{"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":"2026-08-06T09:40:24Z","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-2026-07-30":11},"run_count":8,"token_priced_attempt_count":11,"total":12.660969999999999},"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-2026-07-30":8},"run_count":8,"token_priced_attempt_count":8,"total":4.0371999999999995}},"codegen_cost_usd":{"admitted_cell_count":15,"cell_count":16,"cost_basis_counts":{"local_list_price_estimate":19},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":1.91725,"mean":1.043635625,"median":0.8756600000000001,"min":0.33027,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":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":83.35739367463012,"medium":67.61938022412933},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":19,"finish_reasons":["end_turn","max_tokens"],"indexed_attempts":23,"output_token_observations":19,"total_output_tokens":287406},"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":"9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999","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":"2026-08-05T04:44:21Z","match_totals_all":{"draws":214,"losses":321,"wins":1133},"match_totals_tracks":{"highest":{"draws":126,"losses":143,"wins":645},"medium":{"draws":88,"losses":178,"wins":488}},"model_slug":"claude-fable-5","overall":{"max":100.0,"mean":74.37835430818026,"min":48.695876476828644},"per_game":{"GB2-01":78.1799426050759,"GB2-02":74.10763610887963,"GB2-03":68.08895739222693,"GB2-04":100.0,"GB2-05":91.54521731701738,"GB2-06":86.35067612265574,"GB2-07":68.58671985118539,"GB2-08":100.0},"per_game_match_totals_all":{"GB2-01":{"draws":0,"losses":69,"wins":163},"GB2-02":{"draws":85,"losses":13,"wins":98},"GB2-03":{"draws":44,"losses":7,"wins":31},"GB2-04":{"draws":62,"losses":26,"wins":130},"GB2-05":{"draws":0,"losses":66,"wins":184},"GB2-06":{"draws":22,"losses":45,"wins":149},"GB2-07":{"draws":0,"losses":71,"wins":163},"GB2-08":{"draws":1,"losses":24,"wins":215}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":0,"losses":39,"wins":89},"GB2-02":{"draws":46,"losses":4,"wins":54},"GB2-03":{"draws":44,"losses":7,"wins":31},"GB2-04":{"draws":22,"losses":5,"wins":95},"GB2-05":{"draws":0,"losses":16,"wins":106},"GB2-06":{"draws":13,"losses":19,"wins":74},"GB2-07":{"draws":0,"losses":45,"wins":77},"GB2-08":{"draws":1,"losses":8,"wins":119}},"medium":{"GB2-01":{"draws":0,"losses":30,"wins":74},"GB2-02":{"draws":39,"losses":9,"wins":44},"GB2-04":{"draws":40,"losses":21,"wins":35},"GB2-05":{"draws":0,"losses":50,"wins":78},"GB2-06":{"draws":9,"losses":26,"wins":75},"GB2-07":{"draws":0,"losses":26,"wins":86},"GB2-08":{"draws":0,"losses":16,"wins":96}}},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1847.5791986207955,"GB2-02":1726.5724128111112,"GB2-03":1700.7450741307903,"GB2-04":1883.5568183188263,"GB2-05":2067.6605378147365,"GB2-06":1864.9721170328544,"GB2-07":1748.3528347421668,"GB2-08":2055.9331893482595},"medium":{"GB2-01":1771.292271328763,"GB2-02":1693.6055326946102,"GB2-04":1601.4398535001199,"GB2-05":1691.8487318885484,"GB2-06":1806.124039833382,"GB2-07":1757.9902710692518,"GB2-08":1854.8373059774533}},"per_game_tracks":{"highest":{"GB2-01":78.1799426050759,"GB2-02":74.10763610887963,"GB2-03":68.08895739222693,"GB2-04":100.0,"GB2-05":91.54521731701738,"GB2-06":86.35067612265574,"GB2-07":68.58671985118539,"GB2-08":100.0},"medium":{"GB2-01":70.43804280002986,"GB2-02":66.6442943191533,"GB2-04":48.695876476828644,"GB2-05":60.437208079044204,"GB2-06":80.83296452654382,"GB2-07":69.30390855095736,"GB2-08":76.98336681634814}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":83.35739367463012,"medium":65.3993149417304},"reasoning_agg":{"highest":{"max":100.0,"mean":83.35739367463012,"min":68.08895739222693},"medium":{"max":80.83296452654382,"mean":65.3993149417304,"min":48.695876476828644}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Setting not tested"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":100.0,"reasoning_variance":17.958078732899722},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":100.0,"expected_score":80.3796609898941,"reliability_score":96.83631325909597,"uncertainty_avg":3.16368674090403,"uncertainty_penalty":-2.9777326847360115},"medium":{"ceiling_score":80.83296452654382,"expected_score":84.72838054949037,"reliability_score":95.61251020244362,"uncertainty_avg":4.387489797556391,"uncertainty_penalty":19.329065607759972}}},{"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":1.3205149999999999,"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":0.44617968750000003,"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":14,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":16},"evidence_basis":"Standard list-price estimate","failed_cell_count":2,"max":0.5221625,"mean":0.2856328125,"median":0.2536225,"min":0.2178175,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":16},"run_count":16,"token_priced_attempt_count":16,"total":4.570125}},"codegen_cost_usd":{"admitted_cell_count":41,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":48},"evidence_basis":"Standard list-price estimate","failed_cell_count":7,"max":2.09943,"mean":0.703821875,"median":0.48028875,"min":0.2178175,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":48},"run_count":48,"token_priced_attempt_count":48,"total":33.78345},"codegen_latency_ms":{"attempt_count":48,"max_ms":999214,"mean_ms":286075.0416666667,"min_ms":51907,"run_count":48},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":16,"max_ms":999214,"mean_ms":596693.625,"min_ms":340056,"run_count":16},"medium":{"attempt_count":16,"max_ms":302283,"mean_ms":172049.4375,"min_ms":111251,"run_count":16},"none":{"attempt_count":16,"max_ms":344404,"mean_ms":89482.0625,"min_ms":51907,"run_count":16}},"codegen_output_tokens":{"attempt_count":48,"output_max":88360,"output_mean":25640.5,"output_min":5404,"run_count":48},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":16,"output_max":88360,"output_mean":52673.75,"output_min":31102,"run_count":16},"medium":{"attempt_count":16,"output_max":25625,"output_mean":15334.8125,"output_min":9676,"run_count":16},"none":{"attempt_count":16,"output_max":28699,"output_mean":8912.9375,"output_min":5404,"run_count":16}},"display_name":"Claude Opus 5","economics":{"all":74.03603303938935,"highest":81.79307965612657,"medium":74.34745635799888,"none":69.78432167559474},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":48,"finish_reasons":["end_turn"],"indexed_attempts":48,"output_token_observations":48,"reasoning_token_observations":48,"requested_max_output_token_observations":48,"requested_max_output_tokens":[128000],"total_output_tokens":1230744,"total_reasoning_output_tokens":878158,"total_visible_output_tokens":352586,"visible_token_observations":48},"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":"end_turn","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":128000,"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":"9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999","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":14,"evaluated_cells":16,"failed_game_aliases":["GB2-06","GB2-07"],"first_pass_admitted":14,"first_pass_rate":0.875,"model_code_failure_rate":0.125,"model_code_failures":2},"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":"2026-08-05T05:35:16Z","match_totals_all":{"draws":674,"losses":750,"wins":3049},"match_totals_tracks":{"highest":{"draws":75,"losses":170,"wins":841},"medium":{"draws":216,"losses":291,"wins":1139},"none":{"draws":383,"losses":289,"wins":1069}},"model_slug":"claude-opus-5","overall":{"max":100.0,"mean":72.35173547471699,"min":39.830660376507744},"per_game":{"GB2-01":61.3843149316053,"GB2-02":73.97689904691619,"GB2-03":97.33599973224807,"GB2-04":79.44376401396596,"GB2-05":86.33840661001909,"GB2-07":100.0,"GB2-08":74.0721732581313},"per_game_all":{"GB2-01":65.84781736157461,"GB2-02":67.22781778980263,"GB2-03":82.2022256498798,"GB2-04":55.28154308141859,"GB2-05":85.59135061266151,"GB2-07":88.38958993665153,"GB2-08":73.71188684373685},"per_game_match_totals_all":{"GB2-01":{"draws":149,"losses":151,"wins":379},"GB2-02":{"draws":218,"losses":53,"wins":291},"GB2-03":{"draws":47,"losses":88,"wins":385},"GB2-04":{"draws":237,"losses":156,"wins":293},"GB2-05":{"draws":0,"losses":78,"wins":638},"GB2-06":{"draws":15,"losses":5,"wins":106},"GB2-07":{"draws":0,"losses":68,"wins":400},"GB2-08":{"draws":8,"losses":151,"wins":557}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":2,"losses":54,"wins":92},"GB2-02":{"draws":40,"losses":21,"wins":75},"GB2-03":{"draws":0,"losses":9,"wins":111},"GB2-04":{"draws":33,"losses":20,"wins":143},"GB2-05":{"draws":0,"losses":22,"wins":140},"GB2-07":{"draws":0,"losses":1,"wins":101},"GB2-08":{"draws":0,"losses":43,"wins":179}},"medium":{"GB2-01":{"draws":24,"losses":74,"wins":150},"GB2-02":{"draws":82,"losses":17,"wins":97},"GB2-03":{"draws":8,"losses":15,"wins":167},"GB2-04":{"draws":102,"losses":70,"wins":68},"GB2-05":{"draws":0,"losses":30,"wins":236},"GB2-07":{"draws":0,"losses":39,"wins":205},"GB2-08":{"draws":0,"losses":46,"wins":216}},"none":{"GB2-01":{"draws":123,"losses":23,"wins":137},"GB2-02":{"draws":96,"losses":15,"wins":119},"GB2-03":{"draws":39,"losses":64,"wins":107},"GB2-04":{"draws":102,"losses":66,"wins":82},"GB2-05":{"draws":0,"losses":26,"wins":262},"GB2-06":{"draws":15,"losses":5,"wins":106},"GB2-07":{"draws":0,"losses":28,"wins":94},"GB2-08":{"draws":8,"losses":62,"wins":162}}},"per_game_raw_elo_all":{"GB2-01":1723.314682709126,"GB2-02":1696.7279087151728,"GB2-03":1799.0539503154835,"GB2-04":1635.0289517134163,"GB2-05":1997.145341277627,"GB2-07":1972.4874684823608,"GB2-08":1825.1801340594436},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1684.77832627723,"GB2-02":1735.0704845544929,"GB2-03":1912.3418465864775,"GB2-04":1772.8326811225836,"GB2-05":2013.0080873189577,"GB2-07":2105.4058440588437,"GB2-08":1829.26608314685},"medium":{"GB2-01":1741.6169869231062,"GB2-02":1681.6024352152729,"GB2-03":1904.2815482198878,"GB2-04":1547.6697759458552,"GB2-05":1961.7749539008435,"GB2-07":1940.4116114258877,"GB2-08":1897.8126562352456},"none":{"GB2-01":1743.5487349270413,"GB2-02":1673.5108063757525,"GB2-03":1580.538456140085,"GB2-04":1584.5843980718105,"GB2-05":2016.6529826130795,"GB2-06":1968.7663861920653,"GB2-07":1871.6449499623504,"GB2-08":1748.4616627962346}},"per_game_tracks":{"highest":{"GB2-01":61.3843149316053,"GB2-02":73.97689904691619,"GB2-03":97.33599973224807,"GB2-04":79.44376401396596,"GB2-05":86.33840661001909,"GB2-07":100.0,"GB2-08":74.0721732581313},"medium":{"GB2-01":67.86856369283086,"GB2-02":64.38340087999147,"GB2-03":97.66928476084789,"GB2-04":39.830660376507744,"GB2-05":82.88602996661304,"GB2-07":85.63226983764412,"GB2-08":82.16198499155695},"none":{"GB2-01":68.29057346028767,"GB2-02":63.32315344250023,"GB2-03":51.60139245654345,"GB2-04":46.570204853782045,"GB2-05":87.54961526135239,"GB2-06":96.50163167645941,"GB2-07":79.53649997231051,"GB2-08":64.90150228152228}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":77.65553263999308,"medium":71.90649629376915,"none":67.49317749038875},"reasoning_agg":{"highest":{"max":100.0,"mean":77.65553263999308,"min":61.3843149316053},"medium":{"max":97.66928476084789,"mean":71.90649629376915,"min":39.830660376507744},"none":{"max":96.50163167645941,"mean":67.49317749038875,"min":46.570204853782045}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Thinking disabled"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":100.0,"expected_score":87.30028025535043,"reasoning_variance":10.162355149604338,"reliability_score":94.67688300747827,"uncertainty_avg":5.3231169925217285,"uncertainty_penalty":14.94854478063344},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":100.0,"expected_score":80.98938890405454,"reliability_score":88.90057621813533,"uncertainty_avg":11.099423781864676,"uncertainty_penalty":3.3338562640614526},"medium":{"ceiling_score":97.66928476084789,"expected_score":89.71212447888995,"reliability_score":97.254844081128,"uncertainty_avg":2.745155918872,"uncertainty_penalty":17.805628185120796},"none":{"ceiling_score":96.50163167645941,"expected_score":92.29941146021842,"reliability_score":98.06359694892434,"uncertainty_avg":1.9364030510756551,"uncertainty_penalty":24.806233969829677}}},{"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-2026-07-30":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-2026-07-30":9},"run_count":8,"token_priced_attempt_count":9,"total":3.9891499999999995},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":10},"evidence_basis":"Standard list-price estimate","max":0.15985749999999999,"mean":0.09356500000000001,"median":0.07461,"min":0.06826499999999999,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":10},"run_count":8,"token_priced_attempt_count":10,"total":0.74852}},"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":1.0782631249999999,"median":0.5065824999999999,"min":0.06826499999999999,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":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":56.37407351184414,"highest":72.12620352118518,"medium":46.897011088603556,"none":50.09900592574366},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":28,"finish_reasons":["stop"],"indexed_attempts":28,"output_token_observations":28,"total_output_tokens":1667969},"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":"stop","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":"9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999","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":"2026-08-05T06:55:12Z","match_totals_all":{"draws":804,"losses":567,"wins":1315},"match_totals_tracks":{"highest":{"draws":172,"losses":143,"wins":565},"medium":{"draws":291,"losses":240,"wins":375},"none":{"draws":341,"losses":184,"wins":375}},"model_slug":"gpt-5-4","overall":{"max":100.0,"mean":56.37407351184413,"min":17.553436099642553},"per_game":{"GB2-01":100.0,"GB2-02":56.16935098002528,"GB2-03":32.829666021771125,"GB2-04":58.68991920919109,"GB2-05":94.13268706699881,"GB2-06":100.0,"GB2-07":89.20483886963211,"GB2-08":45.98316602186302},"per_game_all":{"GB2-01":87.8635957396151,"GB2-02":31.10770926077529,"GB2-03":39.090038566343914,"GB2-04":40.85351797238797,"GB2-05":71.42560874588769,"GB2-06":88.38340097324435,"GB2-07":57.51527043093074,"GB2-08":34.75344640556803},"per_game_match_totals_all":{"GB2-01":{"draws":29,"losses":30,"wins":285},"GB2-02":{"draws":251,"losses":22,"wins":37},"GB2-03":{"draws":113,"losses":75,"wins":78},"GB2-04":{"draws":211,"losses":54,"wins":81},"GB2-05":{"draws":0,"losses":113,"wins":259},"GB2-06":{"draws":33,"losses":41,"wins":234},"GB2-07":{"draws":0,"losses":119,"wins":239},"GB2-08":{"draws":167,"losses":113,"wins":102}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":0,"losses":5,"wins":117},"GB2-02":{"draws":63,"losses":9,"wins":30},"GB2-03":{"draws":20,"losses":28,"wins":22},"GB2-04":{"draws":47,"losses":29,"wins":42},"GB2-05":{"draws":0,"losses":8,"wins":108},"GB2-06":{"draws":11,"losses":8,"wins":85},"GB2-07":{"draws":0,"losses":12,"wins":110},"GB2-08":{"draws":31,"losses":44,"wins":51}},"medium":{"GB2-01":{"draws":27,"losses":18,"wins":57},"GB2-02":{"draws":86,"losses":9,"wins":5},"GB2-03":{"draws":50,"losses":29,"wins":21},"GB2-04":{"draws":72,"losses":15,"wins":25},"GB2-05":{"draws":0,"losses":78,"wins":64},"GB2-06":{"draws":11,"losses":6,"wins":83},"GB2-07":{"draws":0,"losses":44,"wins":82},"GB2-08":{"draws":45,"losses":41,"wins":38}},"none":{"GB2-01":{"draws":2,"losses":7,"wins":111},"GB2-02":{"draws":102,"losses":4,"wins":2},"GB2-03":{"draws":43,"losses":18,"wins":35},"GB2-04":{"draws":92,"losses":10,"wins":14},"GB2-05":{"draws":0,"losses":27,"wins":87},"GB2-06":{"draws":11,"losses":27,"wins":66},"GB2-07":{"draws":0,"losses":63,"wins":47},"GB2-08":{"draws":91,"losses":28,"wins":13}}},"per_game_raw_elo_all":{"GB2-01":1949.8384393785384,"GB2-02":1522.704231219449,"GB2-03":1496.9136309333462,"GB2-04":1554.0987495445395,"GB2-05":1824.9902872414323,"GB2-06":1887.014415846832,"GB2-07":1624.1330864587253,"GB2-08":1479.14181904964},"per_game_raw_elo_tracks":{"highest":{"GB2-01":2074.1985502899956,"GB2-02":1641.8435026438312,"GB2-03":1458.0279417186953,"GB2-04":1653.3360960868538,"GB2-05":2099.7620540108987,"GB2-06":2009.1734856604521,"GB2-07":1980.5083189