},"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":29,"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":5,"losses":0,"wins":7},"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":5,"losses":1,"wins":4},"moonshotai/kimi-k3":{"draws":19,"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":16},"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":3,"losses":1,"wins":10},"xiaomi/mimo-v2.5":{"draws":35,"losses":13,"wins":22},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":1,"wins":7},"z-ai/glm-5.2":{"draws":38,"losses":36,"wins":34}},"cohere/north-mini-code":{"claude-opus-4-5":{"draws":7,"losses":9,"wins":2},"claude-opus-4-8":{"draws":5,"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":8,"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":23,"wins":8},"gpt-5.4-nano":{"draws":22,"losses":29,"wins":17},"gpt-5.5":{"draws":11,"losses":4,"wins":1},"gpt-5.6-luna":{"draws":5,"losses":5,"wins":14},"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":16,"wins":1},"nex-agi/nex-n2-pro":{"draws":8,"losses":6,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":8,"wins":7},"o3":{"draws":3,"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":3,"losses":10,"wins":3},"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":39,"losses":17,"wins":10},"claude-opus-4-8":{"draws":15,"losses":26,"wins":9},"claude-opus-5":{"draws":3,"losses":1,"wins":0},"claude-sonnet-5":{"draws":25,"losses":23,"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":17,"losses":21,"wins":12},"google/gemini-3.1-flash-lite":{"draws":14,"losses":13,"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":18,"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":25,"wins":13},"gpt-5.4-mini":{"draws":82,"losses":68,"wins":42},"gpt-5.4-nano":{"draws":77,"losses":46,"wins":67},"gpt-5.5":{"draws":25,"losses":23,"wins":2},"gpt-5.6-luna":{"draws":39,"losses":18,"wins":19},"gpt-5.6-sol":{"draws":10,"losses":39,"wins":11},"gpt-5.6-terra":{"draws":20,"losses":46,"wins":14},"inclusionai/ling-3.0-flash":{"draws":10,"losses":6,"wins":10},"meituan/longcat-2.0":{"draws":8,"losses":5,"wins":5},"minimax/minimax-m3":{"draws":8,"losses":26,"wins":12},"mistralai/mistral-medium-3-5":{"draws":11,"losses":22,"wins":19},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":4,"wins":3},"moonshotai/kimi-k3":{"draws":32,"losses":51,"wins":11},"nex-agi/nex-n2-pro":{"draws":18,"losses":22,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":28,"losses":14,"wins":20},"o3":{"draws":11,"losses":29,"wins":12},"openai/gpt-oss-120b":{"draws":30,"losses":20,"wins":14},"poolside/laguna-s-2.1":{"draws":9,"losses":10,"wins":3},"qwen/qwen3.7-max":{"draws":18,"losses":18,"wins":8},"qwen/qwen3.7-plus":{"draws":17,"losses":15,"wins":14},"stepfun/step-3.7-flash":{"draws":20,"losses":24,"wins":20},"tencent/hy3-preview":{"draws":24,"losses":17,"wins":15},"thinkingmachines/inkling":{"draws":15,"losses":19,"wins":10},"x-ai/grok-4.5":{"draws":27,"losses":61,"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":18,"wins":16},"z-ai/glm-5.2":{"draws":47,"losses":55,"wins":42}},"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":10},"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":17,"losses":12,"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":6,"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":26},"gpt-5.4-nano":{"draws":23,"losses":19,"wins":26},"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":11,"losses":8,"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":7,"wins":4},"mistralai/mistral-medium-3-5":{"draws":2,"losses":2,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":1,"wins":3},"moonshotai/kimi-k3":{"draws":11,"losses":20,"wins":13},"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":9},"openai/gpt-oss-120b":{"draws":4,"losses":4,"wins":4},"poolside/laguna-s-2.1":{"draws":0,"losses":4,"wins":2},"qwen/qwen3.7-max":{"draws":9,"losses":6,"wins":7},"qwen/qwen3.7-plus":{"draws":4,"losses":0,"wins":4},"stepfun/step-3.7-flash":{"draws":7,"losses":2,"wins":13},"tencent/hy3-preview":{"draws":4,"losses":6,"wins":6},"thinkingmachines/inkling":{"draws":2,"losses":2,"wins":6},"x-ai/grok-4.5":{"draws":10,"losses":34,"wins":14},"x-ai/grok-build-0.1":{"draws":8,"losses":1,"wins":1},"xiaomi/mimo-v2.5":{"draws":9,"losses":8,"wins":13},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":6,"wins":5},"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":19,"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":13},"deepseek/deepseek-v4-pro":{"draws":4,"losses":2,"wins":2},"google/gemini-3.1-flash-lite":{"draws":0,"losses":10,"wins":10},"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":40,"wins":27},"gpt-5.5":{"draws":9,"losses":7,"wins":2},"gpt-5.6-luna":{"draws":9,"losses":8,"wins":11},"gpt-5.6-sol":{"draws":5,"losses":8,"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":8,"wins":6},"thinkingmachines/inkling":{"draws":7,"losses":9,"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":11,"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":5},"google/gemma-4-31b-it":{"draws":2,"losses":4,"wins":4},"gpt-4.1":{"draws":0,"losses":0,"wins":4},"gpt-5":{"draws":7,"losses":5,"wins":10},"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":22,"losses":23,"wins":17},"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":5,"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":8,"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":2},"gpt-5.4":{"draws":6,"losses":2,"wins":0},"gpt-5.4-mini":{"draws":13,"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":3,"wins":2},"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":5,"losses":4,"wins":7},"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":6,"losses":3,"wins":3},"tencent/hy3-preview":{"draws":4,"losses":2,"wins":4},"thinkingmachines/inkling":{"draws":71,"losses":82,"wins":81},"x-ai/grok-4.5":{"draws":59,"losses":110,"wins":35},"x-ai/grok-build-0.1":{"draws":0,"losses":3,"wins":3},"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":12,"wins":7}},"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":4,"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":5,"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":6,"losses":11,"wins":7},"gpt-5.4-mini":{"draws":12,"losses":6,"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":4,"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":39,"losses":66,"wins":79},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":4},"xiaomi/mimo-v2.5":{"draws":13,"losses":4,"wins":9},"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":8},"deepseek/deepseek-v4-flash":{"draws":13,"losses":15,"wins":18},"deepseek/deepseek-v4-pro":{"draws":6,"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":20,"wins":17},"gpt-5.4-nano":{"draws":12,"losses":20,"wins":20},"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":8,"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":7},"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":4,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":6,"wins":6},"o3":{"draws":4,"losses":7,"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":7,"wins":1},"thinkingmachines/inkling":{"draws":0,"losses":4,"wins":0},"x-ai/grok-4.5":{"draws":5,"losses":22,"wins":3},"x-ai/grok-build-0.1":{"draws":5,"losses":5,"wins":4},"xiaomi/mimo-v2.5":{"draws":2,"losses":12,"wins":14},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":6,"wins":4},"z-ai/glm-5.2":{"draws":7,"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":12,"wins":6},"gpt-5.4-nano":{"draws":4,"losses":8,"wins":6},"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":3,"wins":7},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":5,"wins":5},"z-ai/glm-5.2":{"draws":6,"losses":17,"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":4,"losses":10,"wins":2},"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":7,"losses":10,"wins":5},"google/gemini-3.5-flash-lite":{"draws":2,"losses":2,"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":4,"losses":2,"wins":2},"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":6,"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":20,"losses":12,"wins":8},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":3,"wins":6},"z-ai/glm-5.2":{"draws":25,"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":24},"claude-opus-4-8":{"draws":6,"losses":16,"wins":18},"claude-opus-5":{"draws":12,"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":13,"wins":25},"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":6,"losses":7,"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":41,"losses":21,"wins":56},"gpt-5.4-nano":{"draws":36,"losses":16,"wins":56},"gpt-5.5":{"draws":20,"losses":15,"wins":17},"gpt-5.6-luna":{"draws":24,"losses":4,"wins":22},"gpt-5.6-sol":{"draws":6,"losses":13,"wins":27},"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":3},"minimax/minimax-m3":{"draws":5,"losses":4,"wins":11},"mistralai/mistral-medium-3-5":{"draws":1,"losses":0,"wins":7},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":4,"wins":3},"moonshotai/kimi-k3":{"draws":18,"losses":18,"wins":44},"nex-agi/nex-n2-pro":{"draws":6,"losses":2,"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":3,"wins":11},"poolside/laguna-s-2.1":{"draws":0,"losses":2,"wins":2},"qwen/qwen3.7-max":{"draws":4,"losses":4,"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":31,"wins":58},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":23,"losses":5,"wins":22},"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":9,"losses":23,"wins":6},"claude-opus-4-5":{"draws":43,"losses":33,"wins":20},"claude-opus-4-8":{"draws":24,"losses":34,"wins":20},"claude-opus-5":{"draws":6,"losses":31,"wins":7},"claude-sonnet-5":{"draws":29,"losses":33,"wins":28},"cohere/north-mini-code":{"draws":17,"losses":8,"wins":23},"deepseek/deepseek-v4-flash":{"draws":82,"losses":42,"wins":68},"deepseek/deepseek-v4-pro":{"draws":22,"losses":26,"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":13,"losses":11,"wins":8},"google/gemini-3.6-flash":{"draws":12,"losses":10,"wins":6},"google/gemma-4-31b-it":{"draws":19,"losses":17,"wins":20},"gpt-4.1":{"draws":12,"losses":6,"wins":12},"gpt-5":{"draws":24,"losses":11,"wins":17},"gpt-5.4":{"draws":41,"losses":56,"wins":21},"gpt-5.4-mini":{"draws":104,"losses":76,"wins":76},"gpt-5.4-nano":{"draws":101,"losses":88,"wins":114},"gpt-5.5":{"draws":39,"losses":20,"wins":11},"gpt-5.6-luna":{"draws":47,"losses":33,"wins":32},"gpt-5.6-sol":{"draws":17,"losses":35,"wins":18},"gpt-5.6-terra":{"draws":55,"losses":45,"wins":30},"inclusionai/ling-3.0-flash":{"draws":6,