186464,"GB2-08":1578.607560959858},"medium":{"GB2-01":1726.1208318729848,"GB2-02":1459.0231648557492,"GB2-03":1419.5707786523924,"GB2-04":1514.3585869717513,"GB2-05":1522.7373353693486,"GB2-06":1955.8803057155433,"GB2-07":1629.8152809272333,"GB2-08":1437.4436413007966},"none":{"GB2-01":2049.195935972635,"GB2-02":1467.2460261587667,"GB2-03":1613.1421724289517,"GB2-04":1494.6015655750139,"GB2-05":1852.4714723440495,"GB2-06":1695.989456164501,"GB2-07":1262.0756595302967,"GB2-08":1421.374254888266}},"per_game_tracks":{"highest":{"GB2-01":100.0,"GB2-02":56.16935098002528,"GB2-03":32.829666021771125,"GB2-04":58.68991920919109,"GB2-05":94.13268706699881,"GB2-06":100.0,"GB2-07":89.20483886963211,"GB2-08":45.98316602186302},"medium":{"GB2-01":66.0359053103189,"GB2-02":17.553436099642553,"GB2-03":28.421961467653944,"GB2-04":33.64521003475906,"GB2-05":46.55395008692883,"GB2-06":94.87005862041984,"GB2-07":58.11004723437738,"GB2-08":29.985519854727933},"none":{"GB2-01":97.55488190852645,"GB2-02":19.60034070265804,"GB2-03":56.01848820960669,"GB2-04":30.225424673213766,"GB2-05":73.59018908373541,"GB2-06":70.28014429931316,"GB2-07":25.230925188782717,"GB2-08":28.291653340113125}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":72.12620352118518,"medium":46.897011088603556,"none":50.09900592574367},"reasoning_agg":{"highest":{"max":100.0,"mean":72.12620352118518,"min":32.829666021771125},"medium":{"max":94.87005862041984,"mean":46.897011088603556,"min":17.553436099642553},"none":{"max":97.55488190852645,"mean":50.09900592574367,"min":19.60034070265804}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":100.0,"expected_score":57.84416897785146,"reasoning_variance":25.22919243258162,"reliability_score":96.27671334760234,"uncertainty_avg":3.723286652397666,"uncertainty_penalty":1.4700954660073293},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":100.0,"expected_score":67.68421956854476,"reliability_score":95.75058992420051,"uncertainty_avg":4.249410075799486,"uncertainty_penalty":-4.441983952640413},"medium":{"ceiling_score":94.87005862041984,"expected_score":48.54552427983166,"reliability_score":96.4503411400382,"uncertainty_avg":3.5496588599617986,"uncertainty_penalty":1.6485131912281048},"none":{"ceiling_score":97.55488190852645,"expected_score":57.30276308517796,"reliability_score":96.62920897856829,"uncertainty_avg":3.370791021431714,"uncertainty_penalty":7.203757159434289}}},{"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-2026-07-30":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":0.36661499999999997,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":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":0.12146437500000001,"median":0.124865,"min":0.09045,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":9},"run_count":9,"token_priced_attempt_count":9,"total":1.069485}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":27},"evidence_basis":"Standard list-price estimate","failed_cell_count":2,"max":12.915325,"mean":3.549568958333333,"median":0.4352825,"min":0.09045,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":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":13803.555555555555,"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":56.06247655095409,"highest":66.33428289138148,"medium":58.47896809317596,"none":43.37417866830485},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":27,"finish_reasons":["stop"],"indexed_attempts":51,"output_token_observations":27,"total_output_tokens":2820489},"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":"9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999","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":"2026-08-05T05:17:02Z","match_totals_all":{"draws":528,"losses":758,"wins":1370},"match_totals_tracks":{"highest":{"draws":101,"losses":247,"wins":554},"medium":{"draws":190,"losses":218,"wins":464},"none":{"draws":237,"losses":293,"wins":352}},"model_slug":"gpt-5-6-sol","overall":{"max":100.0,"mean":55.07733741392539,"min":19.935559087203618},"per_game":{"GB2-01":79.75919518016714,"GB2-02":100.0,"GB2-03":64.47438248139325,"GB2-04":58.064818144611,"GB2-05":67.68754926078236,"GB2-06":82.35863358446323,"GB2-07":58.3941253924312,"GB2-08":19.935559087203618},"per_game_all":{"GB2-01":63.0371367463631,"GB2-02":58.56037617342755,"GB2-03":50.90123901084356,"GB2-04":40.22268736400856,"GB2-05":62.44168335857355,"GB2-06":70.54306059035417,"GB2-07":59.58750764115968,"GB2-08":43.20612152290257},"per_game_match_totals_all":{"GB2-01":{"draws":18,"losses":108,"wins":234},"GB2-02":{"draws":142,"losses":32,"wins":118},"GB2-03":{"draws":71,"losses":72,"wins":113},"GB2-04":{"draws":231,"losses":24,"wins":91},"GB2-05":{"draws":0,"losses":126,"wins":226},"GB2-06":{"draws":21,"losses":112,"wins":197},"GB2-07":{"draws":0,"losses":145,"wins":223},"GB2-08":{"draws":45,"losses":139,"wins":168}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":0,"losses":31,"wins":97},"GB2-02":{"draws":15,"losses":11,"wins":82},"GB2-03":{"draws":7,"losses":26,"wins":51},"GB2-04":{"draws":53,"losses":8,"wins":57},"GB2-05":{"draws":0,"losses":34,"wins":80},"GB2-06":{"draws":5,"losses":26,"wins":73},"GB2-07":{"draws":0,"losses":39,"wins":83},"GB2-08":{"draws":21,"losses":72,"wins":31}},"medium":{"GB2-01":{"draws":1,"losses":43,"wins":76},"GB2-02":{"draws":53,"losses":12,"wins":29},"GB2-03":{"draws":16,"losses":17,"wins":39},"GB2-04":{"draws":100,"losses":9,"wins":17},"GB2-05":{"draws":0,"losses":44,"wins":74},"GB2-06":{"draws":13,"losses":18,"wins":77},"GB2-07":{"draws":0,"losses":50,"wins":76},"GB2-08":{"draws":7,"losses":25,"wins":76}},"none":{"GB2-01":{"draws":17,"losses":34,"wins":61},"GB2-02":{"draws":74,"losses":9,"wins":7},"GB2-03":{"draws":48,"losses":29,"wins":23},"GB2-04":{"draws":78,"losses":7,"wins":17},"GB2-05":{"draws":0,"losses":48,"wins":72},"GB2-06":{"draws":3,"losses":68,"wins":47},"GB2-07":{"draws":0,"losses":56,"wins":64},"GB2-08":{"draws":17,"losses":42,"wins":61}}},"per_game_raw_elo_all":{"GB2-01":1692.083115319151,"GB2-02":1654.2021282333335,"GB2-03":1580.1195210207468,"GB2-04":1550.6734839237981,"GB2-05":1717.5690664880865,"GB2-06":1697.72969615349,"GB2-07":1646.9317937330654,"GB2-08":1555.3773690887413},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1863.9196141834548,"GB2-02":1848.6927283605112,"GB2-03":1674.9780101817953,"GB2-04":1649.8433166463897,"GB2-05":1781.323497099848,"GB2-06":1823.2710278734628,"GB2-07":1633.5864634999832,"GB2-08":1348.5846777749914},"medium":{"GB2-01":1666.6223623937797,"GB2-02":1597.7113348170712,"GB2-03":1579.797238543221,"GB2-04":1505.241305078549,"GB2-05":1717.0927003529362,"GB2-06":1851.262045065243,"GB2-07":1666.4268161629404,"GB2-08":1785.981513065026},"none":{"GB2-01":1545.707369380218,"GB2-02":1516.202321522418,"GB2-03":1485.5833143372236,"GB2-04":1496.9358300464557,"GB2-05":1654.2910020114755,"GB2-06":1418.6560155217642,"GB2-07":1640.7821015362729,"GB2-08":1531.5659164262063}},"per_game_tracks":{"highest":{"GB2-01":79.75919518016714,"GB2-02":100.0,"GB2-03":64.47438248139325,"GB2-04":58.064818144611,"GB2-05":67.68754926078236,"GB2-06":82.35863358446323,"GB2-07":58.3941253924312,"GB2-08":19.935559087203618},"medium":{"GB2-01":60.58028362371113,"GB2-02":46.52465329657686,"GB2-03":50.3566269308408,"GB2-04":32.39551820970374,"GB2-05":62.411231853726754,"GB2-06":85.08346922744767,"GB2-07":61.361579256614846,"GB2-08":69.11838234678588},"none":{"GB2-01":48.77193143521104,"GB2-02":29.15647522370581,"GB2-03":37.87270762029662,"GB2-04":30.207725737710934,"GB2-05":57.22626896121154,"GB2-06":44.187078959151634,"GB2-07":59.006818274433016,"GB2-08":40.56442313471822}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":66.33428289138148,"medium":56.782115654344075,"none":42.11561369605062},"reasoning_agg":{"highest":{"max":100.0,"mean":66.33428289138148,"min":19.935559087203618},"medium":{"max":85.08346922744767,"mean":56.782115654344075,"min":32.39551820970374},"none":{"max":59.006818274433016,"mean":42.11561369605062,"min":29.15647522370581}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":100.0,"expected_score":57.96301915778301,"reasoning_variance":24.218669195330854,"reliability_score":96.10412937136394,"uncertainty_avg":3.895870628636064,"uncertainty_penalty":2.885681743857617},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":100.0,"expected_score":59.71820702568358,"reliability_score":96.59918947172211,"uncertainty_avg":3.400810528277892,"uncertainty_penalty":-6.616075865697894},"medium":{"ceiling_score":85.08346922744767,"expected_score":64.70889440657143,"reliability_score":95.5465948784993,"uncertainty_avg":4.453405121500695,"uncertainty_penalty":7.9267787522273565},"none":{"ceiling_score":59.006818274433016,"expected_score":49.46195604109401,"reliability_score":96.1666037638704,"uncertainty_avg":3.8333962361296052,"uncertainty_penalty":7.346342345043389}}},{"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-2026-07-30":9},"run_count":8,"token_priced_attempt_count":9,"total":7.449890000000001},"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-2026-07-30":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-2026-07-30":8},"run_count":8,"token_priced_attempt_count":8,"total":1.2628249999999999}},"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":0.20305499999999999,"min":0.131495,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":25},"run_count":24,"token_priced_attempt_count":25,"total":10.456240000000001},"codegen_latency_ms":{"attempt_count":25,"max_ms":604929,"mean_ms":175315.375,"min_ms":28646,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":9,"max_ms":604929,"mean_ms":421376.5,"min_ms":132563,"run_count":8},"medium":{"attempt_count":8,"max_ms":137577,"mean_ms":68957.5,"min_ms":35597,"run_count":8},"none":{"attempt_count":8,"max_ms":48121,"mean_ms":35612.125,"min_ms":28646,"run_count":8}},"codegen_output_tokens":{"attempt_count":25,"output_max":52366,"output_mean":14843.708333333334,"output_min":2908,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":9,"output_max":52366,"output_mean":34524.125,"output_min":11990,"run_count":8},"medium":{"attempt_count":8,"output_max":11318,"output_mean":6205.25,"output_min":3583,"run_count":8},"none":{"attempt_count":8,"output_max":5116,"output_mean":3801.75,"output_min":2908,"run_count":8}},"display_name":"Claude Opus 4.8","economics":{"all":52.008907329781586,"highest":68.15597422847155,"medium":42.28532376648441,"none":44.39353927490981},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":25,"finish_reasons":["end_turn","max_tokens"],"indexed_attempts":31,"output_token_observations":25,"total_output_tokens":356249},"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":"9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999","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":"2026-08-05T04:43:45Z","match_totals_all":{"draws":664,"losses":716,"wins":1188},"match_totals_tracks":{"highest":{"draws":109,"losses":223,"wins":532},"medium":{"draws":357,"losses":247,"wins":314},"none":{"draws":198,"losses":246,"wins":342}},"model_slug":"claude-opus-4-8","overall":{"max":86.15355149666183,"mean":50.379878430994545,"min":16.591663020618228},"per_game":{"GB2-01":55.79662342229386,"GB2-02":81.91642338098146,"GB2-04":57.093874217143885,"GB2-05":49.197008068659926,"GB2-06":86.15355149666183,"GB2-07":76.93117424326455,"GB2-08":70.00316477029536},"per_game_all":{"GB2-01":49.04267542970583,"GB2-02":38.66565992991068,"GB2-04":37.56314149571693,"GB2-05":45.08936538590808,"GB2-06":73.70065905782901,"GB2-07":64.7069050029542,"GB2-08":55.293945006446336},"per_game_match_totals_all":{"GB2-01":{"draws":69,"losses":128,"wins":165},"GB2-02":{"draws":202,"losses":19,"wins":69},"GB2-03":{"draws":43,"losses":20,"wins":15},"GB2-04":{"draws":234,"losses":46,"wins":70},"GB2-05":{"draws":0,"losses":202,"wins":198},"GB2-06":{"draws":14,"losses":89,"wins":225},"GB2-07":{"draws":0,"losses":119,"wins":253},"GB2-08":{"draws":102,"losses":93,"wins":193}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":20,"losses":44,"wins":66},"GB2-02":{"draws":39,"losses":5,"wins":64},"GB2-04":{"draws":48,"losses":18,"wins":54},"GB2-05":{"draws":0,"losses":74,"wins":68},"GB2-06":{"draws":2,"losses":21,"wins":83},"GB2-07":{"draws":0,"losses":30,"wins":96},"GB2-08":{"draws":0,"losses":31,"wins":101}},"medium":{"GB2-01":{"draws":21,"losses":51,"wins":48},"GB2-02":{"draws":82,"losses":6,"wins":2},"GB2-03":{"draws":43,"losses":20,"wins":15},"GB2-04":{"draws":107,"losses":13,"wins":6},"GB2-05":{"draws":0,"losses":62,"wins":74},"GB2-06":{"draws":2,"losses":27,"wins":81},"GB2-07":{"draws":0,"losses":42,"wins":82},"GB2-08":{"draws":102,"losses":26,"wins":6}},"none":{"GB2-01":{"draws":28,"losses":33,"wins":51},"GB2-02":{"draws":81,"losses":8,"wins":3},"GB2-04":{"draws":79,"losses":15,"wins":10},"GB2-05":{"draws":0,"losses":66,"wins":56},"GB2-06":{"draws":10,"losses":41,"wins":61},"GB2-07":{"draws":0,"losses":47,"wins":75},"GB2-08":{"draws":0,"losses":36,"wins":86}}},"per_game_raw_elo_all":{"GB2-01":1547.1934482102622,"GB2-02":1559.9603043862965,"GB2-04":1535.5859982387392,"GB2-05":1506.1977483889812,"GB2-06":1731.0866039947925,"GB2-07":1704.3795655219517,"GB2-08":1660.4958582267727},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1615.7106919093821,"GB2-02":1762.8973316433855,"GB2-04":1644.1138216200993,"GB2-05":1554.595661388488,"GB2-06":1862.8948429941306,"GB2-07":1841.737030413011,"GB2-08":1790.1758610356108},"medium":{"GB2-01":1453.9647599651043,"GB2-02":1456.590051762334,"GB2-03":1463.33064839219,"GB2-04":1476.5540638545763,"GB2-05":1550.5784583726859,"GB2-06":1817.5613422611286,"GB2-07":1683.4145361717362,"GB2-08":1408.747777600697},"none":{"GB2-01":1571.9048927563001,"GB2-02":1460.39352975317,"GB2-04":1486.0901092415422,"GB2-05":1413.4191254057696,"GB2-06":1512.8036267291184,"GB2-07":1587.987129981108,"GB2-08":1782.5639360440102}},"per_game_tracks":{"highest":{"GB2-01":55.79662342229386,"GB2-02":81.91642338098146,"GB2-04":57.093874217143885,"GB2-05":49.197008068659926,"GB2-06":86.15355149666183,"GB2-07":76.93117424326455,"GB2-08":70.00316477029536},"medium":{"GB2-01":40.027558696955204,"GB2-02":16.591663020618228,"GB2-03":33.94213073013162,"GB2-04":27.261376379497502,"GB2-05":48.80361235858553,"GB2-06":81.9183167340137,"GB2-07":62.84516887775912,"GB2-08":26.892763334314395},"none":{"GB2-01":51.303844169868434,"GB2-02":17.488893388132354,"GB2-04":28.334173890509387,"GB2-05":37.26747573047881,"GB2-06":53.03010894281152,"GB2-07":54.34437188783892,"GB2-08":68.98590691472927}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":65.9182916044786,"medium":42.28532376648441,"none":42.93601992202063},"reasoning_agg":{"highest":{"max":86.15355149666183,"mean":65.9182916044786,"min":49.197008068659926},"medium":{"max":81.9183167340137,"mean":42.28532376648441,"min":16.591663020618228},"none":{"max":68.98590691472927,"mean":42.93601992202063,"min":17.488893388132354}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Thinking field