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":7,"losses":10,"wins":13},"minimax/minimax-m3":{"draws":29,"losses":24,"wins":27},"mistralai/mistral-medium-3-5":{"draws":10,"losses":11,"wins":21},"moonshotai/kimi-k2.7-code":{"draws":9,"losses":18,"wins":5},"moonshotai/kimi-k3":{"draws":55,"losses":47,"wins":24},"nex-agi/nex-n2-pro":{"draws":19,"losses":13,"wins":26},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":45,"losses":18,"wins":23},"o3":{"draws":14,"losses":43,"wins":21},"openai/gpt-oss-120b":{"draws":30,"losses":26,"wins":26},"poolside/laguna-s-2.1":{"draws":7,"losses":6,"wins":9},"qwen/qwen3.7-max":{"draws":26,"losses":25,"wins":21},"qwen/qwen3.7-plus":{"draws":24,"losses":30,"wins":16},"stepfun/step-3.7-flash":{"draws":23,"losses":23,"wins":36},"tencent/hy3-preview":{"draws":21,"losses":12,"wins":23},"thinkingmachines/inkling":{"draws":18,"losses":16,"wins":14},"x-ai/grok-4.5":{"draws":54,"losses":102,"wins":26},"x-ai/grok-build-0.1":{"draws":3,"losses":12,"wins":9},"xiaomi/mimo-v2.5":{"draws":75,"losses":69,"wins":56},"xiaomi/mimo-v2.5-pro":{"draws":19,"losses":17,"wins":22},"z-ai/glm-5.2":{"draws":83,"losses":75,"wins":62}},"gpt-5.4-nano":{"claude-fable-5":{"draws":7,"losses":45,"wins":10},"claude-opus-4-5":{"draws":32,"losses":56,"wins":26},"claude-opus-4-8":{"draws":20,"losses":44,"wins":20},"claude-opus-5":{"draws":9,"losses":47,"wins":12},"claude-sonnet-5":{"draws":33,"losses":25,"wins":18},"cohere/north-mini-code":{"draws":22,"losses":17,"wins":29},"deepseek/deepseek-v4-flash":{"draws":77,"losses":67,"wins":46},"deepseek/deepseek-v4-pro":{"draws":23,"losses":26,"wins":19},"google/gemini-3.1-flash-lite":{"draws":17,"losses":27,"wins":40},"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":12,"losses":20,"wins":20},"gpt-4.1":{"draws":4,"losses":6,"wins":8},"gpt-5":{"draws":27,"losses":32,"wins":19},"gpt-5.4":{"draws":36,"losses":56,"wins":16},"gpt-5.4-mini":{"draws":101,"losses":114,"wins":88},"gpt-5.4-nano":{"draws":90,"losses":101,"wins":101},"gpt-5.5":{"draws":28,"losses":31,"wins":21},"gpt-5.6-luna":{"draws":42,"losses":33,"wins":39},"gpt-5.6-sol":{"draws":10,"losses":53,"wins":23},"gpt-5.6-terra":{"draws":38,"losses":29,"wins":35},"inclusionai/ling-3.0-flash":{"draws":17,"losses":8,"wins":3},"meituan/longcat-2.0":{"draws":13,"losses":15,"wins":18},"minimax/minimax-m3":{"draws":37,"losses":30,"wins":31},"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":51,"losses":75,"wins":43},"nex-agi/nex-n2-pro":{"draws":22,"losses":27,"wins":19},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":56,"losses":23,"wins":19},"o3":{"draws":23,"losses":23,"wins":30},"openai/gpt-oss-120b":{"draws":52,"losses":32,"wins":28},"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":13},"stepfun/step-3.7-flash":{"draws":24,"losses":21,"wins":23},"tencent/hy3-preview":{"draws":36,"losses":26,"wins":14},"thinkingmachines/inkling":{"draws":13,"losses":35,"wins":16},"x-ai/grok-4.5":{"draws":50,"losses":92,"wins":58},"x-ai/grok-build-0.1":{"draws":13,"losses":15,"wins":6},"xiaomi/mimo-v2.5":{"draws":86,"losses":68,"wins":60},"xiaomi/mimo-v2.5-pro":{"draws":24,"losses":31,"wins":21},"z-ai/glm-5.2":{"draws":86,"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":10,"losses":9,"wins":23},"claude-opus-5":{"draws":7,"losses":28,"wins":19},"claude-sonnet-5":{"draws":12,"losses":8,"wins":12},"cohere/north-mini-code":{"draws":11,"losses":1,"wins":4},"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":17,"wins":15},"gpt-5.4-mini":{"draws":39,"losses":11,"wins":20},"gpt-5.4-nano":{"draws":28,"losses":21,"wins":31},"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":17,"wins":21},"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":31},"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":7,"losses":2,"wins":11},"openai/gpt-oss-120b":{"draws":13,"losses":2,"wins":11},"poolside/laguna-s-2.1":{"draws":1,"losses":3,"wins":2},"qwen/qwen3.7-max":{"draws":9,"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":16,"losses":5,"wins":11},"thinkingmachines/inkling":{"draws":5,"losses":4,"wins":9},"x-ai/grok-4.5":{"draws":26,"losses":42,"wins":34},"x-ai/grok-build-0.1":{"draws":7,"losses":5,"wins":2},"xiaomi/mimo-v2.5":{"draws":27,"losses":7,"wins":12},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":7,"wins":5},"z-ai/glm-5.2":{"draws":27,"losses":20,"wins":27}},"gpt-5.6-luna":{"claude-fable-5":{"draws":2,"losses":16,"wins":2},"claude-opus-4-5":{"draws":20,"losses":16,"wins":16},"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":14,"wins":5},"deepseek/deepseek-v4-flash":{"draws":39,"losses":19,"wins":18},"deepseek/deepseek-v4-pro":{"draws":13,"losses":5,"wins":4},"google/gemini-3.1-flash-lite":{"draws":9,"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":4,"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":47,"losses":32,"wins":33},"gpt-5.4-nano":{"draws":42,"losses":39,"wins":33},"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":2,"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":9,"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":18,"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":11,"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":37,"losses":36,"wins":25}},"gpt-5.6-sol":{"claude-fable-5":{"draws":8,"losses":26,"wins":14},"claude-opus-4-5":{"draws":12,"losses":9,"wins":33},"claude-opus-4-8":{"draws":8,"losses":11,"wins":21},"claude-opus-5":{"draws":16,"losses":44,"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":10,"losses":11,"wins":39},"deepseek/deepseek-v4-pro":{"draws":2,"losses":7,"wins":13},"google/gemini-3.1-flash-lite":{"draws":5,"losses":3,"wins":8},"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":8},"gpt-4.1":{"draws":3,"losses":1,"wins":6},"gpt-5":{"draws":4,"losses":5,"wins":11},"gpt-5.4":{"draws":6,"losses":27,"wins":13},"gpt-5.4-mini":{"draws":17,"losses":18,"wins":35},"gpt-5.4-nano":{"draws":10,"losses":23,"wins":53},"gpt-5.5":{"draws":14,"losses":21,"wins":17},"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":12,"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":10},"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":4,"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":12,"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":6,"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":2,"losses":3,"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":12,"losses":9,"wins":13},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":3,"wins":10},"z-ai/glm-5.2":{"draws":23,"losses":24,"wins":43}},"gpt-5.6-terra":{"claude-fable-5":{"draws":5,"losses":25,"wins":4},"claude-opus-4-5":{"draws":18,"losses":14,"wins":24},"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":14,"wins":46},"deepseek/deepseek-v4-pro":{"draws":11,"losses":7,"wins":8},"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":55,"losses":30,"wins":45},"gpt-5.4-nano":{"draws":38,"losses":35,"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":12,"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":8,"losses":6,"wins":6},"mistralai/mistral-medium-3-5":{"draws":2,"losses":1,"wins":13},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":3,"wins":4},"moonshotai/kimi-k3":{"draws":34,"losses":32,"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":9,"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":8},"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":4},"x-ai/grok-4.5":{"draws":27,"losses":45,"wins":26},"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":6,"losses":5,"wins":3},"z-ai/glm-5.2":{"draws":27,"losses":26,"wins":27}},"inclusionai/ling-3.0-flash":{"claude-opus-4-5":{"draws":3,"losses":2,"wins":1},"claude-opus-4-8":{"draws":1,"losses":1,"wins":0},"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":6,"losses":2,"wins":0},"gpt-5.4-nano":{"draws":17,"losses":3,"wins":8},"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":5,"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":4},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":0,"wins":1},"z-ai/glm-5.2":{"draws":6,"losses":7,"wins":3}},"meituan/longcat-2.0":{"claude-fable-5":{"draws":1,"losses":2,"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":5,"losses":7,"wins":0},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":0},"deepseek/deepseek-v4-flash":{"draws":8,"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":4,"losses":2,"wins":2},"gpt-5.4":{"draws":1,"losses":3,"wins":0},"gpt-5.4-mini":{"draws":7,"losses":13,"wins":10},"gpt-5.4-nano":{"draws":13,"losses":18,"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":2,"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":5,"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":2,"wins":3},"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":12,"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":16,"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":12,"wins":26},"deepseek/deepseek-v4-pro":{"draws":3,"losses":4,"wins":7},"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":2,"wins":3},"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":29,"losses":27,"wins":24},"gpt-5.4-nano":{"draws":37,"losses":31,"wins":30},"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":8,"losses":6,"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":11,"losses":18,"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":6},"openai/gpt-oss-120b":{"draws":3,"losses":4,"wins":5},"qwen/qwen3.7-max":{"draws":6,"losses":8,"wins":6},"qwen/qwen3.7-plus":{"draws":4,"losses":5,"wins":7},"stepfun/step-3.7-flash":{"draws":2,"losses":3,"wins":7},"tencent/hy3-preview":{"draws":4,"losses":4,"wins":2},"thinkingmachines/inkling":{"draws":2,"losses":3,"wins":5},"x-ai/grok-4.5":{"draws":17,"losses":20,"wins":3},"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":5,"losses":9,"wins":6},"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":19,"wins":22},"deepseek/deepseek-v4-pro":{"draws":2,"losses":8,"wins":2},"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":7,"wins":5},"gpt-5":{"draws":0,"losses":6,"wins":2},"gpt-5.4":{"draws":1,"losses":7,"wins":0},"gpt-5.4-mini":{"draws":10,"losses":21,"wins":11},"gpt-5.4-nano":{"draws":9,"losses":19,"wins":18},"gpt-5.5":{"draws":2,"losses":4,"wins":0},"gpt-5.6-luna":{"draws":2,"losses":3,"wins":6},"gpt-5.6-sol":{"draws":0,"losses":10,"wins":0},"gpt-5.6-terra":{"draws":2,"losses":13,"wins":1},"inclusionai/ling-3.0-flash":{"draws":2,"losses":0,"wins":4},"meituan/longcat-2.0":{"draws":2,"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":25,"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":6,"losses":8,"wins":2},"