omitted"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":86.15355149666183,"expected_score":52.177857238541684,"reasoning_variance":23.632967837994187,"reliability_score":97.59849989713418,"uncertainty_avg":2.401500102865819,"uncertainty_penalty":1.797978807547139},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":86.15355149666183,"expected_score":62.192238096817206,"reliability_score":98.42135576590115,"uncertainty_avg":1.578644234098843,"uncertainty_penalty":-3.7260535076613905},"medium":{"ceiling_score":81.9183167340137,"expected_score":40.623296551732274,"reliability_score":96.47871660682887,"uncertainty_avg":3.521283393171127,"uncertainty_penalty":-1.6620272147521362},"none":{"ceiling_score":68.98590691472927,"expected_score":50.976965236499396,"reliability_score":96.61212565393964,"uncertainty_avg":3.387874346060354,"uncertainty_penalty":8.040945314478769}}},{"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-2026-07-30":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":0.44285687500000004,"median":0.4176025,"min":0.34269,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":9},"run_count":8,"token_priced_attempt_count":9,"total":3.5428550000000003},"none":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.156555,"mean":0.1422525,"median":0.14850249999999998,"min":0.12078,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":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-2026-07-30":26},"run_count":24,"token_priced_attempt_count":26,"total":26.566349999999996},"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":50.59808509713923,"highest":66.32419996398228,"medium":48.92694853208289,"none":37.189039884034734},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":26,"finish_reasons":["stop"],"indexed_attempts":26,"output_token_observations":26,"total_output_tokens":851788},"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":"stop","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":"9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999","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":"2026-08-05T05:26:46Z","match_totals_all":{"draws":901,"losses":651,"wins":1028},"match_totals_tracks":{"highest":{"draws":153,"losses":171,"wins":468},"medium":{"draws":316,"losses":267,"wins":361},"none":{"draws":432,"losses":213,"wins":199}},"model_slug":"gpt-5-5","overall":{"max":90.99516388242985,"mean":49.68055448034795,"min":12.006801731616441},"per_game":{"GB2-01":72.50601879226893,"GB2-03":46.36721779549708,"GB2-04":12.006801731616441,"GB2-05":84.01665989467725,"GB2-06":90.18024385545019,"GB2-07":90.99516388242985,"GB2-08":68.19729379593623},"per_game_all":{"GB2-01":60.830760525225664,"GB2-03":37.73330009684258,"GB2-04":21.89985189179743,"GB2-05":66.88800223438088,"GB2-07":68.61187545982244,"GB2-08":47.62472037476643},"per_game_match_totals_all":{"GB2-01":{"draws":224,"losses":52,"wins":124},"GB2-02":{"draws":148,"losses":21,"wins":25},"GB2-03":{"draws":126,"losses":87,"wins":69},"GB2-04":{"draws":219,"losses":86,"wins":47},"GB2-05":{"draws":0,"losses":101,"wins":247},"GB2-06":{"draws":9,"losses":103,"wins":128},"GB2-07":{"draws":0,"losses":106,"wins":260},"GB2-08":{"draws":175,"losses":95,"wins":128}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":36,"losses":18,"wins":70},"GB2-03":{"draws":33,"losses":29,"wins":26},"GB2-04":{"draws":56,"losses":40,"wins":10},"GB2-05":{"draws":0,"losses":22,"wins":96},"GB2-06":{"draws":7,"losses":21,"wins":76},"GB2-07":{"draws":0,"losses":9,"wins":113},"GB2-08":{"draws":21,"losses":32,"wins":77}},"medium":{"GB2-01":{"draws":78,"losses":14,"wins":36},"GB2-02":{"draws":56,"losses":11,"wins":25},"GB2-03":{"draws":48,"losses":27,"wins":19},"GB2-04":{"draws":79,"losses":25,"wins":24},"GB2-05":{"draws":0,"losses":33,"wins":83},"GB2-06":{"draws":2,"losses":82,"wins":52},"GB2-07":{"draws":0,"losses":38,"wins":76},"GB2-08":{"draws":53,"losses":37,"wins":46}},"none":{"GB2-01":{"draws":110,"losses":20,"wins":18},"GB2-02":{"draws":92,"losses":10,"wins":0},"GB2-03":{"draws":45,"losses":31,"wins":24},"GB2-04":{"draws":84,"losses":21,"wins":13},"GB2-05":{"draws":0,"losses":46,"wins":68},"GB2-07":{"draws":0,"losses":59,"wins":71},"GB2-08":{"draws":101,"losses":26,"wins":5}}},"per_game_raw_elo_all":{"GB2-01":1667.4385265229278,"GB2-03":1485.888257803724,"GB2-04":1447.9538636444565,"GB2-05":1771.3686112256003,"GB2-07":1748.6743426354242,"GB2-08":1592.2297576419066},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1789.4305585121388,"GB2-03":1547.5150630244484,"GB2-04":1394.493662395028,"GB2-05":1977.5155798619357,"GB2-06":1905.694154233326,"GB2-07":2000.6669846925447,"GB2-08":1774.4726146237526},"medium":{"GB2-01":1647.795835483077,"GB2-02":1576.1451957449874,"GB2-03":1452.0203867601301,"GB2-04":1463.8284045199428,"GB2-05":1763.8599969928403,"GB2-06":1476.0649919553914,"GB2-07":1773.1661991465724,"GB2-08":1576.6942987321636},"none":{"GB2-01":1565.0891855735679,"GB2-02":1485.9195447594993,"GB2-03":1458.1293236265938,"GB2-04":1485.5395240183984,"GB2-05":1572.7302568220246,"GB2-07":1472.1898440671557,"GB2-08":1425.5223595698037}},"per_game_tracks":{"highest":{"GB2-01":72.50601879226893,"GB2-03":46.36721779549708,"GB2-04":12.006801731616441,"GB2-05":84.01665989467725,"GB2-06":90.18024385545019,"GB2-07":90.99516388242985,"GB2-08":68.19729379593623},"medium":{"GB2-01":58.87147462359901,"GB2-02":41.88652077650536,"GB2-03":32.8904510243238,"GB2-04":25.033306918921557,"GB2-05":66.26529025688052,"GB2-06":49.87158633438607,"GB2-07":70.68089553312336,"GB2-08":45.91606278892348},"none":{"GB2-01":51.11478815980904,"GB2-02":23.30438447793437,"GB2-03":33.94223147070685,"GB2-04":28.65944702485429,"GB2-05":50.38205655158486,"GB2-07":44.15956696391413,"GB2-08":28.760804539439587}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":64.14665776772328,"medium":48.92694853208289,"none":35.968057141237665},"reasoning_agg":{"highest":{"max":90.99516388242985,"mean":64.14665776772328,"min":12.006801731616441},"medium":{"max":70.68089553312336,"mean":48.92694853208289,"min":25.033306918921557},"none":{"max":51.11478815980904,"mean":35.968057141237665,"min":23.30438447793437}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":90.99516388242985,"expected_score":49.985889478652275,"reasoning_variance":28.17860062648562,"reliability_score":97.63151253543094,"uncertainty_avg":2.368487464569061,"uncertainty_penalty":0.30533499830432476},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":90.99516388242985,"expected_score":60.433065759473536,"reliability_score":96.67550168074203,"uncertainty_avg":3.3244983192579753,"uncertainty_penalty":-3.7135920082497478},"medium":{"ceiling_score":70.68089553312336,"expected_score":50.18811617054689,"reliability_score":97.30726878281757,"uncertainty_avg":2.692731217182433,"uncertainty_penalty":1.261167638464002},"none":{"ceiling_score":51.11478815980904,"expected_score":39.1637779247369,"reliability_score":97.64593018826567,"uncertainty_avg":2.354069811734339,"uncertainty_penalty":3.195720783499233}}},{"codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":22,"cell_count":8,"cost_basis_counts":{"provider_reported":50},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.19006573333333335,"mean":0.11809463333333332,"median":0.09664113333333335,"min":0.06671613333333333,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":50},"recorded_attempt_count":50,"run_count":24,"total":2.8342712000000003},"medium":{"admitted_cell_count":21,"cell_count":8,"cost_basis_counts":{"provider_reported":54},"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.15843093333333336,"mean":0.1253849,"median":0.12730913333333332,"min":0.06204813333333333,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":54},"recorded_attempt_count":54,"run_count":24,"total":3.0092376000000005},"none":{"admitted_cell_count":15,"cell_count":8,"cost_basis_counts":{"provider_reported":28},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.11634299999999999,"mean":0.07787519999999999,"median":0.0843883,"min":0.041110400000000005,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":28},"recorded_attempt_count":28,"run_count":16,"total":1.2460031999999999}},"codegen_cost_usd":{"admitted_cell_count":58,"cell_count":24,"cost_basis_counts":{"provider_reported":132},"evidence_basis":"Provider-reported","failed_cell_count":6,"max":0.19006573333333335,"mean":0.10711824444444444,"median":0.09929546666666667,"min":0.041110400000000005,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":132},"recorded_attempt_count":132,"run_count":64,"total":7.089512},"codegen_latency_ms":{"attempt_count":132,"max_ms":331882,"mean_ms":131309.9375,"min_ms":45373,"run_count":64},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":50,"max_ms":331882,"mean_ms":146027.25,"min_ms":52667,"run_count":24},"medium":{"attempt_count":54,"max_ms":256062,"mean_ms":142309.20833333334,"min_ms":60384,"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":132,"output_max":38968,"output_mean":12919.796875,"output_min":3846,"run_count":64},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":50,"output_max":38968,"output_mean":14388.125,"output_min":4776,"run_count":24},"medium":{"attempt_count":54,"output_max":32806,"output_mean":14801.708333333334,"output_min":5674,"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":49.75341940249558,"highest":48.905709680771956,"medium":58.330562486741115,"none":42.02398603997368},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":132,"finish_reasons":["stop"],"indexed_attempts":148,"output_token_observations":132,"reasoning_token_observations":104,"total_output_tokens":826867,"total_reasoning_output_tokens":58913,"total_visible_output_tokens":577790,"visible_token_observations":104},"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":"9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":21,"evaluated_cells":24,"failed_game_aliases":["GB2-02","GB2-06","GB2-07"],"first_pass_admitted":18,"first_pass_rate":0.75,"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":0.125,"model_code_failures":3,"repaired_admitted":3,"repaired_rate":0.125},"baseline":{"admitted_plugins":15,"evaluated_cells":16,"failed_game_aliases":["GB2-04"],"first_pass_admitted":14,"first_pass_rate":0.875,"model_code_failure_rate":0.0625,"model_code_failures":1,"repaired_admitted":1,"repaired_rate":0.0625},"intensive":{"admitted_plugins":22,"evaluated_cells":24,"failed_game_aliases":["GB2-02","GB2-03"],"first_pass_admitted":20,"first_pass_rate":0.8333333333333334,"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":0.08333333333333333,"model_code_failures":2,"repaired_admitted":2,"repaired_rate":0.08333333333333333}},"id":"x-ai/grok-4.5","is_recent_addition":false,"last_measured_at":"2026-08-05T06:54:57Z","match_totals_all":{"draws":1171,"losses":1442,"wins":2710},"match_totals_tracks":{"highest":{"draws":325,"losses":579,"wins":1022},"medium":{"draws":455,"losses":491,"wins":1105},"none":{"draws":391,"losses":372,"wins":583}},"model_slug":"x-ai-grok-4-5","overall":{"max":88.85644622319035,"mean":48.54006988577404,"min":16.238936021776848},"per_game":{"GB2-01":65.44532137869037,"GB2-02":34.09734496097713,"GB2-03":37.6743793289876,"GB2-04":18.785677670777737,"GB2-05":53.69350786141744,"GB2-06":55.56087546422818,"GB2-07":57.021020326201075,"GB2-08":68.96755045489611},"per_game_all":{"GB2-01":59.78113679085369,"GB2-02":29.58549230089893,"GB2-03":33.350948328704085,"GB2-04":25.94927311462675,"GB2-05":58.24878431966797,"GB2-06":57.82735353196936,"GB2-07":60.12813640755248,"GB2-08":73.15623042569145},"per_game_match_totals_all":{"GB2-01":{"draws":205,"losses":200,"wins":481},"GB2-02":{"draws":292,"losses":56,"wins":74},"GB2-03":{"draws":244,"losses":190,"wins":130},"GB2-04":{"draws":381,"losses":105,"wins":72},"GB2-05":{"draws":0,"losses":233,"wins":443},"GB2-06":{"draws":44,"losses":267,"wins":362},"GB2-07":{"draws":0,"losses":228,"wins":392},"GB2-08":{"draws":5,"losses":163,"wins":756}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":57,"losses":76,"wins":223},"GB2-02":{"draws":68,"losses":23,"wins":37},"GB2-03":{"draws":45,"losses":27,"wins":32},"GB2-04":{"draws":143,"losses":63,"wins":30},"GB2-05":{"draws":0,"losses":79,"wins":103},"GB2-06":{"draws":11,"losses":112,"wins":143},"GB2-07":{"draws":0,"losses":113,"wins":163},"GB2-08":{"draws":1,"losses":86,"wins":291}},"medium":{"GB2-01":{"draws":25,"losses":80,"wins":177},"GB2-02":{"draws":100,"losses":20,"wins":34},"GB2-03":{"draws":130,"losses":77,"wins":75},"GB2-04":{"draws":179,"losses":35,"wins":32},"GB2-05":{"draws":0,"losses":89,"wins":229},"GB2-06":{"draws":20,"losses":76,"wins":121},"GB2-07":{"draws":0,"losses":71,"wins":133},"GB2-08":{"draws":1,"losses":43,"wins":304}},"none":{"GB2-01":{"draws":123,"losses":44,"wins":81},"GB2-02":{"draws":124,"losses":13,"wins":3},"GB2-03":{"draws":69,"losses":86,"wins":23},"GB2-04":{"draws":59,"losses":7,"wins":10},"GB2-05":{"draws":0,"losses":65,"wins":111},"GB2-06":{"draws":13,"losses":79,"wins":98},"GB2-07":{"draws":0,"losses":44,"wins":96},"GB2-08":{"draws":3,"losses":34,"wins":161}}},"per_game_raw_elo_all":{"GB2-01":1671.2042094918588,"GB2-02":1537.6431015512135,"GB2-03":1470.6072081523944,"GB2-04":1489.9503395599288,"GB2-05":1683.420927815914,"GB2-06":1576.737324741529,"GB2-07":1671.3902948926104,"GB2-08":1833.0184898908913},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1732.2042579092843,"GB2-02":1559.377695628946,"GB2-03":1512.2301237737283,"GB2-04":1452.582785992217,"GB2-05":1634.7605219975048,"GB2-06":1556.7203640226057,"GB2-07":1636.509245658041,"GB2-08":1796.9439417067679},"medium":{"GB2-01":1715.840502074611,"GB2-02":1567.0189580640395,"GB2-03":1512.3805631851592,"GB2-04":1520.4132564019528,"GB2-05":1775.7285813884528,"GB2-06":1657.1298506300159,"GB2-07":1725.4022170469711,"GB2-08":1959.177771791579},"none":{"GB2-01":1565.567868491681,"GB2-02":1486.5326509606543,"GB2-03":1387.2109374982958,"GB2-04":1496.8549762856173,"GB2-05":1639.773680061784,"GB2-06":1516.361759571965,"GB2-07":1652.2594219728185,"GB2-08":1742.9337561743264}},"per_game_tracks":{"highest":{"GB2-01":65.44532137869037,"GB2-02":34.09734496097713,"GB2-03":37.6743793289876,"GB2-04":18.785677670777737,"GB2-05":53.69350786141744,"GB2-06":55.56087546422818,"GB2-07":57.021020326201075,"GB2-08":68.96755045489611},"medium":{"GB2-01":64.77698597319846,"GB2-02":38.420195919942806,"GB2-03":41.52750766968367,"GB2-04":33.28968021864736,"GB2-05":67.06621443748418,"GB2-06":66.59262070172484,"GB2-07":66.11484875005729,"GB2-08":88.85644622319035},"none":{"GB2-01":49.12110302067223,"GB2-02":16.238936021776848,"GB2-03":20.850957987441,"GB2-04":25.77246145445514,"GB2-05":53.986630660102286,"GB2-06":51.32856442995505,"GB2-07":57.248540146399066,"GB2-08":61.644694598987854}},"provider_color":"#9CA3AF","provider_company":"xAI","provider_key":"x-ai","provider_text_color":"#0b1120","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":47.853358704885466,"medium":56.41546571640121,"none":41.35138523603543},"reasoning_agg":{"highest":{"max":68.96755045489611,"mean":47.853358704885466,"min":18.785677670777737},"medium":{"max":88.85644622319035,"mean":56.41546571640121,"min":33.28968021864736},"none":{"max":61.644694598987854,"mean":41.35138523603543,"min":16.238936021776848}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"high"},"score_diagnostics":{"ceiling_score":88.85644622319035,"expected_score":52.54184965289799,"reasoning_variance":15.064080480365774,"reliability_score":76.30653843534749,"uncertainty_avg":23.693461564652505,"uncertainty_penalty":4.001779767123949},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":68.96755045489611,"expected_score":41.46850697605008,"reliability_score":71.97821298440476,"uncertainty_avg":28.021787015595244,"uncertainty_penalty":-6.384851728835386},"medium":{"ceiling_score":88.85644622319035,"expected_score":65.10306813460731,"reliability_score":91.45084055677262,"uncertainty_avg":8.549159443227383,"uncertainty_penalty":8.687602418206104},"none":{"ceiling_score":61.644694598987854,"expected_score":51.05397384803655,"reliability_score":65.4905617648651,"uncertainty_avg":34.5094382351349,"uncertainty_penalty":9.702588612001115}}},{"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":0.48907706250000005,"median":0.483741,"min":0.401826,"recorded_attempt_count":18,"run_count":8,"total":3.9126164999999995},"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":2.7900240000000003}},"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":0.41891503124999996,"median":0.4031475,"min":0.254883,"recorded_attempt_count":37,"run_count":16,"total":6.7026405},"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":41.41206956369944,"medium":52.18181048687467},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":37,"finish_reasons":["stop"],"indexed_attempts":37,"output_token_observations":37,"total_output_tokens":690711},"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":"stop","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":"9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999","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":"2026-08-05T06:54:47Z","match_totals_all":{"draws":459,"losses":469,"wins":612},"match_totals_tracks":{"highest":{"draws":182,"losses":250,"wins":234},"medium":{"draws":277,"losses":219,"wins":378}},"model_slug":"google-gemini-3-5-flash","overall":{"max":88.04000833669701,"mean":45.36004182416376,"min":12.88406623711618},"per_game":{"GB2-03":39.26992541010253,"GB2-04":17.855391019353213,"GB2-05":44.84698418707792,"GB2-06":77.86243893295662,"GB2-07":55.753611595590186,"GB2-08":12.88406623711618},"per_game_match_totals_all":{"GB2-01":{"draws":0,"losses":11,"wins":93},"GB2-02":{"draws":82,"losses":10,"wins":18},"GB2-03":{"draws":102,"losses":27,"wins":41},"GB2-04":{"draws":101,"losses":64,"wins":61},"GB2-05":{"draws":0,"losses":131,"wins":127},"GB2-06":{"draws":19,"losses":35,"wins":150},"GB2-07":{"draws":0,"losses":116,"wins":122},"GB2-08":{"draws":155,"losses":75,"wins":0}},"per_game_match_totals_tracks":{"highest":{"GB2-03":{"draws":65,"losses":12,"wins":13},"GB2-04":{"draws":35,"losses":46,"wins":31},"GB2-05":{"draws":0,"losses":67,"wins":57},"GB2-06":{"draws":8,"losses":19,"wins":75},"GB2-07":{"draws":0,"losses":58,"wins":58},"GB2-08":{"draws":74,"losses":48,"wins":0}},"medium":{"GB2-01":{"draws":0,"losses":11,"wins":93},"GB2-02":{"draws":82,"losses":10,"wins":18},"GB2-03":{"draws":37,"losses":15,"wins":28},"GB2-04":{"draws":66,"losses":18,"wins":30},"GB2-05":{"draws":0,"losses":64,"wins":70},"GB2-06":{"draws":11,"losses":16,"wins":75},"GB2-07":{"draws":0,"losses":58,"wins":64},"GB2-08":{"draws":81,"losses":27,"wins":0}}},"per_game_raw_elo_tracks":{"highest":{"GB2-03":1514.528494060152,"GB2-04":1441.5829391383131,"GB2-05":1519.2804128851371,"GB2-06":1792.51834753957,"GB2-07":1620.2275642237973,"GB2-08":1302.4253612380444},"medium":{"GB2-01":1953.4185734322302,"GB2-02":1527.4533953211321,"GB2-03":1596.2983594055843,"GB2-04":1549.1647476691362,"GB2-05":1570.0136054414809,"GB2-06":1868.8044414067544,"GB2-07":1532.4430409822883,"GB2-08":1330.54682570675}},"per_game_tracks":{"highest":{"GB2-03":39.26992541010253,"GB2-04":17.855391019353213,"GB2-05":44.84698418707792,"GB2-06":77.86243893295662,"GB2-07":55.753611595590186,"GB2-08":12.88406623711618},"medium":{"GB2-01":88.04000833669701,"GB2-02":32.3636679002474,"GB2-03":53.058616923197214,"GB2-04":39.9332689282377,"GB2-05":50.39508357270537,"GB2-06":86.64377257189392,"GB2-07":49.41140792271331,"GB2-08":17.608657739305404}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#f5f9ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":38.538273161452864,"medium":52.18181048687466},"reasoning_agg":{"highest":{"max":77.86243893295662,"mean":38.538273161452864,"min":12.88406623711618},"medium":{"max":88.04000833669701,"mean":52.18181048687466,"min":17.608657739305404}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Setting not tested"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":88.04000833669701,"reasoning_variance":13.643537325421796},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":77.86243893295662,"expected_score":31.446057013108184,"reliability_score":76.52025122530097,"uncertainty_avg":23.479748774699033,"uncertainty_penalty":-7.092216148344679},"medium":{"ceiling_score":88.04000833669701,"expected_score":58.24372705638711,"reliability_score":95.69688008684166,"uncertainty_avg":4.303119913158337,"uncertainty_penalty":6.061916569512448}}},{"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":12.137519999999999,"mean":8.1660015625,"median":8.18098,"min":4.7142525,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":11},"run_count":8,"token_priced_attempt_count":11,"total":65.3280125},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":11},"evidence_basis":"Standard list-price estimate","max":0.24673750000000003,"mean":0.16744,"median":0.15809499999999999,"min":0.108735,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":11},"run_count":8,"token_priced_attempt_count":11,"total":1.3395199999999998},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":10},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.1192425,"mean":0.0683559375,"median":0.06152125,"min":0.0542775,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":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":12.137519999999999,"mean":2.8005991666666663,"median":0.15809499999999999,"min":0.0542775,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":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":45.15466564373782,"highest":55.34391807732854,"medium":40.42457131635801,"none":39.69550753752692},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":32,"finish_reasons":["stop"],"indexed_attempts":56,"output_token_observations":32,"total_output_tokens":4442592},"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":"9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999","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":"2026-08-05T06:54:57Z","match_totals_all":{"draws":898,"losses":884,"wins":998},"match_totals_tracks":{"highest":{"draws":187,"losses":299,"wins":420},"medium":{"draws":348,"losses":289,"wins":307},"none":{"draws":363,"losses":296,"wins":271}},"model_slug":"gpt-5-6-terra","overall":{"max":74.75879788264669,"mean":44.77072465337242,"min":25.620832892368888},"per_game":{"GB2-01":40.24489520124794,"GB2-02":48.68530133471744,"GB2-03":50.36568330922522,"GB2-04":44.546679444120066,"GB2-05":61.05007234863776,"GB2-06":74.75879788264669,"GB2-07":73.16043333134834,"GB2-08":49.93948176668485},"per_game_all":{"GB2-01":45.425601481287146,"GB2-02":34.240934816070336,"GB2-03":43.17615016612808,"GB2-04":37.933049894487745,"GB2-05":55.446057424695255,"GB2-06":55.396440595503016,"GB2-07":52.13082949137206,"GB2-08":37.48826128035894},"per_game_match_totals_all":{"GB2-01":{"draws":107,"losses":139,"wins":122},"GB2-02":{"draws":259,"losses":38,"wins":27},"GB2-03":{"draws":110,"losses":79,"wins":79},"GB2-04":{"draws":228,"losses":42,"wins":66},"GB2-05":{"draws":0,"losses":148,"wins":220},"GB2-06":{"draws":16,"losses":157,"wins":179},"GB2-07":{"draws":0,"losses":167,"wins":215},"GB2-08":{"draws":178,"losses":114,"wins":90}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":35,"losses":58,"wins":33},"GB2-02":{"draws":66,"losses":20,"wins":22},"GB2-03":{"draws":16,"losses":23,"wins":37},"GB2-04":{"draws":48,"losses":24,"wins":42},"GB2-05":{"draws":0,"losses":47,"wins":73},"GB2-06":{"draws":0,"losses":45,"wins":69},"GB2-07":{"draws":0,"losses":36,"wins":84},"GB2-08":{"draws":22,"losses":46,"wins":60}},"medium":{"GB2-01":{"draws":37,"losses":35,"wins":46},"GB2-02":{"draws":90,"losses":9,"wins":1},"GB2-03":{"draws":52,"losses":25,"wins":15},"GB2-04":{"draws":90,"losses":11,"wins":15},"GB2-05":{"draws":0,"losses":55,"wins":77},"GB2-06":{"draws":14,"losses":49,"wins":57},"GB2-07":{"draws":0,"losses":64,"wins":72},"GB2-08":{"draws":65,"losses":41,"wins":24}},"none":{"GB2-01":{"draws":35,"losses":46,"wins":43},"GB2-02":{"draws":103,"losses":9,"wins":4},"GB2-03":{"draws":42,"losses":31,"wins":27},"GB2-04":{"draws":90,"losses":7,"wins":9},"GB2-05":{"draws":0,"losses":46,"wins":70},"GB2-06":{"draws":2,"losses":63,"wins":53},"GB2-07":{"draws":0,"losses":67,"wins":59},"GB2-08":{"draws":91,"losses":27,"wins":6}}},"per_game_raw_elo_all":{"GB2-01":1509.4340560893622,"GB2-02":1536.7583976913168,"GB2-03":1525.113781824334,"GB2-04":1538.338132642575,"GB2-05":1632.4787826520214,"GB2-06":1536.8881477941093,"GB2-07":1562.3404118708995,"GB2-08":1503.3181395203821},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1455.3441495353725,"GB2-02":1605.236191959549,"GB2-03":1578.6282681640967,"GB2-04":1574.9423799806716,"GB2-05":1700.3815440244537,"GB2-06":1741.4491229052383,"GB2-07":1800.148693292092,"GB2-08":1613.3119824922603},"medium":{"GB2-01":1497.9159537242554,"GB2-02":1497.2979775705355,"GB2-03":1498.0744357797557,"GB2-04":1513.6000534256289,"GB2-05":1597.5335585643102,"GB2-06":1496.508649868163,"GB2-07":1446.775336915899,"GB2-08":1474.332639053323},"none":{"GB2-01":1575.0420650084584,"GB2-02":1507.7410235438656,"GB2-03":1498.6386415291488,"GB2-04":1526.471964521424,"GB2-05":1599.5212453673003,"GB2-06":1372.7066706089265,"GB2-07":1440.0972054047072,"GB2-08":1422.3097970155627}},"per_game_tracks":{"highest":{"GB2-01":40.24489520124794,"GB2-02":48.68530133471744,"GB2-03":50.36568330922522,"GB2-04":44.546679444120066,"GB2-05":61.05007234863776,"GB2-06":74.75879788264669,"GB2-07":73.16043333134834,"GB2-08":49.93948176668485},"medium":{"GB2-01":44.24590085260889,"GB2-02":25.620832892368888,"GB2-03":39.420981492242916,"GB2-04":33.62557494988089,"GB2-05":52.65682323634443,"GB2-06":51.60384576894331,"GB2-07":41.97118928762754,"GB2-08":34.25142205084722},"none":{"GB2-01":51.78600839000461,"GB2-02":28.416670221124697,"GB2-03":39.7417856969161,"GB2-04":35.626895289462276,"GB2-05":52.63127668910358,"GB2-06":39.82667813491906,"GB2-07":41.26086585514032,"GB2-08":28.273880023544745}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":55.34391807732854,"medium":40.424571316358005,"none":38.54368456643071},"reasoning_agg":{"highest":{"max":74.75879788264669,"mean":55.34391807732854,"min":40.24489520124794},"medium":{"max":52.65682323634443,"mean":40.424571316358005,"min":25.620832892368888},"none":{"max":52.63127668910358,"mean":38.54368456643071,"min":28.273880023544745}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":74.75879788264669,"expected_score":43.934363634688424,"reasoning_variance":16.800233510897826,"reliability_score":97.16793074977666,"uncertainty_avg":2.832069250223342,"uncertainty_penalty":-0.8363610186839949},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":74.75879788264669,"expected_score":46.81680455277971,"reliability_score":96.57230687361428,"uncertainty_avg":3.427693126385715,"uncertainty_penalty":-8.527113524548831},"medium":{"ceiling_score":52.65682323634443,"expected_score":40.235486651841754,"reliability_score":97.4545086368651,"uncertainty_avg":2.5454913631348965,"uncertainty_penalty":-0.18908466451625117},"none":{"ceiling_score":52.63127668910358,"expected_score":44.75079969944382,"reliability_score":97.47697673885058,"uncertainty_avg":2.523023261149417,"uncertainty_penalty":6.2071151330131045}}},{"codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":12,"cell_count":8,"cost_basis_counts":{"provider_reported":53},"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.531673125,"mean":0.47737264687500003,"median":0.48302475,"min":0.3855675,"recorded_attempt_count":53,"run_count":16,"total":7.6379623500000005},"medium":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"provider_reported":44},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.3888165,"mean":0.26060548125,"median":0.24728879999999998,"min":0.17802225,"recorded_attempt_count":44,"run_count":16,"total":4.169687700000001},"none":{"admitted_cell_count":16,"cell_count":8,"cost_basis_counts":{"provider_reported":29},"evidence_basis":"Provider-reported","max":0.07826175,"mean":0.05584070625,"median":0.0541695,"min":0.0411735,"recorded_attempt_count":29,"run_count":16,"total":0.8934513000000001}},"codegen_cost_usd":{"admitted_cell_count":42,"cell_count":24,"cost_basis_counts":{"provider_reported":126},"evidence_basis":"Provider-reported","failed_cell_count":6,"max":0.531673125,"mean":0.264606278125,"median":0.24728879999999998,"min":0.0411735,"recorded_attempt_count":126,"run_count":48,"total":12.701101349999998},"codegen_latency_ms":{"attempt_count":122,"max_ms":348942,"mean_ms":136127.20833333334,"min_ms":17298,"run_count":48},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":49,"max_ms":348942,"mean_ms":238985.4375,"min_ms":149523,"run_count":16},"medium":{"attempt_count":44,"max_ms":261708,"mean_ms":136549.0,"min_ms":44747,"run_count":16},"none":{"attempt_count":29,"max_ms":50160,"mean_ms":32847.1875,"min_ms":17298,"run_count":16}},"codegen_output_tokens":{"attempt_count":126,"output_max":100087,"output_mean":32301.520833333332,"output_min":2060,"run_count":48},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":53,"output_max":100087,"output_mean":61701.5625,"output_min":36597,"run_count":16},"medium":{"attempt_count":44,"output_max":63652,"output_mean":30566.4375,"output_min":8874,"run_count":16},"none":{"attempt_count":29,"output_max":7962,"output_mean":4636.5625,"output_min":2060,"run_count":16}},"display_name":"Gemini 3.6 Flash","economics":{"all":47.23470153833624,"highest":48.607615644623934,"medium":50.410518444816546,"none":35.192117790614326},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":122,"finish_reasons":["length","stop"],"indexed_attempts":126,"output_token_observations":126,"reasoning_token_observations":82,"total_output_tokens":1550473,"total_reasoning_output_tokens":771353,"total_visible_output_tokens":207435,"visible_token_observations":82},"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":"9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999","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":["GB2-02","GB2-08"],"first_pass_admitted":14,"first_pass_rate":0.875,"model_code_failure_rate":0.125,"model_code_failures":2},"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":12,"evaluated_cells":16,"failed_game_aliases":["GB2-02","GB2-03","GB2-07"],"first_pass_admitted":8,"first_pass_rate":0.5,"model_code_failure_rate":0.25,"model_code_failures":4,"repaired_admitted":4,"repaired_rate":0.25}},"id":"google/gemini-3.6-flash","is_recent_addition":false,"last_measured_at":"2026-08-05T06:55:12Z","match_totals_all":{"draws":1125,"losses":1037,"wins":1530},"match_totals_tracks":{"highest":{"draws":182,"losses":321,"wins":532},"medium":{"draws":375,"losses":303,"wins":618},"none":{"draws":568,"losses":413,"wins":380}},"model_slug":"google-gemini-3-6-flash","overall":{"max":83.67694797963125,"mean":43.06068399835349,"min":15.356957668247802},"per_game":{"GB2-01":43.04679801633584,"GB2-03":48.426383488215265,"GB2-04":37.62630808796079,"GB2-05":60.18939037750328,"GB2-06":72.5401989690437,"GB2-07":43.412038961161755,"GB2-08":35.01219161214689},"per_game_all":{"GB2-01":48.43447606174252,"GB2-03":41.91496192810441,"GB2-04":29.192808142991684,"GB2-05":58.964074766759445,"GB2-06":64.94173045375614,"GB2-07":48.99265471234338,"GB2-08":38.20220470265613},"per_game_match_totals_all":{"GB2-01":{"draws":172,"losses":167,"wins":249},"GB2-02":{"draws":240,"losses":15,"wins":1},"GB2-03":{"draws":101,"losses":105,"wins":127},"GB2-04":{"draws":336,"losses":94,"wins":115},"GB2-05":{"draws":0,"losses":172,"wins":346},"GB2-06":{"draws":47,"losses":151,"wins":321},"GB2-07":{"draws":0,"losses":218,"wins":263},"GB2-08":{"draws":229,"losses":115,"wins":108}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":60,"losses":65,"wins":71},"GB2-03":{"draws":6,"losses":11,"wins":25},"GB2-04":{"draws":46,"losses":53,"wins":77},"GB2-05":{"draws":0,"losses":33,"wins":123},"GB2-06":{"draws":12,"losses":42,"wins":130},"GB2-07":{"draws":0,"losses":56,"wins":41},"GB2-08":{"draws":58,"losses":61,"wins":65}},"medium":{"GB2-01":{"draws":53,"losses":27,"wins":118},"GB2-02":{"draws":104,"losses":9,"wins":1},"GB2-03":{"draws":35,"losses":43,"wins":41},"GB2-04":{"draws":158,"losses":25,"wins":28},"GB2-05":{"draws":0,"losses":54,"wins":126},"GB2-06":{"draws":14,"losses":22,"wins":132},"GB2-07":{"draws":0,"losses":98,"wins":134},"GB2-08":{"draws":11,"losses":25,"wins":38}},"none":{"GB2-01":{"draws":59,"losses":75,"wins":60},"GB2-02":{"draws":136,"losses":6,"wins":0},"GB2-03":{"draws":60,"losses":51,"wins":61},"GB2-04":{"draws":132,"losses":16,"wins":10},"GB2-05":{"draws":0,"losses":85,"wins":97},"GB2-06":{"draws":21,"losses":87,"wins":59},"GB2-07":{"draws":0,"losses":64,"wins":88},"GB2-08":{"draws":160,"losses":29,"wins":5}}},"per_game_raw_elo_all":{"GB2-01":1556.7665539071343,"GB2-03":1540.3053383574304,"GB2-04":1506.889168802325,"GB2-05":1694.4078750871602,"GB2-06":1655.6652243649112,"GB2-07":1546.249689397913,"GB2-08":1530.9383338703446},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1508.1427938732331,"GB2-03":1606.495361338857,"GB2-04":1560.013755601416,"GB2-05":1717.2211615795206,"GB2-06":1740.0120087892494,"GB2-07":1488.2585103323468,"GB2-08":1512.638154159525},"medium":{"GB2-01":1744.3715807356245,"GB2-02":1457.63809611208,"GB2-03":1471.2197047485586,"GB2-04":1469.161344400508,"GB2-05":1811.3147558011215,"GB2-06":1841.5133446168375,"GB2-07":1563.7216538502953,"GB2-08":1651.8394288276704},"none":{"GB2-01":1417.785287112545,"GB2-02":1475.2464671154166,"GB2-03":1543.2009489848747,"GB2-04":1491.4924064050508,"GB2-05":1554.687707880838,"GB2-06":1385.4703196886467,"GB2-07":1586.7689040110965,"GB2-08":1428.3374186238389}},"per_game_tracks":{"highest":{"GB2-01":43.04679801633584,"GB2-03":48.426383488215265,"GB2-04":37.62630808796079,"GB2-05":60.18939037750328,"GB2-06":72.5401989690437,"GB2-07":43.412038961161755,"GB2-08":35.01219161214689},"medium":{"GB2-01":67.70990700393389,"GB2-02":17.78870942250549,"GB2-03":34.1367649976849,"GB2-04":25.126773678453485,"GB2-05":69.79149227763016,"GB2-06":83.67694797963125,"GB2-07":51.99731786762054,"GB2-08":53.05623433107263},"none":{"GB2-01":34.546723164957854,"GB2-02":15.356957668247802,"GB2-03":43.18173729841307,"GB2-04":24.82534266256079,"GB2-05":46.911341645144915,"GB2-06":38.608044412593436,"GB2-07":51.56860730824784,"GB2-08":26.53818816474888}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#f5f9ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":45.234483308254276,"medium":48.75545089619188,"none":35.192117790614326},"reasoning_agg":{"highest":{"max":72.5401989690437,"mean":45.234483308254276,"min":35.01219161214689},"medium":{"max":83.67694797963125,"mean":48.75545089619188,"min":17.78870942250549},"none":{"max":51.56860730824784,"mean":35.192117790614326,"min":15.356957668247802}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Minimal"},"reasoning_settings":{"balanced":"medium","baseline":"minimal","intensive":"high"},"score_diagnostics":{"ceiling_score":83.67694797963125,"expected_score":48.702415479108005,"reasoning_variance":13.563333105577556,"reliability_score":73.07800842022368,"uncertainty_avg":26.921991579776325,"uncertainty_penalty":5.641731480754515},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":72.5401989690437,"expected_score":41.9467851133356,"reliability_score":62.300117704555404,"uncertainty_avg":37.699882295444596,"uncertainty_penalty":-3.2876981949186757},"medium":{"ceiling_score":83.67694797963125,"expected_score":51.583497959696665,"reliability_score":90.5349472909155,"uncertainty_avg":9.465052709084507,"uncertainty_penalty":2.8280470635047834},"none":{"ceiling_score":51.56860730824784,"expected_score":42.31624992039235,"reliability_score":66.5094225878542,"uncertainty_avg":33.490577412145804,"uncertainty_penalty":7.124132129778026}}},{"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":0.19681749999999998,"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-2026-07-30":8},"run_count":8,"token_priced_attempt_count":8,"total":0.9739299999999999}},"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":0.19681749999999998,"min":0.09594,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":16,"boardgame-list-prices-2026-07-30":8},"run_count":24,"token_priced_attempt_count":24,"total":7.107714999999999},"codegen_latency_ms":{"attempt_count":24,"max_ms":319301,"mean_ms":98881.45833333333,"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":{"all":42.42327640773363,"highest":38.43255487282136,"medium":43.52801384089684,"none":45.30926050948271},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":24,"finish_reasons":["end_turn"],"indexed_attempts":24,"output_token_observations":24,"reasoning_token_observations":16,"requested_max_output_token_observations":16,"requested_max_output_tokens":[64000],"total_output_tokens":239955,"total_reasoning_output_tokens":171858,"total_visible_output_tokens":43839,"visible_token_observations":16},"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":"end_turn","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":"9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999","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":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"model_code_failure_rate":0.0,"model_code_failures":0},"intensive":{"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":"2026-08-05T05:11:15Z","match_totals_all":{"draws":1277,"losses":1309,"wins":1405},"match_totals_tracks":{"highest":{"draws":425,"losses":544,"wins":483},"medium":{"draws":523,"losses":502,"wins":566},"none":{"draws":329,"losses":263,"wins":356}},"model_slug":"claude-opus-4-5","overall":{"max":64.91944958274557,"mean":42.42327640773364,"min":17.12149396001877},"per_game":{"GB2-01":41.37674581224034,"GB2-02":17.12149396001877,"GB2-03":29.22692688715613,"GB2-04":18.618360953390088,"GB2-05":46.83576466893516,"GB2-06":54.40171912715226,"GB2-07":53.130070940092246,"GB2-08":46.74935663358592},"per_game_all":{"GB2-01":43.27087347856682,"GB2-02":22.938541260323095,"GB2-03":37.06838785443522,"GB2-04":30.622214951130577,"GB2-05":47.9023610300006,"GB2-06":51.442361169479454,"GB2-07":49.08135149721727,"GB2-08":57.06012002071608},"per_game_match_totals_all":{"GB2-01":{"draws":246,"losses":130,"wins":164},"GB2-02":{"draws":394,"losses":42,"wins":12},"GB2-03":{"draws":154,"losses":92,"wins":76},"GB2-04":{"draws":338,"losses":88,"wins":59},"GB2-05":{"draws":0,"losses":277,"wins":311},"GB2-06":{"draws":42,"losses":238,"wins":236},"GB2-07":{"draws":0,"losses":265,"wins":281},"GB2-08":{"draws":103,"losses":177,"wins":266}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":68,"losses":51,"wins":75},"GB2-02":{"draws":146,"losses":17,"wins":3},"GB2-03":{"draws":15,"losses":28,"wins":19},"GB2-04":{"draws":115,"losses":49,"wins":22},"GB2-05":{"draws":0,"losses":122,"wins":112},"GB2-06":{"draws":24,"losses":92,"wins":80},"GB2-07":{"draws":0,"losses":101,"wins":97},"GB2-08":{"draws":57,"losses":84,"wins":75}},"medium":{"GB2-01":{"draws":92,"losses":50,"wins":68},"GB2-02":{"draws":152,"losses":14,"wins":4},"GB2-03":{"draws":69,"losses":44,"wins":41},"GB2-04":{"draws":158,"losses":24,"wins":17},"GB2-05":{"draws":0,"losses":103,"wins":121},"GB2-06":{"draws":13,"losses":98,"wins":97},"GB2-07":{"draws":0,"losses":106,"wins":114},"GB2-08":{"draws":39,"losses":63,"wins":104}},"none":{"GB2-01":{"draws":86,"losses":29,"wins":21},"GB2-02":{"draws":96,"losses":11,"wins":5},"GB2-03":{"draws":70,"losses":20,"wins":16},"GB2-04":{"draws":65,"losses":15,"wins":20},"GB2-05":{"draws":0,"losses":52,"wins":78},"GB2-06":{"draws":5,"losses":48,"wins":59},"GB2-07":{"draws":0,"losses":58,"wins":70},"GB2-08":{"draws":7,"losses":30,"wins":87}}},"per_game_raw_elo_all":{"GB2-01":1492.2625597657482,"GB2-02":1489.3251701284835,"GB2-03":1491.752776187668,"GB2-04":1503.2711381586523,"GB2-05":1544.5423063091755,"GB2-06":1500.3988193681923,"GB2-07":1533.5407775132696,"GB2-08":1681.5206303298157},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1481.8432876524253,"GB2-02":1470.0542238659314,"GB2-03":1456.1284872075441,"GB2-04":1442.7829577904,"GB2-05":1536.89287568197,"GB2-06":1538.4845633830778,"GB2-07":1587.5380517863227,"GB2-08":1596.2791154741321},"medium":{"GB2-01":1520.028184936769,"GB2-02":1502.44121600246,"GB2-03":1492.8677330951837,"GB2-04":1495.1339801476183,"GB2-05":1537.0016338263567,"GB2-06":1520.3452760559187,"GB2-07":1516.0991425629509,"GB2-08":1701.9630242155704},"none":{"GB2-01":1474.9162067080504,"GB2-02":1495.4800705170592,"GB2-03":1526.2621082602757,"GB2-04":1571.8964765379387,"GB2-05":1559.7324094191993,"GB2-06":1442.3666186655798,"GB2-07":1496.9851381905353,"GB2-08":1746.3197512997453}},"per_game_tracks":{"highest":{"GB2-01":41.37674581224034,"GB2-02":17.12149396001877,"GB2-03":29.22692688715613,"GB2-04":18.618360953390088,"GB2-05":46.83576466893516,"GB2-06":54.40171912715226,"GB2-07":53.130070940092246,"GB2-08":46.74935663358592},"medium":{"GB2-01":46.17182865923943,"GB2-02":25.99852516396363,"GB2-03":38.11964378771493,"GB2-04":29.69438395580862,"GB2-05":47.37246936992358,"GB2-06":53.57943316939411,"GB2-07":47.776272775313714,"GB2-08":59.511553845816714},"none":{"GB2-01":42.2640459642207,"GB2-02":25.69560465698689,"GB2-03":43.85859288843461,"GB2-04":43.553899944193034,"GB2-05":49.49884905114305,"GB2-06":46.345931211891994,"GB2-07":46.33771077624585,"GB2-08":64.91944958274557}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":38.43255487282136,"medium":43.52801384089684,"none":45.30926050948271},"reasoning_agg":{"highest":{"max":54.40171912715226,"mean":38.43255487282136,"min":17.12149396001877},"medium":{"max":59.511553845816714,"mean":43.52801384089684,"min":25.99852516396363},"none":{"max":64.91944958274557,"mean":45.30926050948271,"min":25.69560465698689}},"reasoning_labels":{"highest":"High effort + 32,000 thinking tokens","medium":"Medium effort + 16,000 thinking tokens","none":"Thinking field omitted"},"reasoning_settings":{"balanced":"medium","intensive":"high"},"score_diagnostics":{"ceiling_score":64.91944958274557,"expected_score":43.22479784439908,"reasoning_variance":6.876705636661349,"reliability_score":90.11289442536379,"uncertainty_avg":9.88710557463621,"uncertainty_penalty":0.8015214366654391},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":54.40171912715226,"expected_score":28.073996308345077,"reliability_score":79.27138460013425,"uncertainty_avg":20.728615399865742,"uncertainty_penalty":-10.358558564476287},"medium":{"ceiling_score":59.511553845816714,"expected_score":43.771666243285566,"reliability_score":93.36788313438453,"uncertainty_avg":6.632116865615468,"uncertainty_penalty":0.24365240238872587},"none":{"ceiling_score":64.91944958274557,"expected_score":57.82873098156658,"reliability_score":97.69941554157258,"uncertainty_avg":2.3005844584274184,"uncertainty_penalty":12.519470472083867}}},{"codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":20,"cell_count":8,"cost_basis_counts":{"provider_reported":65},"evidence_basis":"Provider-reported","failed_cell_count":5,"max":1.1177706,"mean":0.8961934,"median":0.9197228499999999,"min":0.6673354000000001,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":65},"recorded_attempt_count":65,"run_count":26,"total":23.267240399999995},"medium":{"admitted_cell_count":16,"cell_count":8,"cost_basis_counts":{"provider_reported":32},"evidence_basis":"Provider-reported","max":0.3926418,"mean":0.31750829999999997,"median":0.32150055,"min":0.2298153,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":32},"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,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":17},"recorded_attempt_count":17,"run_count":16,"total":1.1192034}},"codegen_cost_usd":{"admitted_cell_count":52,"cell_count":24,"cost_basis_counts":{"provider_reported":114},"evidence_basis":"Provider-reported","failed_cell_count":5,"max":1.1177706,"mean":0.4278839708333333,"median":0.32150055,"min":0.0587988,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":114},"recorded_attempt_count":114,"run_count":58,"total":29.4665766},"codegen_latency_ms":{"attempt_count":114,"max_ms":3868120,"mean_ms":894043.724137931,"min_ms":64944,"run_count":58},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":65,"max_ms":3868120,"mean_ms":1591494.6923076923,"min_ms":367290,"run_count":26},"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":114,"output_max":138632,"output_mean":31620.08620689655,"output_min":2237,"run_count":58},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":65,"output_max":138632,"output_mean":57071.769230769234,"output_min":13522,"run_count":26},"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":43.13719016757199,"highest":48.43186177867785,"medium":37.13772805268788,"none":43.84198067135024},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":112,"finish_reasons":["length","stop"],"indexed_attempts":117,"output_token_observations":114,"reasoning_token_observations":98,"total_output_tokens":1833965,"total_reasoning_output_tokens":1155229,"total_visible_output_tokens":284415,"visible_token_observations":98},"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":"9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999","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":15,"first_pass_rate":0.9375,"model_code_failure_rate":0.0,"model_code_failures":0,"repaired_admitted":1,"repaired_rate":0.0625},"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":20,"evaluated_cells":25,"failed_game_aliases":["GB2-02","GB2-04","GB2-05","GB2-06","GB2-08"],"first_pass_admitted":16,"first_pass_rate":0.64,"infra_excluded_game_aliases":["GB2-08"],"infra_failures_excluded":1,"model_code_failure_rate":0.2,"model_code_failures":5,"repaired_admitted":4,"repaired_rate":0.16}},"id":"moonshotai/kimi-k3","is_recent_addition":false,"last_measured_at":"2026-08-05T06:55:02Z","match_totals_all":{"draws":1177,"losses":1128,"wins":1620},"match_totals_tracks":{"highest":{"draws":264,"losses":249,"wins":491},"medium":{"draws":436,"losses":438,"wins":419},"none":{"draws":477,"losses":441,"wins":710}},"model_slug":"moonshotai-kimi-k3","overall":{"max":76.9153537911332,"mean":42.26124520320811,"min":17.703162245681458},"per_game":{"GB2-01":55.1044008888968,"GB2-02":20.09827284833638,"GB2-03":43.919362734240536,"GB2-04":44.8242290880386,"GB2-05":49.71671953757412,"GB2-06":76.9153537911332,"GB2-07":54.395254355004845,"GB2-08":42.48130098619828},"per_game_all":{"GB2-01":47.32164280346732,"GB2-02":19.180005199763034,"GB2-03":44.281000479557726,"GB2-04":34.86031068908479,"GB2-05":49.403179525117004,"GB2-06":65.41523929786224,"GB2-07":41.68604166034438,"GB2-08":42.950101685379416},"per_game_match_totals_all":{"GB2-01":{"draws":205,"losses":153,"wins":210},"GB2-02":{"draws":388,"losses":40,"wins":24},"GB2-03":{"draws":116,"losses":89,"wins":175},"GB2-04":{"draws":286,"losses":61,"wins":115},"GB2-05":{"draws":0,"losses":220,"wins":312},"GB2-06":{"draws":35,"losses":157,"wins":299},"GB2-07":{"draws":0,"losses":305,"wins":281},"GB2-08":{"draws":147,"losses":103,"wins":204}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":36,"losses":55,"wins":105},"GB2-02":{"draws":134,"losses":12,"wins":6},"GB2-03":{"draws":26,"losses":19,"wins":45},"GB2-04":{"draws":61,"losses":17,"wins":54},"GB2-05":{"draws":0,"losses":43,"wins":53},"GB2-06":{"draws":5,"losses":8,"wins":71},"GB2-07":{"draws":0,"losses":79,"wins":123},"GB2-08":{"draws":2,"losses":16,"wins":34}},"medium":{"GB2-01":{"draws":54,"losses":41,"wins":35},"GB2-02":{"draws":86,"losses":12,"wins":12},"GB2-03":{"draws":56,"losses":26,"wins":44},"GB2-04":{"draws":110,"losses":19,"wins":25},"GB2-05":{"draws":0,"losses":97,"wins":111},"GB2-06":{"draws":20,"losses":81,"wins":100},"GB2-07":{"draws":0,"losses":113,"wins":53},"GB2-08":{"draws":110,"losses":49,"wins":39}},"none":{"GB2-01":{"draws":115,"losses":57,"wins":70},"GB2-02":{"draws":168,"losses":16,"wins":6},"GB2-03":{"draws":34,"losses":44,"wins":86},"GB2-04":{"draws":115,"losses":25,"wins":36},"GB2-05":{"draws":0,"losses":80,"wins":148},"GB2-06":{"draws":10,"losses":68,"wins":128},"GB2-07":{"draws":0,"losses":113,"wins":105},"GB2-08":{"draws":35,"losses":38,"wins":131}}},"per_game_raw_elo_all":{"GB2-01":1553.172654279063,"GB2-02":1495.9464809992508,"GB2-03":1564.7544057091388,"GB2-04":1545.6535989285549,"GB2-05":1579.3586546275098,"GB2-06":1664.1288335054933,"GB2-07":1467.9041588157042,"GB2-08":1581.3342988705383},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1630.8022570539633,"GB2-02":1497.0237227206553,"GB2-03":1573.4871568460653,"GB2-04":1599.8218153276666,"GB2-05":1584.696720232599,"GB2-06":1787.873868416896,"GB2-07":1609.3503322080414,"GB2-08":1589.1308178470354},"medium":{"GB2-01":1503.674483808534,"GB2-02":1510.3422066867968,"GB2-03":1538.186271761107,"GB2-04":1511.5521886227466,"GB2-05":1531.0851080733141,"GB2-06":1569.8482780083127,"GB2-07":1365.7115581527555,"GB2-08":1483.5107778326746},"none":{"GB2-01":1525.041221974691,"GB2-02":1480.4735135903006,"GB2-03":1582.589788520244,"GB2-04":1525.5867928352518,"GB2-05":1622.2941355766166,"GB2-06":1634.6643540912712,"GB2-07":1428.6505860863158,"GB2-08":1671.3613009319051}},"per_game_tracks":{"highest":{"GB2-01":55.1044008888968,"GB2-02":20.09827284833638,"GB2-03":43.919362734240536,"GB2-04":44.8242290880386,"GB2-05":49.71671953757412,"GB2-06":76.9153537911332,"GB2-07":54.395254355004845,"GB2-08":42.48130098619828},"medium":{"GB2-01":41.66078657358321,"GB2-02":19.738580505271273,"GB2-03":40.78232130318044,"GB2-04":28.207540924358696,"GB2-05":45.42181568717994,"GB2-06":56.503902002777224,"GB2-07":32.215324657126956,"GB2-08":32.57155276802534},"none":{"GB2-01":45.199740947921946,"GB2-02":17.703162245681458,"GB2-03":48.1413174012522,"GB2-04":31.549162054857096,"GB2-05":53.07100335059694,"GB2-06":62.82646209967631,"GB2-07":38.44754596890132,"GB2-08":53.79745130191461}},"provider_color":"#7C3AED","provider_company":"Moonshot","provider_key":"moonshotai","provider_text_color":"#faf5ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":45.8040268855862,"medium":37.13772805268788,"none":43.84198067135024},"reasoning_agg":{"highest":{"max":76.9153537911332,"mean":45.8040268855862,"min":20.09827284833638},"medium":{"max":56.503902002777224,"mean":37.13772805268788,"min":19.738580505271273},"none":{"max":62.82646209967631,"mean":43.84198067135024,"min":17.703162245681458}},"reasoning_labels":{"highest":"Max","medium":"High","none":"Low"},"reasoning_settings":{"balanced":"high","baseline":"low","intensive":"max"},"score_diagnostics":{"ceiling_score":76.9153537911332,"expected_score":47.02882427399723,"reasoning_variance":8.666298832898313,"reliability_score":65.12896470932745,"uncertainty_avg":34.871035290672545,"uncertainty_penalty":4.767579070789118},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":76.9153537911332,"expected_score":42.767620334507896,"reliability_score":62.31996946447718,"uncertainty_avg":37.68003053552282,"uncertainty_penalty":-3.0364065510783007},"medium":{"ceiling_score":56.503902002777224,"expected_score":41.00186388556228,"reliability_score":62.083741906023455,"uncertainty_avg":37.916258093976545,"uncertainty_penalty":3.864135832874396},"none":{"ceiling_score":62.82646209967631,"expected_score":57.31698860192155,"reliability_score":70.98318275748173,"uncertainty_avg":29.016817242518268,"uncertainty_penalty":13.475007930571309}}},{"codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":10,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":11},"evidence_basis":"Standard