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":10,"wins":0},"x-ai/grok-build-0.1":{"draws":0,"losses":4,"wins":0},"xiaomi/mimo-v2.5":{"draws":3,"losses":18,"wins":9},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":4,"wins":0},"z-ai/glm-5.2":{"draws":2,"losses":20,"wins":14}},"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":5,"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":18},"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},"thinkingmachines/inkling":{"draws":0,"losses":1,"wins":1},"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":25,"losses":27,"wins":28},"claude-opus-5":{"draws":22,"losses":70,"wins":14},"claude-sonnet-5":{"draws":19,"losses":11,"wins":22},"cohere/north-mini-code":{"draws":5,"losses":1,"wins":16},"deepseek/deepseek-v4-flash":{"draws":32,"losses":11,"wins":51},"deepseek/deepseek-v4-pro":{"draws":11,"losses":13,"wins":20},"google/gemini-3.1-flash-lite":{"draws":13,"losses":1,"wins":22},"google/gemini-3.5-flash":{"draws":22,"losses":17,"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":18},"gpt-5.4-mini":{"draws":55,"losses":24,"wins":47},"gpt-5.4-nano":{"draws":51,"losses":43,"wins":75},"gpt-5.5":{"draws":27,"losses":31,"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":32},"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":11,"losses":5,"wins":18},"mistralai/mistral-medium-3-5":{"draws":3,"losses":0,"wins":25},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":5,"wins":8},"moonshotai/kimi-k3":{"draws":58,"losses":49,"wins":49},"nex-agi/nex-n2-pro":{"draws":8,"losses":4,"wins":20},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":29,"losses":6,"wins":27},"o3":{"draws":11,"losses":12,"wins":27},"openai/gpt-oss-120b":{"draws":29,"losses":4,"wins":29},"poolside/laguna-s-2.1":{"draws":45,"losses":17,"wins":28},"qwen/qwen3.7-max":{"draws":15,"losses":12,"wins":15},"qwen/qwen3.7-plus":{"draws":11,"losses":4,"wins":5},"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":97},"x-ai/grok-build-0.1":{"draws":11,"losses":0,"wins":5},"xiaomi/mimo-v2.5":{"draws":28,"losses":17,"wins":33},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":9,"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":7,"wins":3},"claude-opus-4-8":{"draws":10,"losses":6,"wins":2},"claude-opus-5":{"draws":0,"losses":4,"wins":0},"claude-sonnet-5":{"draws":4,"losses":14,"wins":4},"cohere/north-mini-code":{"draws":8,"losses":6,"wins":6},"deepseek/deepseek-v4-flash":{"draws":18,"losses":10,"wins":22},"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":4},"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":2},"gpt-5.4-mini":{"draws":19,"losses":26,"wins":13},"gpt-5.4-nano":{"draws":22,"losses":19,"wins":27},"gpt-5.5":{"draws":4,"losses":7,"wins":3},"gpt-5.6-luna":{"draws":9,"losses":4,"wins":9},"gpt-5.6-sol":{"draws":4,"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":8,"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":6,"wins":0},"openai/gpt-oss-120b":{"draws":11,"losses":8,"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":7,"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":6,"wins":6},"z-ai/glm-5.2":{"draws":12,"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":16,"wins":8},"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":16,"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":5,"losses":7,"wins":4},"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":5},"meituan/longcat-2.0":{"draws":6,"losses":3,"wins":5},"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":29,"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":19,"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":17,"wins":8},"claude-opus-5":{"draws":0,"losses":22,"wins":0},"claude-sonnet-5":{"draws":3,"losses":12,"wins":13},"cohere/north-mini-code":{"draws":3,"losses":4,"wins":9},"deepseek/deepseek-v4-flash":{"draws":11,"losses":12,"wins":29},"deepseek/deepseek-v4-pro":{"draws":3,"losses":9,"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":7},"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":14,"losses":21,"wins":43},"gpt-5.4-nano":{"draws":23,"losses":30,"wins":23},"gpt-5.5":{"draws":7,"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":9,"losses":7,"wins":6},"meituan/longcat-2.0":{"draws":0,"losses":1,"wins":3},"minimax/minimax-m3":{"draws":4,"losses":6,"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":6},"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":2,"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":9},"x-ai/grok-4.5":{"draws":12,"losses":44,"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":8,"wins":6},"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":14,"wins":20},"deepseek/deepseek-v4-pro":{"draws":4,"losses":4,"wins":4},"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":11,"wins":3},"gpt-5.4-mini":{"draws":30,"losses":26,"wins":26},"gpt-5.4-nano":{"draws":52,"losses":28,"wins":32},"gpt-5.5":{"draws":13,"losses":11,"wins":2},"gpt-5.6-luna":{"draws":18,"losses":13,"wins":11},"gpt-5.6-sol":{"draws":12,"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":6,"losses":2,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":29,"losses":29,"wins":4},"nex-agi/nex-n2-pro":{"draws":11,"losses":3,"wins":8},"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":14,"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":9,"losses":7,"wins":2},"thinkingmachines/inkling":{"draws":3,"losses":0,"wins":5},"x-ai/grok-4.5":{"draws":15,"losses":29,"wins":4},"x-ai/grok-build-0.1":{"draws":3,"losses":9,"wins":2},"xiaomi/mimo-v2.5":{"draws":20,"losses":14,"wins":16},"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":9,"losses":3,"wins":10},"deepseek/deepseek-v4-pro":{"draws":0,"losses":2,"wins":4},"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":6,"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":60,"wins":21},"x-ai/grok-build-0.1":{"draws":1,"losses":3,"wins":2},"xiaomi/mimo-v2.5":{"draws":6,"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":9},"claude-opus-5":{"draws":0,"losses":18,"wins":6},"claude-sonnet-5":{"draws":5,"losses":7,"wins":4},"cohere/north-mini-code":{"draws":3,"losses":2,"wins":7},"deepseek/deepseek-v4-flash":{"draws":18,"losses":8,"wins":18},"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":5,"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":4},"gpt-5.4-mini":{"draws":26,"losses":21,"wins":25},"gpt-5.4-nano":{"draws":36,"losses":15,"wins":27},"gpt-5.5":{"draws":9,"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":6,"losses":6,"wins":8},"mistralai/mistral-medium-3-5":{"draws":2,"losses":3,"wins":5},"moonshotai/kimi-k3":{"draws":15,"losses":15,"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":14,"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":7,"losses":5,"wins":6},"stepfun/step-3.7-flash":{"draws":4,"losses":3,"wins":9},"tencent/hy3-preview":{"draws":8,"losses":3,"wins":5},"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":12,"losses":10,"wins":12},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":3,"wins":11},"z-ai/glm-5.2":{"draws":14,"losses":13,"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":6,"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":4,"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":6,"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":16,"wins":30},"gpt-5.4-nano":{"draws":23,"losses":13,"wins":40},"gpt-5.5":{"draws":7,"losses":5,"wins":0},"gpt-5.6-luna":{"draws":11,"losses":5,"wins":8},"gpt-5.6-sol":{"draws":6,"losses":5,"wins":3},"gpt-5.6-terra":{"draws":9,"losses":8,"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":11,"losses":5,"wins":4},"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":2,"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":7,"losses":6,"wins":5},"qwen/qwen3.7-plus":{"draws":4,"losses":4,"wins":4},"stepfun/step-3.7-flash":{"draws":0,"losses":8,"wins":6},"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":4,"losses":2,"wins":8},"xiaomi/mimo-v2.5":{"draws":9,"losses":14,"wins":11},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":11,"wins":1},"z-ai/glm-5.2":{"draws":19,"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":15,"wins":4},"claude-opus-4-8":{"draws":0,"losses":6,"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":3,"losses":3,"wins":10},"deepseek/deepseek-v4-flash":{"draws":20,"losses":20,"wins":24},"deepseek/deepseek-v4-pro":{"draws":7,"losses":13,"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":23,"losses":36,"wins":23},"gpt-5.4-nano":{"draws":24,"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":7,"wins":3},"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":6,"wins":8},"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":23,"losses":18,"wins":17},"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":24,"losses":15,"wins":17},"deepseek/deepseek-v4-pro":{"draws":4,"losses":6,"wins":6},"google/gemini-3.1-flash-lite":{"draws":2,"losses":6,"wins":8},"google/gemini-3.5-flash":{"draws":2,"losses":8,"wins":2},"google/gemini-3.5-flash-lite":{"draws":4,"losses":4,"wins":2},"google/gemini-3.6-flash":{"draws":4,"losses":0,"wins":4},"google/gemma-4-31b-it":{"draws":2,"losses":1,"wins":7},"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":36,"losses":14,"wins":26},"gpt-5.5":{"draws":16,"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":3,"wins":2},"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":9,"losses":2,"wins":7},"poolside/laguna-s-2.1":{"draws":0,"losses":4,"wins":4},"qwen/qwen3.7-max":{"draws":8,"losses":5,"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":4},"x-ai/grok-4.5":{"draws":16,"losses":31,"wins":11},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":12,"losses":14,"wins":10},"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":15,"losses":10,"wins":19},"deepseek/deepseek-v4-pro":{"draws":2,"losses":6,"wins":2},"google/gemini-3.1-flash-lite":{"draws":7,"losses":6,"wins":9},"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":16},"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":2,"losses":5,"wins":3},"gpt-5.6-terra":{"draws":8,"losses":4,"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":3},"mistralai/mistral-medium-3-5":{"draws":4,"losses":5,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":1},"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":9,"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":4,"wins":2},"thinkingmachines/inkling":{"draws":38,"losses":43,"wins":43},"x-ai/grok-4.5":{"draws":34,"losses":64,"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":5,"wins":5},"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":41},"claude-opus-5":{"draws":27,"losses":134,"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":61},"deepseek/deepseek-v4-pro":{"draws":10,"losses":14,"wins":34},"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":35,"wins":110},"google/gemini-3.6-flash":{"draws":39,"losses":79,"wins":66},"google/gemma-4-31b-it":{"draws":5,"losses":3,"wins":22},"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":31},"gpt-5.4-mini":{"draws":54,"losses":26,"wins":102},"gpt-5.4-nano":{"draws":50,"losses":58,"wins":92},"gpt-5.5":{"draws":26,"losses":34,"wins":42},"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":27,"losses":26,"wins":45},"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":17,"losses":3,"wins":20},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":1,"wins":31},"moonshotai/kimi-k3":{"draws":72,"losses":97,"wins":109},"nex-agi/nex-n2-pro":{"draws":7,"losses":4,"wins":17},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":11,"wins":20},"o3":{"draws":12,"losses":20,"wins":44},"openai/gpt-oss-120b":{"draws":15,"losses":4,"wins":29},"poolside/laguna-s-2.1":{"draws":29,"losses":21,"wins":60},"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":16,"losses":11,"wins":31},"thinkingmachines/inkling":{"draws":34,"losses":16,"wins":64},"x-ai/grok-4.5":{"draws":72,"losses":108,"wins":108},"x-ai/grok-build-0.1":{"draws":8,"losses":4,"wins":14},"xiaomi/mimo-v2.5":{"draws":23,"losses":13,"wins":56},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":12,"wins":24},"z-ai/glm-5.2":{"draws":18,"losses":48,"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":6,"losses":4,"wins":6},"claude-opus-5":{"draws":4,"losses":2,"wins":2},"claude-sonnet-5":{"draws":3,"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":3,"wins":3},"google/gemini-3.6-flash":{"draws":0,"losses":4,"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":2,"wins":3},"qwen/qwen3.7-max":{"draws":0,"losses":2,"wins":8},"qwen/qwen3.7-plus":{"draws":4,"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":34,"losses":27,"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":22,"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":13,"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":9,"wins":4},"google/gemma-4-31b-it":{"draws":2,"losses":14,"wins":12},"gpt-4.1":{"draws":0,"losses":7,"wins":3},"gpt-5":{"draws":20,"losses":8,"wins":12},"gpt-5.4":{"draws":23,"losses":22,"wins":5},"gpt-5.4-mini":{"draws":75,"losses":56,"wins":69},"gpt-5.4-nano":{"draws":86,"losses":60,"wins":68},"gpt-5.5":{"draws":27,"losses":12,"wins":7},"gpt-5.6-luna":{"draws":19,"losses":11,"wins":24},"gpt-5.6-sol":{"draws":12,"losses":13,"wins":9},"gpt-5.6-terra":{"draws":21,"losses":21,"wins":8},"inclusionai/ling-3.0-flash":{"draws":6,"losses":4,"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":9,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":10,"wins":6},"moonshotai/kimi-k3":{"draws":28,"losses":33,"wins":17},"nex-agi/nex-n2-pro":{"draws":12,"losses":14,"wins":20},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":19,"losses":8,"wins":9},"o3":{"draws":17,"losses":30,"wins":7},"openai/gpt-oss-120b":{"draws":20,"losses":16,"wins":14},"poolside/laguna-s-2.1":{"draws":6,"losses":2,"wins":4},"qwen/qwen3.7-max":{"draws":12,"losses":12,"wins":10},"qwen/qwen3.7-plus":{"draws":9,"losses":11,"wins":14},"stepfun/step-3.7-flash":{"draws":23,"losses":17,"wins":18},"tencent/hy3-preview":{"draws":12,"losses":10,"wins":14},"thinkingmachines/inkling":{"draws":22,"losses":9,"wins":15},"x-ai/grok-4.5":{"draws":23,"losses":56,"wins":13},"x-ai/grok-build-0.1":{"draws":12,"losses":11,"wins":5},"xiaomi/mimo-v2.5":{"draws":52,"losses":26,"wins":26},"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":16,"wins":18},"deepseek/deepseek-v4-pro":{"draws":3,"losses":5,"wins":6},"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":22,"wins":17},"gpt-5.4-nano":{"draws":24,"losses":21,"wins":31},"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":6,"losses":3,"wins":5},"inclusionai/ling-3.0-flash":{"draws":1,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":2,"losses":0,"wins":12},"minimax/minimax-m3":{"draws":5,"losses":6,"wins":9},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":4},"moonshotai/kimi-k3":{"draws":6,"losses":13,"wins":9},"nex-agi/nex-n2-pro":{"draws":4,"losses":6,"wins":6},"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":8,"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":5,"wins":5},"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":16,"wins":5}},"z-ai/glm-5.2":{"claude-fable-5":{"draws":1,"losses":33,"wins":8},"claude-opus-4-5":{"draws":41,"losses":46,"wins":39},"claude-opus-4-8":{"draws":23,"losses":35,"wins":24},"claude-opus-5":{"draws":16,"losses":63,"wins":11},"claude-sonnet-5":{"draws":38,"losses":34,"wins":36},"cohere/north-mini-code":{"draws":14,"losses":2,"wins":4},"deepseek/deepseek-v4-flash":{"draws":47,"losses":42,"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":7,"wins":12},"google/gemini-3.6-flash":{"draws":13,"losses":8,"wins":5},"google/gemma-4-31b-it":{"draws":7,"losses":6,"wins":7},"gpt-4.1":{"draws":6,"losses":11,"wins":17},"gpt-5":{"draws":25,"losses":29,"wins":32},"gpt-5.4":{"draws":41,"losses":30,"wins":17},"gpt-5.4-mini":{"draws":83,"losses":62,"wins":75},"gpt-5.4-nano":{"draws":86,"losses":70,"wins":87},"gpt-5.5":{"draws":27,"losses":27,"wins":20},"gpt-5.6-luna":{"draws":37,"losses":25,"wins":36},"gpt-5.6-sol":{"draws":23,"losses":43,"wins":24},"gpt-5.6-terra":{"draws":27,"losses":27,"wins":26},"inclusionai/ling-3.0-flash":{"draws":6,"losses":3,"wins":7},"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":14,"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":12,"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":13},"qwen/qwen3.7-plus":{"draws":19,"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":18,"losses":72,"wins":48},"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":5,"wins":16},"z-ai/glm-5.2":{"draws":98,"losses":69,"wins":69}}},"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":12,"losses":12,"wins":22},"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":11},"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":5,"losses":2,"wins":21},"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":21,"wins":16}},"deepseek/deepseek-v4-flash":{"claude-fable-5":{"draws":1,"losses":4,"wins":1},"claude-opus-4-5":{"draws":12,"losses":9,"wins":7},"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":6,"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":25}},"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":7},"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":4,"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":5,"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":2},"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-3.5-flash-lite":{"draws":0,"losses":2,"wins":0},"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":2,"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":2,"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":33}},"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":19,"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":2,"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":8,"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":8,"losses":7,"wins":17}},"gpt-5.6-luna":{"claude-fable-5":{"draws":2,"losses":10,"wins":2},"claude-opus-4-5":{"draws":5,"losses":6,"wins":13},"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},"thinkingmachines/inkling":{"draws":1,"losses":1,"wins":0},"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":3,"losses":2,"wins":11},"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":12,"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":12,"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":8},"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":3,"wins":1},"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":3},"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":11,"losses":31,"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":15,"wins":35},"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":11,"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":28,"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":2,"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":20,"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":8,"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":2,"wins":2},"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":7,"losses":2,"wins":15},"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":1,"losses":1,"wins":2},"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":5,"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":7,"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":15,"wins":1},"x-ai/grok-build-0.1":{"draws":4,"losses":4,"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":4,"wins":13}},"claude-opus-5":{"claude-fable-5":{"draws":8,"losses":16,"wins":10},"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":6,"losses":2,"wins":26},"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":1,"losses":4,"wins":11},"gpt-5.4-nano":{"draws":4,"losses":6,"wins":20},"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":17},"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":4},"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":11,"losses":28,"wins":49},"x-ai/grok-build-0.1":{"draws":1,"losses":1,"wins":2},"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":27}},"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":5,"losses":1,"wins":4},"moonshotai/kimi-k3":{"draws":8,"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":2,"losses":0,"wins":8},"xiaomi/mimo-v2.5":{"draws":19,"losses":3,"wins":14},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":1,"wins":3},"z-ai/glm-5.2":{"draws":6,"losses":3,"wins":7}},"cohere/north-mini-code":{"claude-opus-4-5":{"draws":3,"losses":3,"wins":2},"claude-opus-4-8":{"draws":5,"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":11,"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":6,"losses":0,"wins":2},"claude-opus-4-8":{"draws":7,"losses":3,"wins":0},"claude-sonnet-5":{"draws":9,"losses":5,"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":6,"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":9,"wins":3},"inclusionai/ling-3.0-flash":{"draws":0,"losses":3,"wins":3},"meituan/longcat-2.0":{"draws":3,"losses":4,"wins":3},"minimax/minimax-m3":{"draws":4,"losses":8,"wins":4},"mistralai/mistral-medium-3-5":{"draws":7,"losses":7,"wins":2},"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":5,"wins":1},"poolside