list-price estimate","max":0.4567,"mean":0.3802064166666667,"median":0.3908776666666667,"min":0.234622,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":2,"boardgame-list-prices-2026-07-30":9},"run_count":10,"token_priced_attempt_count":11,"total":3.8844619999999996},"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-2026-07-30":9},"run_count":8,"token_priced_attempt_count":9,"total":0.6244280000000001},"none":{"admitted_cell_count":9,"cell_count":8,"cost_basis_counts":{"estimated":1,"local_list_price_estimate":8,"provider_dashboard_reconciled":1},"evidence_basis":"Mixed: Provider-reported + Recorded attempt + Standard list-price estimate","max":0.07806,"mean":0.062955625,"median":0.061544,"min":0.049788,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":9},"recorded_attempt_count":2,"run_count":9,"token_priced_attempt_count":8,"total":0.57987}},"codegen_cost_usd":{"admitted_cell_count":26,"cell_count":24,"cost_basis_counts":{"estimated":1,"local_list_price_estimate":28,"provider_dashboard_reconciled":1},"evidence_basis":"Mixed: Provider-reported + Recorded attempt + Standard list-price estimate","failed_cell_count":1,"max":0.4567,"mean":0.17373851388888892,"median":0.0769495,"min":0.049788,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":2,"boardgame-list-prices-2026-07-30":27},"recorded_attempt_count":2,"run_count":27,"token_priced_attempt_count":28,"total":5.0887600000000015},"codegen_latency_ms":{"attempt_count":29,"max_ms":590864,"mean_ms":143367.25925925927,"min_ms":2034,"run_count":27},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":11,"max_ms":590864,"mean_ms":331567.4,"min_ms":185272,"run_count":10},"medium":{"attempt_count":9,"max_ms":95118,"mean_ms":42408.875,"min_ms":23645,"run_count":8},"none":{"attempt_count":9,"max_ms":31612,"mean_ms":23996.777777777777,"min_ms":2034,"run_count":9}},"codegen_output_tokens":{"attempt_count":30,"output_max":62762,"output_mean":16063.703703703704,"output_min":2627,"run_count":27},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":11,"output_max":62762,"output_mean":36044.4,"output_min":21120,"run_count":10},"medium":{"attempt_count":9,"output_max":10845,"output_mean":5045.625,"output_min":3136,"run_count":8},"none":{"attempt_count":10,"output_max":4594,"output_mean":3656.777777777778,"output_min":2627,"run_count":9}},"display_name":"Claude Sonnet 5","economics":{"all":41.65002908400444,"highest":44.37848240907164,"medium":39.446348181834175,"none":40.65157086620186},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":29,"finish_reasons":["end_turn","max_tokens"],"indexed_attempts":48,"output_token_observations":30,"reasoning_token_observations":3,"requested_max_output_token_observations":4,"requested_max_output_tokens":[128000],"total_output_tokens":433720,"total_reasoning_output_tokens":47819,"total_visible_output_tokens":6893,"visible_token_observations":3},"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":"9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999","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},"baseline":{"admitted_plugins":9,"evaluated_cells":9,"first_pass_admitted":9,"first_pass_rate":1.0,"model_code_failure_rate":0.0,"model_code_failures":0},"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":"2026-08-05T05:41:08Z","match_totals_all":{"draws":1111,"losses":950,"wins":985},"match_totals_tracks":{"highest":{"draws":350,"losses":411,"wins":359},"medium":{"draws":293,"losses":264,"wins":327},"none":{"draws":468,"losses":275,"wins":299}},"model_slug":"claude-sonnet-5","overall":{"max":62.31323923781224,"mean":41.06043574753804,"min":22.62500365197257},"per_game":{"GB2-01":62.31323923781224,"GB2-02":36.05496996375109,"GB2-03":39.24190944943468,"GB2-04":38.255041035684194,"GB2-05":51.723957204300376,"GB2-06":57.81303259089284,"GB2-07":40.61113499633033,"GB2-08":29.014574794367363},"per_game_all":{"GB2-01":52.17120856002075,"GB2-02":27.591758158447067,"GB2-04":34.95805023817247,"GB2-05":47.30908616570782,"GB2-06":53.60029566172539,"GB2-07":48.46969017855364,"GB2-08":27.450114625403984},"per_game_match_totals_all":{"GB2-01":{"draws":143,"losses":151,"wins":196},"GB2-02":{"draws":266,"losses":30,"wins":22},"GB2-03":{"draws":142,"losses":130,"wins":100},"GB2-04":{"draws":237,"losses":40,"wins":57},"GB2-05":{"draws":0,"losses":169,"wins":209},"GB2-06":{"draws":18,"losses":160,"wins":180},"GB2-07":{"draws":0,"losses":189,"wins":197},"GB2-08":{"draws":305,"losses":81,"wins":24}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":25,"losses":44,"wins":63},"GB2-02":{"draws":72,"losses":15,"wins":17},"GB2-03":{"draws":101,"losses":98,"wins":75},"GB2-04":{"draws":70,"losses":17,"wins":21},"GB2-05":{"draws":0,"losses":65,"wins":61},"GB2-06":{"draws":11,"losses":50,"wins":55},"GB2-07":{"draws":0,"losses":73,"wins":55},"GB2-08":{"draws":71,"losses":49,"wins":12}},"medium":{"GB2-01":{"draws":12,"losses":52,"wins":60},"GB2-02":{"draws":91,"losses":4,"wins":1},"GB2-04":{"draws":81,"losses":14,"wins":25},"GB2-05":{"draws":0,"losses":49,"wins":79},"GB2-06":{"draws":4,"losses":63,"wins":71},"GB2-07":{"draws":0,"losses":56,"wins":82},"GB2-08":{"draws":105,"losses":26,"wins":9}},"none":{"GB2-01":{"draws":106,"losses":55,"wins":73},"GB2-02":{"draws":103,"losses":11,"wins":4},"GB2-03":{"draws":41,"losses":32,"wins":25},"GB2-04":{"draws":86,"losses":9,"wins":11},"GB2-05":{"draws":0,"losses":55,"wins":69},"GB2-06":{"draws":3,"losses":47,"wins":54},"GB2-07":{"draws":0,"losses":60,"wins":60},"GB2-08":{"draws":129,"losses":6,"wins":3}}},"per_game_raw_elo_all":{"GB2-01":1579.1337484544645,"GB2-02":1505.6199089288027,"GB2-04":1521.847353198451,"GB2-05":1533.886213869089,"GB2-06":1517.8312042726754,"GB2-07":1520.942464241527,"GB2-08":1413.3485486491102},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1682.8738949315364,"GB2-02":1546.0360257430739,"GB2-03":1497.5177561237024,"GB2-04":1540.800435260969,"GB2-05":1587.0990394515595,"GB2-06":1562.556641341538,"GB2-07":1432.5051547512048,"GB2-08":1427.7661257245363},"medium":{"GB2-01":1509.3045165513727,"GB2-02":1483.89697802721,"GB2-04":1502.14488539432,"GB2-05":1592.574318717706,"GB2-06":1424.3657683124545,"GB2-07":1544.2909691339737,"GB2-08":1422.5477969238084},"none":{"GB2-01":1545.222833880484,"GB2-02":1486.926723016124,"GB2-03":1518.1113435198147,"GB2-04":1522.5967389400641,"GB2-05":1421.9852834380013,"GB2-06":1566.5712031640337,"GB2-07":1586.0312688394026,"GB2-08":1389.731723298986}},"per_game_tracks":{"highest":{"GB2-01":62.31323923781224,"GB2-02":36.05496996375109,"GB2-03":39.24190944943468,"GB2-04":38.255041035684194,"GB2-05":51.723957204300376,"GB2-06":57.81303259089284,"GB2-07":40.61113499633033,"GB2-08":29.014574794367363},"medium":{"GB2-01":45.4326698055027,"GB2-02":22.62500365197257,"GB2-04":31.685761656722633,"GB2-05":52.20111840015675,"GB2-06":44.98896150615873,"GB2-07":50.65363080364732,"GB2-08":28.53729144867848},"none":{"GB2-01":48.76771663674732,"GB2-02":24.09530085961754,"GB2-03":42.47234326149914,"GB2-04":34.93334802211057,"GB2-05":38.002182892666326,"GB2-06":57.99889288812461,"GB2-07":54.14430473568327,"GB2-08":24.798477633166108}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":44.378482409071644,"medium":38.1512539673406,"none":40.65157086620186},"reasoning_agg":{"highest":{"max":62.31323923781224,"mean":44.378482409071644,"min":29.014574794367363},"medium":{"max":52.20111840015675,"mean":38.1512539673406,"min":22.62500365197257},"none":{"max":57.99889288812461,"mean":40.65157086620186,"min":24.09530085961754}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Thinking disabled"},"reasoning_settings":{"baseline":"none"},"score_diagnostics":{"ceiling_score":62.31323923781224,"expected_score":38.876968720286314,"reasoning_variance":6.227228441731043,"reliability_score":98.08756823988958,"uncertainty_avg":1.9124317601104244,"uncertainty_penalty":-2.183467027251723},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":62.31323923781224,"expected_score":32.76497594913609,"reliability_score":97.31038236860752,"uncertainty_avg":2.689617631392484,"uncertainty_penalty":-11.613506459935557},"medium":{"ceiling_score":52.20111840015675,"expected_score":39.71789810895979,"reliability_score":98.5763202032138,"uncertainty_avg":1.4236797967861998,"uncertainty_penalty":1.5666441416191859},"none":{"ceiling_score":57.99889288812461,"expected_score":45.352766548192875,"reliability_score":96.98181323748717,"uncertainty_avg":3.018186762512821,"uncertainty_penalty":4.701195681991017}}},{"codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":20,"cell_count":8,"cost_basis_counts":{"exact_cumulative_delta":1,"provider_reported":64},"evidence_basis":"Provider-reported","failed_cell_count":7,"max":0.25823185295,"mean":0.20846239076375003,"median":0.20662718916666667,"min":0.13654539825,"recorded_attempt_count":65,"run_count":29,"total":5.97530434986}},"codegen_cost_usd":{"admitted_cell_count":20,"cell_count":8,"cost_basis_counts":{"exact_cumulative_delta":1,"provider_reported":64},"evidence_basis":"Provider-reported","failed_cell_count":7,"max":0.25823185295,"mean":0.20846239076375003,"median":0.20662718916666667,"min":0.13654539825,"recorded_attempt_count":65,"run_count":29,"total":5.97530434986},"codegen_latency_ms":{"attempt_count":64,"max_ms":3869582,"mean_ms":1364159.1724137932,"min_ms":364048,"run_count":29},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":64,"max_ms":3869582,"mean_ms":1364159.1724137932,"min_ms":364048,"run_count":29}},"codegen_output_tokens":{"attempt_count":64,"output_max":153344,"output_mean":65703.06896551725,"output_min":27968,"run_count":29},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":64,"output_max":153344,"output_mean":65703.06896551725,"output_min":27968,"run_count":29}},"display_name":"GLM-5.2","economics":{"all":41.17263919801496,"highest":42.31385173430746,"medium":42.74392751708084,"none":38.46013834265657},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":64,"finish_reasons":["error","length","stop","unknown"],"indexed_attempts":67,"output_token_observations":64,"reasoning_token_observations":5,"total_output_tokens":1905389,"total_reasoning_output_tokens":94090,"total_visible_output_tokens":10550,"visible_token_observations":5},"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":"9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"intensive":{"admitted_plugins":20,"evaluated_cells":27,"failed_game_aliases":["GB2-01","GB2-03","GB2-04","GB2-06"],"first_pass_admitted":3,"first_pass_rate":0.1111111111111111,"infra_excluded_game_aliases":["GB2-03","GB2-06"],"infra_failures_excluded":2,"model_code_failure_rate":0.25925925925925924,"model_code_failures":7,"repaired_admitted":17,"repaired_rate":0.6296296296296297}},"id":"z-ai/glm-5.2","is_recent_addition":false,"last_measured_at":"2026-08-05T05:05:01Z","match_totals_all":{"draws":2054,"losses":2147,"wins":2061},"match_totals_tracks":{"highest":{"draws":713,"losses":790,"wins":684},"medium":{"draws":584,"losses":411,"wins":502},"none":{"draws":757,"losses":946,"wins":875}},"model_slug":"z-ai-glm-5-2","overall":{"max":78.66120174874919,"mean":40.153146573452666,"min":16.341761309376864},"per_game":{"GB2-01":42.20358864197766,"GB2-02":20.17228110668475,"GB2-03":35.09417723351375,"GB2-04":25.496322085294256,"GB2-05":49.992442092413626,"GB2-06":76.82222311841032,"GB2-07":53.01864952960553,"GB2-08":35.71113006655985},"per_game_all":{"GB2-01":39.70680186940228,"GB2-02":18.12019167643534,"GB2-03":34.290390545125724,"GB2-04":27.893634400189125,"GB2-05":47.54790676793706,"GB2-06":66.87428510856758,"GB2-07":57.65220622920751,"GB2-08":37.295696987255084},"per_game_match_totals_all":{"GB2-01":{"draws":287,"losses":295,"wins":268},"GB2-02":{"draws":560,"losses":71,"wins":24},"GB2-03":{"draws":194,"losses":138,"wins":94},"GB2-04":{"draws":483,"losses":151,"wins":106},"GB2-05":{"draws":0,"losses":515,"wins":487},"GB2-06":{"draws":54,"losses":280,"wins":312},"GB2-07":{"draws":0,"losses":436,"wins":526},"GB2-08":{"draws":476,"losses":261,"wins":244}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":128,"losses":74,"wins":46},"GB2-02":{"draws":246,"losses":50,"wins":17},"GB2-03":{"draws":57,"losses":58,"wins":39},"GB2-04":{"draws":138,"losses":54,"wins":28},"GB2-05":{"draws":0,"losses":204,"wins":190},"GB2-06":{"draws":7,"losses":25,"wins":72},"GB2-07":{"draws":0,"losses":183,"wins":195},"GB2-08":{"draws":137,"losses":142,"wins":97}},"medium":{"GB2-01":{"draws":98,"losses":43,"wins":65},"GB2-02":{"draws":83,"losses":3,"wins":0},"GB2-03":{"draws":50,"losses":12,"wins":6},"GB2-04":{"draws":82,"losses":52,"wins":36},"GB2-05":{"draws":0,"losses":105,"wins":93},"GB2-06":{"draws":22,"losses":49,"wins":107},"GB2-07":{"draws":0,"losses":107,"wins":181},"GB2-08":{"draws":249,"losses":40,"wins":14}},"none":{"GB2-01":{"draws":61,"losses":178,"wins":157},"GB2-02":{"draws":231,"losses":18,"wins":7},"GB2-03":{"draws":87,"losses":68,"wins":49},"GB2-04":{"draws":263,"losses":45,"wins":42},"GB2-05":{"draws":0,"losses":206,"wins":204},"GB2-06":{"draws":25,"losses":206,"wins":133},"GB2-07":{"draws":0,"losses":146,"wins":150},"GB2-08":{"draws":90,"losses":79,"wins":133}}},"per_game_raw_elo_all":{"GB2-01":1452.6654552077416,"GB2-02":1463.5679383776087,"GB2-03":1471.998883534159,"GB2-04":1485.8223505386159,"GB2-05":1539.320434536424,"GB2-06":1662.0342073311538,"GB2-07":1627.8989060445274,"GB2-08":1504.6002826011834},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1475.924403802806,"GB2-02":1470.6823474356468,"GB2-03":1483.742396565601,"GB2-04":1469.168428759483,"GB2-05":1565.5375887832508,"GB2-06":1764.9290441113433,"GB2-07":1572.489463921882,"GB2-08":1487.8881549864773},"medium":{"GB2-01":1434.431436730129,"GB2-02":1456.35753048828,"GB2-03":1472.620482045245,"GB2-04":1489.2138469305178,"GB2-05":1599.0007086934363,"GB2-06":1787.4376165902647,"GB2-07":1720.1848392389459,"GB2-08":1424.623772094612},"none":{"GB2-01":1447.6405250902899,"GB2-02":1463.6639372088994,"GB2-03":1459.6337719916312,"GB2-04":1499.0847759258468,"GB2-05":1453.4230061325848,"GB2-06":1433.7359612918535,"GB2-07":1591.0224149727546,"GB2-08":1601.288920722461}},"per_game_tracks":{"highest":{"GB2-01":42.20358864197766,"GB2-02":20.17228110668475,"GB2-03":35.09417723351375,"GB2-04":25.496322085294256,"GB2-05":49.992442092413626,"GB2-06":76.82222311841032,"GB2-07":53.01864952960553,"GB2-08":35.71113006655985},"medium":{"GB2-01":37.852645783461874,"GB2-02":16.341761309376864,"GB2-03":34.82102759332112,"GB2-04":28.156444808513356,"GB2-05":52.33642397618402,"GB2-06":78.66120174874919,"GB2-07":65.68010929815331,"GB2-08":28.101805618887024},"none":{"GB2-01":39.064171182767296,"GB2-02":17.84653261324441,"GB2-03":32.95596680854231,"GB2-04":30.02813630675977,"GB2-05":40.31485423521351,"GB2-06":45.139430458543245,"GB2-07":54.257859859863686,"GB2-08":48.07415527631838}},"provider_color":"#2563EB","provider_company":"Zhipu","provider_key":"z-ai","provider_text_color":"#f8fbff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":39.2553738606206,"medium":42.74392751708085,"none":38.46013834265657},"reasoning_agg":{"highest":{"max":76.82222311841032,"mean":39.2553738606206,"min":20.17228110668475},"medium":{"max":78.66120174874919,"mean":42.74392751708085,"min":16.341761309376864},"none":{"max":54.257859859863686,"mean":38.46013834265657,"min":17.84653261324441}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":78.66120174874919,"expected_score":39.06716913324153,"reasoning_variance":4.283789174424278,"reliability_score":92.38574992961249,"uncertainty_avg":7.614250070387509,"uncertainty_penalty":-1.0859774402111384},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":76.82222311841032,"expected_score":31.51229867718155,"reliability_score":94.43511998705527,"uncertainty_avg":5.5648800129447284,"uncertainty_penalty":-7.74307518343905},"medium":{"ceiling_score":78.66120174874919,"expected_score":42.36483676709789,"reliability_score":91.25876844745294,"uncertainty_avg":8.74123155254706,"uncertainty_penalty":-0.3790907499829572},"none":{"ceiling_score":54.257859859863686,"expected_score":43.32437195544513,"reliability_score":91.46336135432927,"uncertainty_avg":8.53663864567074,"uncertainty_penalty":4.86423361278856}}},{"codegen_cost_by_reasoning":{"none":{"admitted_cell_count":1,"cell_count":1,"cost_basis_counts":{"estimated":1,"local_standard_estimate":1},"evidence_basis":"Mixed: Recorded attempt + Standard list-price estimate","max":0.0023425,"mean":0.0023425,"median":0.0023425,"min":0.0023425,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":1,"boardgame-list-prices-2026-07-30":1},"recorded_attempt_count":1,"run_count":1,"token_priced_attempt_count":1,"total":0.0023425}},"codegen_cost_usd":{"admitted_cell_count":1,"cell_count":1,"cost_basis_counts":{"estimated":1,"local_standard_estimate":1},"evidence_basis":"Mixed: Recorded attempt + Standard list-price estimate","max":0.0023425,"mean":0.0023425,"median":0.0023425,"min":0.0023425,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":1,"boardgame-list-prices-2026-07-30":1},"recorded_attempt_count":1,"run_count":1,"token_priced_attempt_count":1,"total":0.0023425},"codegen_latency_ms":{"attempt_count":1,"max_ms":3362,"mean_ms":3362.0,"min_ms":3362,"run_count":1},"codegen_latency_ms_by_reasoning":{"none":{"attempt_count":1,"max_ms":3362,"mean_ms":3362.0,"min_ms":3362,"run_count":1}},"codegen_output_tokens":{"attempt_count":2,"output_max":2006,"output_mean":2006.0,"output_min":2006,"run_count":1},"codegen_output_tokens_by_reasoning":{"none":{"attempt_count":2,"output_max":2006,"output_mean":2006.0,"output_min":2006,"run_count":1}},"display_name":"GPT 4.1 Nano","economics":{"none":39.478292990152276},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":1,"finish_reasons":["stop"],"indexed_attempts":2,"output_token_observations":2,"reasoning_token_observations":1,"total_output_tokens":2006,"total_visible_output_tokens":64,"visible_token_observations":1},"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-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":"9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"baseline":{"admitted_plugins":1,"evaluated_cells":1,"first_pass_admitted":1,"first_pass_rate":1.0,"model_code_failure_rate":0.0,"model_code_failures":0}},"id":"gpt-4.1-nano","is_recent_addition":false,"last_measured_at":"2026-08-05T05:02:05Z","match_totals_all":{"draws":30,"losses":32,"wins":36},"match_totals_tracks":{"none":{"draws":30,"losses":32,"wins":36}},"model_slug":"gpt-4-1-nano","overall":{"max":39.478292990152276,"mean":39.478292990152276,"min":39.478292990152276},"per_game_match_totals_all":{"GB2-01":{"draws":30,"losses":32,"wins":36}},"per_game_match_totals_tracks":{"none":{"GB2-01":{"draws":30,"losses":32,"wins":36}}},"per_game_raw_elo_tracks":{"none":{"GB2-01":1452.1194224909668}},"per_game_tracks":{"none":{"GB2-01":39.478292990152276}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"none":39.478292990152276},"reasoning_agg":{"none":{"max":39.478292990152276,"mean":39.478292990152276,"min":39.478292990152276}},"reasoning_labels":{"highest":"Setting not tested","medium":"Setting not tested","none":"Reasoning field omitted"},"reasoning_settings":{"baseline":"none"},"score_diagnostics":{"ceiling_score":39.478292990152276},"score_diagnostics_by_reasoning":{"none":{"ceiling_score":39.478292990152276,"expected_score":31.167753333868617,"reliability_score":93.4981092370394,"uncertainty_avg":6.501890762960602,"uncertainty_penalty":-8.310539656283659}}},{"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":0.015562441375000001,"median":0.013116718500000001,"min":0.005612805,"recorded_attempt_count":12,"run_count":8,"total":0.12449953100000001}},"codegen_cost_usd":{"admitted_cell_count":13,"cell_count":16,"cost_basis_counts":{"provider_reported":28},"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.10909930499999998,"mean":0.049205097625000006,"median":0.034298199,"min":0.005612805,"recorded_attempt_count":28,"run_count":16,"total":0.7872815620000001},"codegen_latency_ms":{"attempt_count":28,"max_ms":1214284,"mean_ms":465438.125,"min_ms":42870,"run_count":16},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":16,"max_ms":1214284,"mean_ms":845698.625,"min_ms":162422,"run_count":8},"none":{"attempt_count":12,"max_ms":162843,"mean_ms":85177.625,"min_ms":42870,"run_count":8}},"codegen_output_tokens":{"attempt_count":28,"output_max":80681,"output_mean":29459.75,"output_min":2689,"run_count":16},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":16,"output_max":80681,"output_mean":54027.75,"output_min":8210,"run_count":8},"none":{"attempt_count":12,"output_max":7681,"output_mean":4891.75,"output_min":2689,"run_count":8}},"display_name":"DeepSeek V4 Pro","economics":{"highest":43.9705511062461,"none":38.82358458571298},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":28,"finish_reasons":["stop"],"indexed_attempts":28,"output_token_observations":28,"total_output_tokens":471356},"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":"stop","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":"9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999","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":"2026-08-05T05:11:41Z","match_totals_all":{"draws":466,"losses":570,"wins":542},"match_totals_tracks":{"highest":{"draws":177,"losses":304,"wins":267},"none":{"draws":289,"losses":266,"wins":275}},"model_slug":"deepseek-deepseek-v4-pro","overall":{"max":76.14344213568862,"mean":39.234072665806686,"min":17.2055412078098},"per_game":{"GB2-01":38.748929094306256,"GB2-04":25.042469828678968,"GB2-05":76.14344213568862,"GB2-06":42.05907181803922,"GB2-07":56.45100183671994,"GB2-08":25.37839192404362},"per_game_match_totals_all":{"GB2-01":{"draws":81,"losses":113,"wins":82},"GB2-02":{"draws":100,"losses":6,"wins":2},"GB2-03":{"draws":19,"losses":44,"wins":17},"GB2-04":{"draws":59,"losses":33,"wins":18},"GB2-05":{"draws":0,"losses":92,"wins":146},"GB2-06":{"draws":15,"losses":107,"wins":130},"GB2-07":{"draws":0,"losses":120,"wins":128},"GB2-08":{"draws":192,"losses":55,"wins":19}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":27,"losses":58,"wins":41},"GB2-04":{"draws":59,"losses":33,"wins":18},"GB2-05":{"draws":0,"losses":35,"wins":83},"GB2-06":{"draws":5,"losses":75,"wins":60},"GB2-07":{"draws":0,"losses":68,"wins":58},"GB2-08":{"draws":86,"losses":35,"wins":7}},"none":{"GB2-01":{"draws":54,"losses":55,"wins":41},"GB2-02":{"draws":100,"losses":6,"wins":2},"GB2-03":{"draws":19,"losses":44,"wins":17},"GB2-05":{"draws":0,"losses":57,"wins":63},"GB2-06":{"draws":10,"losses":32,"wins":70},"GB2-07":{"draws":0,"losses":52,"wins":70},"GB2-08":{"draws":106,"losses":20,"wins":12}}},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1439.8654932136196,"GB2-04":1466.62788625461,"GB2-05":1882.615074493054,"GB2-06":1393.2494860259037,"GB2-07":1611.1347947383947,"GB2-08":1396.1496435571894},"none":{"GB2-01":1444.7795894298745,"GB2-02":1480.7598583404967,"GB2-03":1345.8681392042768,"GB2-05":1450.2207722244411,"GB2-06":1663.2988732348192,"GB2-07":1455.7320098290559,"GB2-08":1545.3284416661595}},"per_game_tracks":{"highest":{"GB2-01":38.748929094306256,"GB2-04":25.042469828678968,"GB2-05":76.14344213568862,"GB2-06":42.05907181803922,"GB2-07":56.45100183671994,"GB2-08":25.37839192404362},"none":{"GB2-01":39.50826721476022,"GB2-02":22.448726851866137,"GB2-03":17.2055412078098,"GB2-05":40.296018158068726,"GB2-06":67.31147896345796,"GB2-07":42.598572223588526,"GB2-08":42.39648748043947}},"provider_color":"#4C8BF5","provider_company":"DeepSeek","provider_key":"deepseek","provider_text_color":"#f6f9ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":40.919208516869816,"none":37.548936814743556},"reasoning_agg":{"highest":{"max":76.14344213568862,"mean":40.919208516869816,"min":25.042469828678968},"none":{"max":67.31147896345796,"mean":37.548936814743556,"min":17.2055412078098}},"reasoning_labels":{"highest":"XHigh","medium":"Setting not tested","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":76.14344213568862,"reasoning_variance":3.37027170212626},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":76.14344213568862,"expected_score":32.31233544234612,"reliability_score":98.78316318384532,"uncertainty_avg":1.2168368161546834,"uncertainty_penalty":-8.606873074523698},"none":{"ceiling_score":67.31147896345796,"expected_score":36.97871028375552,"reliability_score":96.81843708232714,"uncertainty_avg":3.181562917672865,"uncertainty_penalty":-0.5702265309880374}}},{"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":0.027613287599999998,"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":43.065196543476866,"none":38.62762612577165},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":27,"finish_reasons":["error","length","stop"],"indexed_attempts":27,"output_token_observations":27,"total_output_tokens":643548},"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":"mixed","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":"9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999","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":"2026-08-05T05:17:07Z","match_totals_all":{"draws":350,"losses":562,"wins":546},"match_totals_tracks":{"medium":{"draws":175,"losses":308,"wins":289},"none":{"draws":175,"losses":254,"wins":257}},"model_slug":"xiaomi-mimo-v2-5-pro","overall":{"max":66.15885507474644,"mean":38.62200379032396,"min":19.35129652009281},"per_game_match_totals_all":{"GB2-01":{"draws":62,"losses":108,"wins":106},"GB2-02":{"draws":82,"losses":8,"wins":6},"GB2-03":{"draws":51,"losses":18,"wins":23},"GB2-04":{"draws":63,"losses":24,"wins":27},"GB2-05":{"draws":0,"losses":144,"wins":106},"GB2-06":{"draws":3,"losses":117,"wins":136},"GB2-07":{"draws":0,"losses":112,"wins":140},"GB2-08":{"draws":89,"losses":31,"wins":2}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":21,"losses":50,"wins":67},"GB2-04":{"draws":63,"losses":24,"wins":27},"GB2-05":{"draws":0,"losses":80,"wins":50},"GB2-06":{"draws":2,"losses":58,"wins":74},"GB2-07":{"draws":0,"losses":65,"wins":69},"GB2-08":{"draws":89,"losses":31,"wins":2}},"none":{"GB2-01":{"draws":41,"losses":58,"wins":39},"GB2-02":{"draws":82,"losses":8,"wins":6},"GB2-03":{"draws":51,"losses":18,"wins":23},"GB2-05":{"draws":0,"losses":64,"wins":56},"GB2-06":{"draws":1,"losses":59,"wins":62},"GB2-07":{"draws":0,"losses":47,"wins":71}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1643.003852096852,"GB2-04":1564.629970640442,"GB2-05":1342.0855540317798,"GB2-06":1662.1296966917387,"GB2-07":1490.2719353363145,"GB2-08":1359.055533810906},"none":{"GB2-01":1425.8116737375058,"GB2-02":1497.230475769869,"GB2-03":1469.459954262159,"GB2-05":1414.595814890767,"GB2-06":1416.139471593564,"GB2-07":1563.5214241665924}},"per_game_tracks":{"medium":{"GB2-01":58.53306464293001,"GB2-04":39.7928749336898,"GB2-05":30.195666678862878,"GB2-06":66.15885507474644,"GB2-07":44.359421410539206,"GB2-08":19.35129652009281},"none":{"GB2-01":37.54208643626219,"GB2-02":25.43537970074668,"GB2-03":35.324362595440974,"GB2-05":37.34046965332213,"GB2-06":44.005316505702595,"GB2-07":52.11814186315531}},"provider_color":"#FF6900","provider_company":"Xiaomi","provider_key":"xiaomi","provider_text_color":"#fff7f1","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":40.07668116154651,"none":37.167326419101414},"reasoning_agg":{"medium":{"max":66.15885507474644,"mean":40.07668116154651,"min":19.35129652009281},"none":{"max":52.11814186315531,"mean":37.167326419101414,"min":25.43537970074668}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":66.15885507474644,"reasoning_variance":2.909354742445096},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":66.15885507474644,"expected_score":50.300669981537936,"reliability_score":83.47429745843145,"uncertainty_avg":16.525702541568545,"uncertainty_penalty":10.223988819991426},"none":{"ceiling_score":52.11814186315531,"expected_score":41.4914546393511,"reliability_score":96.6270258279117,"uncertainty_avg":3.372974172088309,"uncertainty_penalty":4.324128220249683}}},{"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":0.45464499999999997,"mean":0.28201406249999994,"median":0.2695775,"min":0.17401125,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":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":0.21477374999999999,"mean":0.17756265624999998,"median":0.17285124999999998,"min":0.1418975,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":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":0.45464499999999997,"mean":0.22978835937499997,"median":0.1997375,"min":0.1418975,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":19},"run_count":16,"token_priced_attempt_count":19,"total":3.6766137500000005},"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":38.58016390752029,"medium":39.611716088428516},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":19,"finish_reasons":["stop"],"indexed_attempts":19,"output_token_observations":19,"total_output_tokens":349054},"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":"stop","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":"9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999","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":"2026-08-05T05:19:06Z","match_totals_all":{"draws":523,"losses":627,"wins":580},"match_totals_tracks":{"highest":{"draws":303,"losses":324,"wins":309},"medium":{"draws":220,"losses":303,"wins":271}},"model_slug":"gpt-5","overall":{"max":66.50580979104048,"mean":38.44567822854766,"min":16.793318043756123},"per_game":{"GB2-01":41.55026889308681,"GB2-02":16.793318043756123,"GB2-03":28.72176486319264,"GB2-04":22.115823492649717,"GB2-05":59.509667167131056,"GB2-06":66.50580979104048,"GB2-07":49.82745014205055,"GB2-08":23.61720886725491},"per_game_match_totals_all":{"GB2-01":{"draws":36,"losses":124,"wins":88},"GB2-02":{"draws":79,"losses":17,"wins":4},"GB2-03":{"draws":77,"losses":54,"wins":31},"GB2-04":{"draws":159,"losses":45,"wins":32},"GB2-05":{"draws":0,"losses":110,"wins":140},"GB2-06":{"draws":18,"losses":92,"wins":122},"GB2-07":{"draws":0,"losses":110,"wins":136},"GB2-08":{"draws":154,"losses":75,"wins":27}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":13,"losses":65,"wins":58},"GB2-02":{"draws":79,"losses":17,"wins":4},"GB2-03":{"draws":31,"losses":32,"wins":19},"GB2-04":{"draws":85,"losses":22,"wins":11},"GB2-05":{"draws":0,"losses":48,"wins":76},"GB2-06":{"draws":10,"losses":39,"wins":61},"GB2-07":{"draws":0,"losses":60,"wins":62},"GB2-08":{"draws":85,"losses":41,"wins":18}},"medium":{"GB2-01":{"draws":23,"losses":59,"wins":30},"GB2-03":{"draws":46,"losses":22,"wins":12},"GB2-04":{"draws":74,"losses":23,"wins":21},"GB2-05":{"draws":0,"losses":62,"wins":64},"GB2-06":{"draws":8,"losses":53,"wins":61},"GB2-07":{"draws":0,"losses":50,"wins":74},"GB2-08":{"draws":69,"losses":34,"wins":9}}},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1481.5108403714787,"GB2-02":1471.6265901311735,"GB2-03":1444.2409871410878,"GB2-04":1463.9539606604203,"GB2-05":1695.9221727866338,"GB2-06":1670.792977708839,"GB2-07":1552.7262387953551,"GB2-08":1392.229001478985},"medium":{"GB2-01":1307.5635018079774,"GB2-03":1415.0451235991713,"GB2-04":1506.187494103844,"GB2-05":1652.4694531265427,"GB2-06":1547.9370321371216,"GB2-07":1628.4297641341607,"GB2-08":1354.8995387907771}},"per_game_tracks":{"highest":{"GB2-01":41.55026889308681,"GB2-02":16.793318043756123,"GB2-03":28.72176486319264,"GB2-04":22.115823492649717,"GB2-05":59.509667167131056,"GB2-06":66.50580979104048,"GB2-07":49.82745014205055,"GB2-08":23.61720886725491},"medium":{"GB2-01":25.756034767008668,"GB2-03":27.109328607264317,"GB2-04":32.354804347535634,"GB2-05":57.14727397018848,"GB2-06":56.51235426034554,"GB2-07":57.96187879269228,"GB2-08":20.440337873964644}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":38.58016390752029,"medium":38.31119254957503},"reasoning_agg":{"highest":{"max":66.50580979104048,"mean":38.58016390752029,"min":16.793318043756123},"medium":{"max":57.96187879269228,"mean":38.31119254957503,"min":20.440337873964644}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Setting