/laguna-s-2.1":{"draws":2,"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":6,"losses":3,"wins":3},"thinkingmachines/inkling":{"draws":5,"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":6,"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":2,"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":17,"wins":13},"gpt-5.5":{"draws":3,"losses":1,"wins":2},"gpt-5.6-luna":{"draws":4,"losses":1,"wins":7},"gpt-5.6-sol":{"draws":3,"losses":2,"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":5,"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":5,"losses":3,"wins":4},"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":13,"losses":8,"wins":9},"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":5,"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":8,"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":2},"gpt-5.4":{"draws":6,"losses":2,"wins":0},"gpt-5.4-mini":{"draws":13,"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":3,"wins":2},"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":5,"losses":4,"wins":7},"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":6,"losses":3,"wins":3},"tencent/hy3-preview":{"draws":4,"losses":2,"wins":4},"thinkingmachines/inkling":{"draws":18,"losses":34,"wins":24},"x-ai/grok-4.5":{"draws":23,"losses":39,"wins":6},"x-ai/grok-build-0.1":{"draws":0,"losses":3,"wins":3},"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":11,"wins":6}},"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":4,"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":5,"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":6,"losses":11,"wins":7},"gpt-5.4-mini":{"draws":12,"losses":6,"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":4,"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":22,"losses":23,"wins":37},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":4},"xiaomi/mimo-v2.5":{"draws":13,"losses":4,"wins":9},"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":8,"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":4,"losses":4,"wins":2},"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":3,"losses":3,"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":4,"losses":1,"wins":1},"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":12,"losses":11,"wins":3},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":0,"wins":3},"z-ai/glm-5.2":{"draws":5,"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":11},"claude-opus-4-8":{"draws":3,"losses":7,"wins":6},"claude-opus-5":{"draws":4,"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":2,"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":7,"losses":11,"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":3,"losses":6,"wins":5},"claude-sonnet-5":{"draws":9,"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":6},"google/gemma-4-31b-it":{"draws":8,"losses":3,"wins":7},"gpt-4.1":{"draws":7,"losses":4,"wins":5},"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":28,"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":26,"losses":13,"wins":13},"inclusionai/ling-3.0-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":3,"losses":3,"wins":8},"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":18,"wins":5},"moonshotai/kimi-k3":{"draws":19,"losses":11,"wins":8},"nex-agi/nex-n2-pro":{"draws":7,"losses":2,"wins":15},"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":12,"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":20,"losses":40,"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":34,"losses":25,"wins":17}},"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":11},"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":28},"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":8},"gpt-4.1":{"draws":0,"losses":4,"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":27},"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":15,"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":15,"losses":18,"wins":9},"nex-agi/nex-n2-pro":{"draws":5,"losses":14,"wins":9},"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":9},"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":8,"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":35,"wins":19},"x-ai/grok-build-0.1":{"draws":10,"losses":14,"wins":4},"xiaomi/mimo-v2.5":{"draws":31,"losses":33,"wins":22},"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":12,"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":1,"losses":2,"wins":5},"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":7,"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":4,"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":15,"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":2},"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":18},"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":7,"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":5,"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":9},"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":23,"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":11,"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":6,"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":4,"wins":6},"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-3.5-flash-lite":{"draws":0,"losses":1,"wins":1},"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":7,"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},"thinkingmachines/inkling":{"draws":0,"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":5,"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":18},"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},"thinkingmachines/inkling":{"draws":0,"losses":1,"wins":1},"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":7,"losses":4,"wins":9},"claude-opus-5":{"draws":5,"losses":15,"wins":4},"claude-sonnet-5":{"draws":8,"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":9,"losses":7,"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":14,"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":6,"losses":1,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":5,"wins":8},"moonshotai/kimi-k3":{"draws":20,"losses":11,"wins":5},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"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":26},"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":17,"wins":4},"gpt-5.4-nano":{"draws":4,"losses":12,"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":3},"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":7,"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":1,"wins":5},"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":11,"wins":14},"gpt-5.5":{"draws":2,"losses":8,"wins":0},"gpt-5.6-luna":{"draws":10,"losses":3,"wins":3},"gpt-5.6-sol":{"draws":5,"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":10,"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":8,"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":5,"wins":5},"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":3,"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":17,"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":8,"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":4,"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":4,"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":15,"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":6,"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":10,"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":10,"losses":5,"wins":13},"deepseek/deepseek-v4-pro":{"draws":0,"losses":2,"wins":2},"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":8},"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":4,"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-k2.7-code":{"draws":0,"losses":1,"wins":1},"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":14,"losses":31,"wins":5},"xiaomi/mimo-v2.5":{"draws":11,"losses":6,"wins":3},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":3,"wins":5},"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":19},"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":13,"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":25,"losses":15,"wins":42},"gpt-5.4-nano":{"draws":12,"losses":19,"wins":43},"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":14,"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":29,"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":21},"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":13,"losses":5,"wins":24},"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":5,"wins":32},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":4,"wins":7},"z-ai/glm-5.2":{"draws":11,"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":6,"losses":4,"wins":6},"claude-opus-5":{"draws":4,"losses":2,"wins":2},"claude-sonnet-5":{"draws":3,"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":3,"wins":3},"google/gemini-3.6-flash":{"draws":0,"losses":4,"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":2,"wins":3},"qwen/qwen3.7-max":{"draws":0,"losses":2,"wins":8},"qwen/qwen3.7-plus":{"draws":4,"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":14,"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":22,"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":8,"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":32,"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":4,"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":6,"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":8},"claude-opus-4-8":{"draws":12,"losses":10,"wins":6},"claude-opus-5":{"draws":2,"losses":13,"wins":1},"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":3,"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":17,"losses":12,"wins":17},"gpt-5.4-nano":{"draws":25,"losses":18,"wins":21},"gpt-5.5":{"draws":9,"losses":7,"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":7},"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":5},"qwen/qwen3.7-plus":{"draws":8,"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":7},"z-ai/glm-5.2":{"draws":35,"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":2,"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":15,"losses":2,"wins":7},"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":13,"losses":5,"wins":16},"gpt-5.4-nano":{"draws":13,"losses":9,"wins":18},"gpt-5.5":{"draws":7,"losses":3,"wins":2},"gpt-5.6-luna":{"draws":9,"losses":1,"wins":6},"gpt-5.6-sol":{"draws":6,"losses":9,"wins":3},"gpt-5.6-terra":{"draws":9,"losses":6,"wins":7},"meituan/longcat-2.0":{"draws":4,"losses":1,"wins":3},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":4},"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":3},"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":12,"losses":6,"wins":12},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":7,"wins":3},"z-ai/glm-5.2":{"draws":2,"losses":8,"wins":12}},"claude-opus-4-8":{"claude-fable-5":{"draws":0,"losses":4,"wins":0},"claude-opus-4-5":{"draws":2,"losses":2,"wins":8},"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":8,"wins":4},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":4},"deepseek/deepseek-v4-flash":{"draws":7,"losses":4,"wins":11},"deepseek/deepseek-v4-pro":{"draws":4,"losses":6,"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":4},"google/gemini-3.6-flash":{"draws":2,"losses":0,"wins":0},"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":12,"losses":8,"wins":20},"gpt-5.4-nano":{"draws":8,"losses":9,"wins":21},"gpt-5.5":{"draws":3,"losses":12,"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},"inclusionai/ling-3.0-flash":{"draws":1,"losses":0,"wins":1},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":6},"mistralai/mistral-medium-3-5":{"draws":0,"losses":2,"wins":2},"moonshotai/kimi-k3":{"draws":11,"losses":8,"wins":7},"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":5,"wins":8},"openai/gpt-oss-120b":{"draws":4,"losses":5,"wins":1},"poolside/laguna-s-2.1":{"draws":0,"losses":1,"wins":5},"qwen/qwen3.7-max":{"draws":2,"losses":7,"wins":3},"qwen/qwen3.7-plus":{"draws":2,"losses":2,"wins":2},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":4},"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":12,"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":7,"losses":10,"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":3,"losses":1,"wins":8},"gpt-5.4":{"draws":9,"losses":15,"wins":8},"gpt-5.4-mini":{"draws":5,"losses":3,"wins":14},"gpt-5.4-nano":{"draws":4,"losses":3,"wins":21},"gpt-5.5":{"draws":5,"losses":6,"wins":13},"gpt-5.6-luna":{"draws":1,"losses":1,"wins":6},"gpt-5.6-sol":{"draws":9,"losses":2,"wins":17},"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":4,"wins":6},"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":48},"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":7,"losses":5,"wins":24}},"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":6,"wins":4},"claude-opus-5":{"draws":4,"losses":12,"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":10,"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":8,"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},"meituan/longcat-2.0":{"draws":1,"losses":0,"wins":1},"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":6},"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":5,"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":14,"wins":6},"gpt-5.4-nano":{"draws":10,"losses":18,"wins":10},"gpt-5.5":{"draws":7,"losses":3,"wins":0},"gpt-5.6-luna":{"draws":2,"losses":2,"wins":6},"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":8,"wins":0},"nex-agi/nex-n2-pro":{"draws":2,"losses":2,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":2,"wins":2},"o3":{"draws":2,"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":3,"losses":7,"wins":2},"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":21,"losses":8,"wins":1},"claude-opus-4-8":{"draws":8,"losses":12,"wins":2},"claude-opus-5":{"draws":2,"losses":0,"wins":0},"claude-sonnet-5":{"draws":11,"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":9,"losses":4,"wins":9},"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":7,"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":12,"wins":6},"gpt-5.4-mini":{"draws":52,"losses":36,"wins":26},"gpt-5.4-nano":{"draws":35,"losses":22,"wins":33},"gpt-5.5":{"draws":16,"losses":12,"wins":2},"gpt-5.6-luna":{"draws":23,"losses":13,"wins":12},"gpt-5.6-sol":{"draws":7,"losses":22,"wins":5},"gpt-5.6-terra":{"draws":10,"losses":25,"wins":5},"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":14,"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":19,"losses":31,"wins":4},"nex-agi/nex-n2-pro":{"draws":14,"losses":15,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":3,"wins":5},"o3":{"draws":7,"losses":13,"wins":6},"openai/gpt-oss-120b":{"draws":16,"losses":9,"wins":13},"poolside/laguna-s-2.1":{"draws":7,"losses":1,"wins":0},"qwen/qwen3.7-max":{"draws":14,"losses":15,"wins":3},"qwen/qwen3.7-plus":{"draws":12,"losses":7,"wins":11},"stepfun/step-3.7-flash":{"draws":14,"losses":11,"wins":9},"tencent/hy3-preview":{"draws":12,"losses":7,"wins":7},"thinkingmachines/inkling":{"draws":8,"losses":7,"wins":5},"x-ai/grok-4.5":{"draws":23,"losses":28,"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":11,"wins":5},"z-ai/glm-5.2":{"draws":14,"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":6},"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":13,"losses":11,"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":4,"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":17},"gpt-5.4-nano":{"draws":15,"losses":13,"wins":14},"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":5,"losses":3,"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":6,"wins":3},"mistralai/mistral-medium-3-5":{"draws":2,"losses":1,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":1,"wins":1},"moonshotai/kimi-k3":{"draws":6,"losses":10,"wins":4},"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":4},"openai/gpt-oss-120b":{"draws":2,"losses":2,"wins":4},"poolside/laguna-s-2.1":{"draws":0,"losses":2,"wins":0},"qwen/qwen3.7-max":{"draws":9,"losses":3,"wins":6},"qwen/qwen3.7-plus":{"draws":4,"losses":0,"wins":4},"stepfun/step-3.7-flash":{"draws":5,"losses":1,"wins":6},"tencent/hy3-preview":{"draws":4,"losses":4,"wins":0},"thinkingmachines/inkling":{"draws":2,"losses":2,"wins":4},"x-ai/grok-4.5":{"draws":7,"losses":16,"wins":9},"x-ai/grok-build-0.1":{"draws":4,"losses":1,"wins":1},"xiaomi/mimo-v2.5":{"draws":3,"losses":6,"wins":11},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":6,"wins":5},"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":4},"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":10,"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":3,"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":5},"deepseek/deepseek-v4-flash":{"draws":13,"losses":14,"wins":13},"deepseek/deepseek-v4-pro":{"draws":6,"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":12,"wins":14},"gpt-5.4-nano":{"draws":7,"losses":12,"wins":13},"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":6,"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":4},"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":2,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":0,"wins":2},"o3":{"draws":2,"losses":3,"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":7,"wins":1},"thinkingmachines/inkling":{"draws":0,"losses":4,"wins":0},"x-ai/grok-4.5":{"draws":1,"losses":11,"wins":0},"x-ai/grok-build-0.1":{"draws":5,"losses":2,"wins":1},"xiaomi/mimo-v2.5":{"draws":2,"losses":12,"wins":8},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":4,"wins":2},"z-ai/glm-5.2":{"draws":4,"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":12,"wins":6},"gpt-5.4-nano":{"draws":4,"losses":8,"wins":6},"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":3,"wins":7},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":5,"wins":5},"z-ai/glm-5.2":{"draws":6,"losses":17,"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":7,"wins":12},"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":4,"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":24,"losses":6,"wins":20},"gpt-5.4-nano":{"draws":15,"losses":7,"wins":16},"gpt-5.5":{"draws":4,"losses":6,"wins":6},"gpt-5.6-luna":{"draws":10,"losses":1,"wins":7},"gpt-5.6-sol":{"draws":4,"losses":6,"wins":10},"gpt-5.6-terra":{"draws":2,"losses":3,"wins":7},"meituan/longcat-2.0":{"draws":0,"losses":0,"wins":2},"minimax/minimax-m3":{"draws":2,"losses":4,"wins":4},"mistralai/mistral-medium-3-5":{"draws":1,"losses":0,"wins":5},"moonshotai/kimi-k3":{"draws":6,"losses":7,"wins":11},"nex-agi/nex-n2-pro":{"draws":5,"losses":2,"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":3,"wins":3},"poolside/laguna-s-2.1":{"draws":0,"losses":2,"wins":0},"qwen/qwen3.7-max":{"draws":2,"losses":2,"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":7,"wins":19},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":16,"losses":3,"wins":15},"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":18,"losses":17,"wins":7},"claude-opus-4-8":{"draws":17,"losses":14,"wins":5},"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":6,"wins":10},"deepseek/deepseek-v4-flash":{"draws":53,"losses":26,"wins":37},"deepseek/deepseek-v4-pro":{"draws":16,"losses":16,"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":7,"losses":8,"wins":5},"google/gemini-3.6-flash":{"draws":6,"losses":2,"wins":0},"google/gemma-4-31b-it":{"draws":11,"losses":14,"wins":11},"gpt-4.1":{"draws":5,"losses":2,"wins":5},"gpt-5":{"draws":6,"losses":4,"wins":0},"gpt-5.4":{"draws":26,"losses":19,"wins":5},"gpt-5.4-mini":{"draws":47,"losses":41,"wins":30},"gpt-5.4-nano":{"draws":52,"losses":47,"wins":43},"gpt-5.5":{"draws":26,"losses":5,"wins":5},"gpt-5.6-luna":{"draws":21,"losses":10,"wins":21},"gpt-5.6-sol":{"draws":8,"losses":18,"wins":4},"gpt-5.6-terra":{"draws":21,"losses":20,"wins":9},"inclusionai/ling-3.0-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":2,"losses":6,"wins":4},"minimax/minimax-m3":{"draws":9,"losses":14,"wins":9},"mistralai/mistral-medium-3-5":{"draws":8,"losses":7,"wins":13},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":26,"losses":22,"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":9,"losses":18,"wins":3},"openai/gpt-oss-120b":{"draws":8,"losses":16,"wins":16},"poolside/laguna-s-2.1":{"draws":3,"losses":3,"wins":4},"qwen/qwen3.7-max":{"draws":8,"losses":10,"wins":6},"qwen/qwen3.7-plus":{"draws":10,"losses":15,"wins":9},"stepfun/step-3.7-flash":{"draws":11,"losses":16,"wins":17},"tencent/hy3-preview":{"draws":11,"losses":10,"wins":9},"thinkingmachines/inkling":{"draws":10,"losses":10,"wins":10},"x-ai/grok-4.5":{"draws":27,"losses":28,"wins":1},"x-ai/grok-build-0.1":{"draws":0,"losses":3,"wins":1},"xiaomi/mimo-v2.5":{"draws":43,"losses":40,"wins":25},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":8,"wins":9},"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":20,"wins":4},"claude-opus-4-8":{"draws":11,"losses":19,"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":12},"deepseek/deepseek-v4-flash":{"draws":43,"losses":39,"wins":28},"deepseek/deepseek-v4-pro":{"draws":15,"losses":12,"wins":9},"google/gemini-3.1-flash-lite":{"draws":9,"losses":11,"wins":8},"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":9,"losses":13,"wins":10},"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":47,"losses":41,"wins":46},"gpt-5.4-nano":{"draws":47,"losses":48,"wins":39},"gpt-5.5":{"draws":21,"losses":10,"wins":7},"gpt-5.6-luna":{"draws":17,"losses":11,"wins":16},"gpt-5.6-sol":{"draws":6,"losses":22,"wins":12},"gpt-5.6-terra":{"draws":19,"losses":3,"wins":14},"inclusionai/ling-3.0-flash":{"draws":10,"losses":3,"wins":3},"meituan/longcat-2.0":{"draws":7,"losses":6,"wins":7},"minimax/minimax-m3":{"draws":13,"losses":12,"wins":9},"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":20,"losses":32,"wins":14},"nex-agi/nex-n2-pro":{"draws":15,"losses":13,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":3,"wins":5},"o3":{"draws":19,"losses":12,"wins":15},"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":9},"stepfun/step-3.7-flash":{"draws":9,"losses":14,"wins":3},"tencent/hy3-preview":{"draws":22,"losses":16,"wins":2},"thinkingmachines/inkling":{"draws":3,"losses":16,"wins":5},"x-ai/grok-4.5":{"draws":26,"losses":30,"wins":14},"x-ai/grok-build-0.1":{"draws":1,"losses":1,"wins":2},"xiaomi/mimo-v2.5":{"draws":47,"losses":35,"wins":30},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":15,"wins":10},"z-ai/glm-5.2":{"draws":29,"losses":33,"wins":18}},"gpt-5.5":{"claude-opus-4-5":{"draws":7,"losses":5,"wins":4},"claude-opus-4-8":{"draws":4,"losses":4,"wins":4},"claude-opus-5":{"draws":2,"losses":0,"wins":0},"claude-sonnet-5":{"draws":0,"losses":2,"wins":2},"cohere/north-mini-code":{"draws":7,"losses":0,"wins":3},"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":7,"wins":3},"gpt-5.4-mini":{"draws":25,"losses":4,"wins":5},"gpt-5.4-nano":{"draws":23,"losses":2,"wins":7},"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":8,"wins":4},"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":8},"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":5,"losses":2,"wins":1},"openai/gpt-oss-120b":{"draws":10,"losses":0,"wins":2},"qwen/qwen3.7-max":{"draws":5,"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":8,"losses":5,"wins":3},"thinkingmachines/inkling":{"draws":3,"losses":1,"wins":0},"x-ai/grok-4.5":{"draws":10,"losses":14,"wins":2},"x-ai/grok-build-0.1":{"draws":4,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":16,"losses":2,"wins":8},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":3,"wins":2},"z-ai/glm-5.2":{"draws":12,"losses":5,"wins":7}},"gpt-5.6-luna":{"claude-opus-4-5":{"draws":9,"losses":3,"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":10,"wins":2},"deepseek/deepseek-v4-flash":{"draws":25,"losses":13,"wins":8},"deepseek/deepseek-v4-pro":{"draws":7,"losses":2,"wins":1},"google/gemini-3.1-flash-lite":{"draws":7,"losses":9,"wins":4},"google/gemini-3.5-flash-lite":{"draws":2,"losses":4,"wins":0},"google/gemini-3.6-flash":{"draws":2,"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":14,"losses":22,"wins":8},"gpt-5.4-nano":{"draws":20,"losses":23,"wins":9},"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":2,"losses":6,"wins":1},"moonshotai/kimi-k3":{"draws":3,"losses":2,"wins":1},"nex-agi/nex-n2-pro":{"draws":4,"losses":6,"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":8,"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":8,"losses":9,"wins":5}},"gpt-5.6-sol":{"claude-fable-5":{"draws":0,"losses":2,"wins":0},"claude-opus-4-5":{"draws":8,"losses":5,"wins":9},"claude-opus-4-8":{"draws":6,"losses":5,"wins":5},"claude-opus-5":{"draws":5,"losses":7,"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":9,"losses":9,"wins":20},"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":4},"gpt-4.1":{"draws":3,"losses":1,"wins":2},"gpt-5.4":{"draws":4,"losses":8,"wins":6},"gpt-5.4-mini":{"draws":7,"losses":6,"wins":13},"gpt-5.4-nano":{"draws":3,"losses":10,"wins":15},"gpt-5.5":{"draws":7,"losses":4,"wins":5},"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":7,"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":4},"moonshotai/kimi-k3":{"draws":8,"losses":19,"wins":15},"nex-agi/nex-n2-pro":{"draws":4,"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":2,"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":2,"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":8,"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":6,"wins":5},"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":9,"wins":26},"deepseek/deepseek-v4-pro":{"draws":7,"losses":4,"wins":3},"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":25,"losses":14,"wins":13},"gpt-5.4-nano":{"draws":20,"losses":8,"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":9,"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":4,"losses":6,"wins":2},"mistralai/mistral-medium-3-5":{"draws":2,"losses":1,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":2,"wins":1},"moonshotai/kimi-k3":{"draws":12,"losses":15,"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":6,"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":2},"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":2},"x-ai/grok-4.5":{"draws":14,"losses":14,"wins":4},"xiaomi/mimo-v2.5":{"draws":11,"losses":6,"wins":7},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":5,"wins":3},"z-ai/glm-5.2":{"draws":6,"losses":7,"wins":5}},"inclusionai/ling-3.0-flash":{"claude-opus-4-5":{"draws":3,"losses":2,"wins":1},"claude-opus-4-8":{"draws":1,"losses":1,"wins":0},"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":6,"losses":2,"wins":0},"gpt-5.4-nano":{"draws":17,"losses":3,"wins":8},"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":5,"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":4},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":0,"wins":1},"z-ai/glm-5.2":{"draws":6,"losses":7,"wins":3}},"meituan/longcat-2.0":{"claude-fable-5":{"draws":1,"losses":1,"wins":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":5,"losses":7,"wins":0},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":0},"deepseek/deepseek-v4-flash":{"draws":8,"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":4,"losses":2,"wins":2},"gpt-5.4":{"draws":1,"losses":3,"wins":0},"gpt-5.4-mini":{"draws":7,"losses":13,"wins":10},"gpt-5.4-nano":{"draws":13,"losses":18,"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":2,"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":5,"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":2,"wins":3},"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":12,"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":10,"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":20},"deepseek/deepseek-v4-pro":{"draws":3,"losses":3,"wins":6},"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":15,"losses":6,"wins":15},"gpt-5.4-nano":{"draws":15,"losses":8,"wins":11},"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":6,"losses":6,"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":13,"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":5},"openai/gpt-oss-120b":{"draws":2,"losses":1,"wins":1},"qwen/qwen3.7-max":{"draws":4,"losses":3,"wins":1},"qwen/qwen3.7-plus":{"draws":1,"losses":1,"wins":4},"stepfun/step-3.7-flash":{"draws":2,"losses":1,"wins":5},"tencent/hy3-preview":{"draws":2,"losses":2,"wins":2},"thinkingmachines/inkling":{"draws":2,"losses":1,"wins":5},"x-ai/grok-4.5":{"draws":7,"losses":12,"wins":3},"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":1,"losses":4,"wins":5},"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":9,"wins":14},"deepseek/deepseek-v4-pro":{"draws":2,"losses":3,"wins":1},"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":4,"wins":2},"gpt-5":{"draws":0,"losses":0,"wins":2},"gpt-5.4":{"draws":1,"losses":3,"wins":0},"gpt-5.4-mini":{"draws":6,"losses":13,"wins":7},"gpt-5.4-nano":{"draws":8,"losses":7,"wins":5},"gpt-5.5":{"draws":2,"losses":2,"wins":0},"gpt-5.6-luna":{"draws":2,"losses":1,"wins":4},"gpt-5.6-sol":{"draws":0,"losses":6,"wins":0},"gpt-5.6-terra":{"draws":2,"losses":7,"wins":1},"inclusionai/ling-3.0-flash":{"draws":2,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":2,"losses":0,"wins":0},"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":8,"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":6,"losses":4,"wins":2},"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-4.5":{"draws":0,"losses":2,"wins":0},"x-ai/grok-build-0.1":{"draws":0,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":2,"losses":11,"wins":7},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":4,"wins":0},"z-ai/glm-5.2":{"draws":0,"losses":4,"wins":12}},"moonshotai/kimi-k3":{"claude-opus-4-5":{"draws":7,"losses":4,"wins":13},"claude-opus-4-8":{"draws":7,"losses":7,"wins":8},"claude-opus-5":{"draws":6,"losses":32,"wins":4},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":8},"deepseek/deepseek-v4-flash":{"draws":17,"losses":3,"wins":28},"deepseek/deepseek-v4-pro":{"draws":6,"losses":4,"wins":10},"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":7},"gpt-5.4-mini":{"draws":23,"losses":8,"wins":21},"gpt-5.4-nano":{"draws":12,"losses":12,"wins":28},"gpt-5.5":{"draws":8,"losses":8,"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":11},"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":13},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":8},"moonshotai/kimi-k3":{"draws":17,"losses":18,"wins":17},"nex-agi/nex-n2-pro":{"draws":4,"losses":4,"wins":6},"o3":{"draws":6,"losses":5,"wins":13},"openai/gpt-oss-120b":{"draws":5,"losses":3,"wins":12},"poolside/laguna-s-2.1":{"draws":13,"losses":6,"wins":13},"qwen/qwen3.7-max":{"draws":6,"losses":5,"wins":11},"qwen/qwen3.7-plus":{"draws":6,"losses":1,"wins":1},"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":7,"losses":12,"wins":21},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":5,"wins":7}},"nex-agi/nex-n2-pro":{"claude-fable-5":{"draws":0,"losses":2,"wins":0},"claude-opus-4-5":{"draws":4,"losses":2,"wins":2},"claude-opus-4-8":{"draws":7,"losses":3,"wins":2},"claude-opus-5":{"draws":0,"losses":4,"wins":0},"claude-sonnet-5":{"draws":2,"losses":3,"wins":3},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":4},"deepseek/deepseek-v4-flash":{"draws":18,"losses":7,"wins":17},"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":2},"gpt-4.1":{"draws":3,"losses":0,"wins":1},"gpt-5.4":{"draws":6,"losses":6,"wins":2},"gpt-5.4-mini":{"draws":10,"losses":9,"wins":9},"gpt-5.4-nano":{"draws":18,"losses":7,"wins":11},"gpt-5.5":{"draws":4,"losses":2,"wins":2},"gpt-5.6-luna":{"draws":5,"losses":1,"wins":4},"gpt-5.6-sol":{"draws":4,"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":8,"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":6,"wins":0},"openai/gpt-oss-120b":{"draws":9,"losses":5,"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":5,"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":2,"wins":4},"z-ai/glm-5.2":{"draws":8,"losses":8,"wins":6}},"nvidia/nemotron-3-ultra-550b-a55b":{"claude-opus-4-5":{"draws":0,"losses":5,"wins":3},"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":2,"losses":3,"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-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":4},"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":5,"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":6,"wins":3},"claude-opus-5":{"draws":0,"losses":14,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":6},"deepseek/deepseek-v4-flash":{"draws":7,"losses":6,"wins":11},"deepseek/deepseek-v4-pro":{"draws":2,"losses":3,"wins":3},"google/gemma-4-31b-it":{"draws":2,"losses":1,"wins":3},"gpt-5.4":{"draws":4,"losses":5,"wins":1},"gpt-5.4-mini":{"draws":6,"losses":3,"wins":15},"gpt-5.4-nano":{"draws":16,"losses":12,"wins":8},"gpt-5.5":{"draws":4,"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":6,"losses":1,"wins":3},"minimax/minimax-m3":{"draws":3,"losses":5,"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":4},"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":2,"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":9,"losses":14,"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":1,"wins":3},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":4},"deepseek/deepseek-v4-flash":{"draws":11,"losses":13,"wins":4},"deepseek/deepseek-v4-pro":{"draws":2,"losses":4,"wins":2},"google/gemma-4-31b-it":{"draws":0,"losses":6,"wins":2},"gpt-5.4":{"draws":4,"losses":3,"wins":1},"gpt-5.4-mini":{"draws":7,"losses":14,"wins":13},"gpt-5.4-nano":{"draws":23,"losses":11,"wins":8},"gpt-5.5":{"draws":7,"losses":1,"wins":0},"gpt-5.6-luna":{"draws":5,"losses":4,"wins":7},"gpt-5.6-sol":{"draws":2,"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":3,"losses":1,"wins":4},"moonshotai/kimi-k3":{"draws":5,"losses":12,"wins":3},"nex-agi/nex-n2-pro":{"draws":5,"losses":2,"wins":3},"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":5,"losses":3,"wins":0},"x-ai/grok-4.5":{"draws":9,"losses":13,"wins":0},"xiaomi/mimo-v2.5":{"draws":6,"losses":6,"wins":10},"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":9,"losses":3,"wins":10},"deepseek/deepseek-v4-pro":{"draws":0,"losses":2,"wins":4},"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":6,"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":44,"wins":15},"x-ai/grok-build-0.1":{"draws":1,"losses":3,"wins":2},"xiaomi/mimo-v2.5":{"draws":6,"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":5},"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":12,"losses":8,"wins":16},"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":2},"gpt-5.4-mini":{"draws":9,"losses":10,"wins":13},"gpt-5.4-nano":{"draws":19,"losses":6,"wins":11},"gpt-5.5":{"draws":5,"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":4,"losses":2,"wins":4},"mistralai/mistral-medium-3-5":{"draws":2,"losses":3,"wins":3},"moonshotai/kimi-k3":{"draws":6,"losses":11,"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":4,"losses":1,"wins":1},"stepfun/step-3.7-flash":{"draws":2,"losses":3,"wins":5},"tencent/hy3-preview":{"draws":7,"losses":2,"wins":3},"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":6,"losses":5,"wins":7},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":1,"wins":3},"z-ai/glm-5.2":{"draws":8,"losses":6,"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":2,"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":4,"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":2,"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":10,"wins":14},"gpt-5.4-nano":{"draws":10,"losses":11,"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":2,"losses":5,"wins":1},"gpt-5.6-terra":{"draws":4,"losses":6,"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":6,"losses":2,"wins":2},"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":2,"losses":4,"wins":0},"openai/gpt-oss-120b":{"draws":2,"losses":8,"wins":0},"qwen/qwen3.7-max":{"draws":4,"losses":1,"wins":1},"qwen/qwen3.7-plus":{"draws":2,"losses":4,"wins":0},"stepfun/step-3.7-flash":{"draws":0,"losses":6,"wins":4},"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":12,"wins":4},"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":4,"wins":0},"cohere/north-mini-code":{"draws":3,"losses":1,"wins":4},"deepseek/deepseek-v4-flash":{"draws":12,"losses":9,"wins":5},"deepseek/deepseek-v4-pro":{"draws":3,"losses":6,"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":9,"losses":15,"wins":12},"gpt-5.4-nano":{"draws":8,"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":3,"wins":1},"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":2,"wins":4},"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":7,"losses":10,"wins":9},"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":16,"losses":7,"wins":9},"deepseek/deepseek-v4-pro":{"draws":4,"losses":0,"wins":4},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":2},"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":4},"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":22,"losses":3,"wins":19},"gpt-5.5":{"draws":8,"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":2,"wins":1},"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":5,"losses":0,"wins":3},"poolside/laguna-s-2.1":{"draws":0,"losses":3,"wins":3},"qwen/qwen3.7-max":{"draws":4,"losses":2,"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":12,"losses":8,"wins":8},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":9,"losses":9,"wins":4},"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":5,"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":4},"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":2,"losses":2,"wins":2},"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":2},"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":5,"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},"tencent/hy3-preview":{"draws":0,"losses":2,"wins":0},"thinkingmachines/inkling":{"draws":18,"losses":13,"wins":19},"x-ai/grok-4.5":{"draws":18,"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":9},"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":27},"deepseek/deepseek-v4-pro":{"draws":4,"losses":6,"wins":12},"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":7},"gpt-5.4":{"draws":8,"losses":13,"wins":5},"gpt-5.4-mini":{"draws":22,"losses":1,"wins":21},"gpt-5.4-nano":{"draws":21,"losses":16,"wins":25},"gpt-5.5":{"draws":8,"losses":3,"wins":11},"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":3,"wins":9},"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":7,"losses":3,"wins":10},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":35,"losses":32,"wins":25},"nex-agi/nex-n2-pro":{"draws":5,"losses":3,"wins":8},"o3":{"draws":9,"losses":7,"wins":14},"openai/gpt-oss-120b":{"draws":9,"losses":0,"wins":13},"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":7,"losses":5,"wins":8},"thinkingmachines/inkling":{"draws":10,"losses":5,"wins":23},"x-ai/grok-4.5":{"draws":20,"losses":24,"wins":14},"xiaomi/mimo-v2.5":{"draws":10,"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":9,"losses":15,"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":11,"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":6,"wins":4},"google/gemma-4-31b-it":{"draws":0,"losses":10,"wins":8},"gpt-4.1":{"draws":0,"losses":6,"wins":2},"gpt-5":{"draws":4,"losses":4,"wins":2},"gpt-5.4":{"draws":12,"losses":17,"wins":3},"gpt-5.4-mini":{"draws":32,"losses":32,"wins":40},"gpt-5.4-nano":{"draws":36,"losses":36,"wins":34},"gpt-5.5":{"draws":13,"losses":8,"wins":5},"gpt-5.6-luna":{"draws":8,"losses":3,"wins":17},"gpt-5.6-sol":{"draws":6,"losses":10,"wins":6},"gpt-5.6-terra":{"draws":11,"losses":9,"wins":6},"inclusionai/ling-3.0-flash":{"draws":2,"losses":4,"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":6,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":1,"wins":2},"moonshotai/kimi-k3":{"draws":7,"losses":21,"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":10,"wins":6},"poolside/laguna-s-2.1":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.7-max":{"draws":4,"losses":6,"wins":6},"qwen/qwen3.7-plus":{"draws":0,"losses":4,"wins":12},"stepfun/step-3.7-flash":{"draws":9,"losses":14,"wins":13},"tencent/hy3-preview":{"draws":7,"losses":6,"wins":7},"thinkingmachines/inkling":{"draws":5,"losses":6,"wins":5},"x-ai/grok-4.5":{"draws":15,"losses":31,"wins":8},"x-ai/grok-build-0.1":{"draws":1,"losses":0,"wins":1},"xiaomi/mimo-v2.5":{"draws":16,"losses":12,"wins":14},"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":10,"wins":10},"deepseek/deepseek-v4-pro":{"draws":2,"losses":4,"wins":6},"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":13,"wins":9},"gpt-5.4-nano":{"draws":12,"losses":11,"wins":15},"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":4,"losses":3,"wins":3},"inclusionai/ling-3.0-flash":{"draws":1,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":0,"losses":0,"wins":6},"minimax/minimax-m3":{"draws":1,"losses":3,"wins":6},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":4},"moonshotai/kimi-k3":{"draws":4,"losses":7,"wins":5},"nex-agi/nex-n2-pro":{"draws":4,"losses":4,"wins":2},"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":5,"wins":3},"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":10,"wins":1}},"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":24,"wins":4},"claude-sonnet-5":{"draws":9,"losses":17,"wins":12},"cohere/north-mini-code":{"draws":5,"losses":1,"wins":0},"deepseek/deepseek-v4-flash":{"draws":16,"losses":27,"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":6,"wins":9},"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":9},"gpt-5":{"draws":5,"losses":12,"wins":11},"gpt-5.4":{"draws":19,"losses":0,"wins":5},"gpt-5.4-mini":{"draws":37,"losses":29,"wins":34},"gpt-5.4-nano":{"draws":24,"losses":37,"wins":43},"gpt-5.5":{"draws":9,"losses":7,"wins":6},"gpt-5.6-luna":{"draws":19,"losses":12,"wins":15},"gpt-5.6-sol":{"draws":11,"losses":15,"wins":12},"gpt-5.6-terra":{"draws":15,"losses":12,"wins":13},"inclusionai/ling-3.0-flash":{"draws":2,"losses":2,"wins":6},"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":12,"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":10,"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":9,"losses":15,"wins":12},"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":3,"wins":5},"z-ai/glm-5.2":{"draws":32,"losses":28,"wins":30}}}}}