not tested"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":66.50580979104048,"reasoning_variance":0.2689713579452544},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":66.50580979104048,"expected_score":28.884105111330218,"reliability_score":77.99880069978101,"uncertainty_avg":22.001199300218985,"uncertainty_penalty":-9.69605879619007},"medium":{"ceiling_score":57.96187879269228,"expected_score":38.692351041803114,"reliability_score":96.65925228578587,"uncertainty_avg":3.3407477142141344,"uncertainty_penalty":0.3811584922280815}}},{"codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":12,"cell_count":8,"cost_basis_counts":{"estimated":2,"local_standard_estimate":18},"evidence_basis":"Mixed: Recorded attempt + Standard list-price estimate","max":1.5164726249999998,"mean":1.0788743062500001,"median":0.9700117500000001,"min":0.8356068750000001,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":2,"boardgame-list-prices-2026-07-30":18},"recorded_attempt_count":2,"run_count":14,"token_priced_attempt_count":18,"total":15.220633649999998},"medium":{"admitted_cell_count":23,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":26},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.29749325000000004,"mean":0.24155631250000004,"median":0.24021375,"min":0.17873725,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":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-2026-07-30":29},"run_count":24,"token_priced_attempt_count":29,"total":0.4149345}},"codegen_cost_usd":{"admitted_cell_count":59,"cell_count":24,"cost_basis_counts":{"estimated":2,"local_standard_estimate":73},"evidence_basis":"Mixed: Recorded attempt + Standard list-price estimate","failed_cell_count":1,"max":1.5164726249999998,"mean":0.44590651875000004,"median":0.24021375,"min":0.01259225,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":2,"boardgame-list-prices-2026-07-30":73},"recorded_attempt_count":2,"run_count":62,"token_priced_attempt_count":73,"total":21.432919649999995},"codegen_latency_ms":{"attempt_count":73,"max_ms":2003150,"mean_ms":287490.3870967742,"min_ms":9399,"run_count":62},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":18,"max_ms":2003150,"mean_ms":954216.6428571428,"min_ms":660984,"run_count":14},"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":75,"output_max":440805,"output_mean":74039.24193548386,"output_min":1473,"run_count":62},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":20,"output_max":440805,"output_mean":233941.7142857143,"output_min":114521,"run_count":14},"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":37.76328306372786,"highest":46.73048991131135,"medium":39.16874370300505,"none":28.626949132145135},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":72,"finish_reasons":["incomplete","stop"],"indexed_attempts":79,"output_token_observations":75,"reasoning_token_observations":2,"total_output_tokens":4590433,"total_reasoning_output_tokens":255888,"visible_token_observations":2},"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":"9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999","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":0.20833333333333334},"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":"2026-08-05T06:55:18Z","match_totals_all":{"draws":2442,"losses":2495,"wins":2033},"match_totals_tracks":{"highest":{"draws":362,"losses":511,"wins":577},"medium":{"draws":947,"losses":963,"wins":844},"none":{"draws":1133,"losses":1021,"wins":612}},"model_slug":"gpt-5-4-mini","overall":{"max":72.91920929796846,"mean":38.03721344850252,"min":16.762689788970278},"per_game":{"GB2-01":56.34870578570014,"GB2-02":18.231928182356505,"GB2-04":29.555732530370754,"GB2-05":50.802629023107144,"GB2-06":59.82214388179885,"GB2-07":72.91920929796846,"GB2-08":39.43308067787763},"per_game_all":{"GB2-01":41.96977614350809,"GB2-02":20.720595899098985,"GB2-04":30.997900069691436,"GB2-05":40.56640022724385,"GB2-06":52.87179404638503,"GB2-07":45.605616344399,"GB2-08":31.61089871576867},"per_game_match_totals_all":{"GB2-01":{"draws":166,"losses":405,"wins":281},"GB2-02":{"draws":731,"losses":65,"wins":20},"GB2-03":{"draws":315,"losses":123,"wins":137},"GB2-04":{"draws":569,"losses":115,"wins":136},"GB2-05":{"draws":0,"losses":571,"wins":455},"GB2-06":{"draws":51,"losses":406,"wins":393},"GB2-07":{"draws":0,"losses":526,"wins":435},"GB2-08":{"draws":610,"losses":284,"wins":176}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":13,"losses":63,"wins":52},"GB2-02":{"draws":168,"losses":23,"wins":5},"GB2-04":{"draws":82,"losses":29,"wins":17},"GB2-05":{"draws":0,"losses":124,"wins":120},"GB2-06":{"draws":18,"losses":113,"wins":113},"GB2-07":{"draws":0,"losses":66,"wins":180},"GB2-08":{"draws":81,"losses":93,"wins":90}},"medium":{"GB2-01":{"draws":43,"losses":170,"wins":137},"GB2-02":{"draws":278,"losses":26,"wins":10},"GB2-03":{"draws":143,"losses":69,"wins":61},"GB2-04":{"draws":231,"losses":41,"wins":78},"GB2-05":{"draws":0,"losses":224,"wins":194},"GB2-06":{"draws":13,"losses":109,"wins":126},"GB2-07":{"draws":0,"losses":216,"wins":177},"GB2-08":{"draws":239,"losses":108,"wins":61}},"none":{"GB2-01":{"draws":110,"losses":172,"wins":92},"GB2-02":{"draws":285,"losses":16,"wins":5},"GB2-03":{"draws":172,"losses":54,"wins":76},"GB2-04":{"draws":256,"losses":45,"wins":41},"GB2-05":{"draws":0,"losses":223,"wins":141},"GB2-06":{"draws":20,"losses":184,"wins":154},"GB2-07":{"draws":0,"losses":244,"wins":78},"GB2-08":{"draws":290,"losses":83,"wins":25}}},"per_game_raw_elo_all":{"GB2-01":1473.6864838132342,"GB2-02":1473.7676126793742,"GB2-04":1498.419086653479,"GB2-05":1452.4784635488024,"GB2-06":1509.6397485055495,"GB2-07":1489.92018496162,"GB2-08":1450.5736214607266},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1621.6929233650376,"GB2-02":1462.6483700277522,"GB2-04":1489.097654712804,"GB2-05":1576.623648139087,"GB2-06":1582.872562787418,"GB2-07":1796.997875751851,"GB2-08":1519.9101728693004},"medium":{"GB2-01":1457.3329076565353,"GB2-02":1480.1661517225318,"GB2-03":1484.6051563726742,"GB2-04":1546.0267619373572,"GB2-05":1434.0659044162278,"GB2-06":1586.5913398799398,"GB2-07":1505.5687273778033,"GB2-08":1413.6318876144662},"none":{"GB2-01":1342.0336204181292,"GB2-02":1478.4883162878389,"GB2-03":1493.4152606481027,"GB2-04":1460.132843310276,"GB2-05":1346.745838091093,"GB2-06":1359.455342849291,"GB2-07":1167.1939517552057,"GB2-08":1418.178803898413}},"per_game_tracks":{"highest":{"GB2-01":56.34870578570014,"GB2-02":18.231928182356505,"GB2-04":29.555732530370754,"GB2-05":50.802629023107144,"GB2-06":59.82214388179885,"GB2-07":72.91920929796846,"GB2-08":39.43308067787763},"medium":{"GB2-01":40.290634444481384,"GB2-02":22.192579972734823,"GB2-03":37.442561303818024,"GB2-04":39.44018940023784,"GB2-05":39.16950375360156,"GB2-06":60.20667295526242,"GB2-07":47.13494994625827,"GB2-08":27.47285784764608},"none":{"GB2-01":29.269988200342766,"GB2-02":21.737279542205624,"GB2-03":39.007466418277744,"GB2-04":23.9977782784657,"GB2-05":31.727067905022835,"GB2-06":38.586565302093824,"GB2-07":16.762689788970278,"GB2-08":27.926757621782304}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":46.73048991131136,"medium":38.754201302051065,"none":28.626949132145132},"reasoning_agg":{"highest":{"max":72.91920929796846,"mean":46.73048991131136,"min":18.231928182356505},"medium":{"max":60.20667295526242,"mean":38.754201302051065,"min":22.192579972734823},"none":{"max":39.007466418277744,"mean":28.626949132145132,"min":16.762689788970278}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":72.91920929796846,"expected_score":34.19024108722295,"reasoning_variance":18.103540779166227,"reliability_score":98.07726492911503,"uncertainty_avg":1.9227350708849669,"uncertainty_penalty":-3.846972361279569},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":72.91920929796846,"expected_score":36.76397832550754,"reliability_score":98.37142669625047,"uncertainty_avg":1.6285733037495287,"uncertainty_penalty":-9.966511585803822},"medium":{"ceiling_score":60.20667295526242,"expected_score":39.692751928337465,"reliability_score":97.56284918283218,"uncertainty_avg":2.437150817167818,"uncertainty_penalty":0.9385506262863998},"none":{"ceiling_score":39.007466418277744,"expected_score":27.941988345209126,"reliability_score":97.01261126668525,"uncertainty_avg":2.9873887333147495,"uncertainty_penalty":-0.6849607869360064}}},{"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":0.12185499999999999,"mean":0.09110296875000001,"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":0.021642500000000002,"min":0.015285,"recorded_attempt_count":9,"run_count":8,"total":0.18239874999999997}},"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":0.12185499999999999,"mean":0.05695140625,"median":0.036751875,"min":0.015285,"recorded_attempt_count":24,"run_count":16,"total":0.9112224999999998},"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":38.11427405995131,"none":39.49308553111995},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":24,"finish_reasons":["stop"],"indexed_attempts":24,"output_token_observations":24,"total_output_tokens":178317},"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":"stop","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":"9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999","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":"2026-08-05T05:35:11Z","match_totals_all":{"draws":605,"losses":563,"wins":530},"match_totals_tracks":{"medium":{"draws":324,"losses":291,"wins":271},"none":{"draws":281,"losses":272,"wins":259}},"model_slug":"qwen-qwen3-7-max","overall":{"max":68.55479086064098,"mean":37.52968553445464,"min":20.42853187574935},"per_game_match_totals_all":{"GB2-01":{"draws":74,"losses":91,"wins":79},"GB2-02":{"draws":181,"losses":20,"wins":15},"GB2-03":{"draws":69,"losses":14,"wins":9},"GB2-04":{"draws":79,"losses":28,"wins":19},"GB2-05":{"draws":0,"losses":132,"wins":142},"GB2-06":{"draws":18,"losses":131,"wins":95},"GB2-07":{"draws":0,"losses":70,"wins":154},"GB2-08":{"draws":184,"losses":77,"wins":17}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":36,"losses":58,"wins":22},"GB2-02":{"draws":101,"losses":13,"wins":6},"GB2-04":{"draws":79,"losses":28,"wins":19},"GB2-05":{"draws":0,"losses":72,"wins":74},"GB2-06":{"draws":16,"losses":52,"wins":60},"GB2-07":{"draws":0,"losses":29,"wins":79},"GB2-08":{"draws":92,"losses":39,"wins":11}},"none":{"GB2-01":{"draws":38,"losses":33,"wins":57},"GB2-02":{"draws":80,"losses":7,"wins":9},"GB2-03":{"draws":69,"losses":14,"wins":9},"GB2-05":{"draws":0,"losses":60,"wins":68},"GB2-06":{"draws":2,"losses":79,"wins":35},"GB2-07":{"draws":0,"losses":41,"wins":75},"GB2-08":{"draws":92,"losses":38,"wins":6}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1313.0654330664993,"GB2-02":1484.1598241632423,"GB2-04":1486.7851670523426,"GB2-05":1550.122545035995,"GB2-06":1567.03231877175,"GB2-07":1714.4239416868895,"GB2-08":1421.2111834594807},"none":{"GB2-01":1621.9941068004882,"GB2-02":1483.2207038900344,"GB2-03":1428.1509269893077,"GB2-05":1517.2916673268228,"GB2-06":1237.0938999004793,"GB2-07":1748.906549027976,"GB2-08":1407.1694751108657}},"per_game_tracks":{"medium":{"GB2-01":24.836164490490482,"GB2-02":20.42853187574935,"GB2-04":26.353579719814093,"GB2-05":47.59284136341126,"GB2-06":56.92689918058069,"GB2-07":63.864244753090226,"GB2-08":26.797657036523127},"none":{"GB2-01":56.377814269152495,"GB2-02":22.482461561801962,"GB2-03":29.410317232417285,"GB2-05":45.955454000683424,"GB2-06":26.92797843552678,"GB2-07":68.55479086064098,"GB2-08":26.74278235761671}},"provider_color":"#FF6A00","provider_company":"Alibaba","provider_key":"qwen","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":36.862914223113556,"none":38.196456845795716},"reasoning_agg":{"medium":{"max":63.864244753090226,"mean":36.862914223113556,"min":20.42853187574935},"none":{"max":68.55479086064098,"mean":38.196456845795716,"min":22.482461561801962}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":68.55479086064098,"reasoning_variance":1.3335426226821596},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":63.864244753090226,"expected_score":39.28710820084531,"reliability_score":80.01913625535687,"uncertainty_avg":19.980863744643138,"uncertainty_penalty":2.424193977731754},"none":{"ceiling_score":68.55479086064098,"expected_score":39.0365661093203,"reliability_score":97.05571195286151,"uncertainty_avg":2.9442880471384925,"uncertainty_penalty":0.8401092635245817}}},{"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-2026-07-30":10},"run_count":9,"token_priced_attempt_count":10,"total":28.806540999999996},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.046574000000000004,"mean":0.036155625000000004,"median":0.035338,"min":0.025803,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":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-2026-07-30":9},"run_count":8,"token_priced_attempt_count":9,"total":0.17574200000000004}},"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-2026-07-30":28},"run_count":26,"token_priced_attempt_count":28,"total":29.297331},"codegen_latency_ms":{"attempt_count":28,"max_ms":220389,"mean_ms":65068.846153846156,"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":38.41713616417055,"highest":51.61421606005783,"medium":43.72233320991606,"none":19.914859222537764},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":28,"finish_reasons":["stop"],"indexed_attempts":52,"output_token_observations":28,"total_output_tokens":4846599},"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":"9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999","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":"2026-08-05T05:41:40Z","match_totals_all":{"draws":941,"losses":976,"wins":808},"match_totals_tracks":{"highest":{"draws":202,"losses":292,"wins":410},"medium":{"draws":363,"losses":268,"wins":297},"none":{"draws":376,"losses":416,"wins":101}},"model_slug":"gpt-5-6-luna","overall":{"max":79.30739463261588,"mean":37.49502654987403,"min":0.0},"per_game":{"GB2-01":78.7550562000012,"GB2-02":23.8282677671406,"GB2-03":22.061882688196544,"GB2-04":31.676324126516743,"GB2-05":54.59451105913189,"GB2-06":79.30739463261588,"GB2-07":73.56738030887553,"GB2-08":49.12291169798428},"per_game_all":{"GB2-01":56.20475603161476,"GB2-02":21.874331122414148,"GB2-03":31.496735927805492,"GB2-04":31.409187810397004,"GB2-05":36.23276841627352,"GB2-06":50.06958816689701,"GB2-07":45.18511687148356,"GB2-08":34.86460496647891},"per_game_match_totals_all":{"GB2-01":{"draws":43,"losses":135,"wins":173},"GB2-02":{"draws":284,"losses":21,"wins":5},"GB2-03":{"draws":134,"losses":75,"wins":57},"GB2-04":{"draws":239,"losses":51,"wins":40},"GB2-05":{"draws":0,"losses":243,"wins":137},"GB2-06":{"draws":22,"losses":165,"wins":153},"GB2-07":{"draws":0,"losses":190,"wins":162},"GB2-08":{"draws":219,"losses":96,"wins":81}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":0,"losses":37,"wins":85},"GB2-02":{"draws":92,"losses":13,"wins":5},"GB2-03":{"draws":31,"losses":34,"wins":15},"GB2-04":{"draws":55,"losses":29,"wins":24},"GB2-05":{"draws":0,"losses":70,"wins":60},"GB2-06":{"draws":14,"losses":24,"wins":66},"GB2-07":{"draws":0,"losses":38,"wins":84},"GB2-08":{"draws":10,"losses":47,"wins":71}},"medium":{"GB2-01":{"draws":9,"losses":33,"wins":66},"GB2-02":{"draws":86,"losses":6,"wins":0},"GB2-03":{"draws":56,"losses":18,"wins":14},"GB2-04":{"draws":100,"losses":6,"wins":6},"GB2-05":{"draws":0,"losses":70,"wins":70},"GB2-06":{"draws":8,"losses":45,"wins":75},"GB2-07":{"draws":0,"losses":66,"wins":58},"GB2-08":{"draws":104,"losses":24,"wins":8}},"none":{"GB2-01":{"draws":34,"losses":65,"wins":22},"GB2-02":{"draws":106,"losses":2,"wins":0},"GB2-03":{"draws":47,"losses":23,"wins":28},"GB2-04":{"draws":84,"losses":16,"wins":10},"GB2-05":{"draws":0,"losses":103,"wins":7},"GB2-06":{"draws":0,"losses":96,"wins":12},"GB2-07":{"draws":0,"losses":86,"wins":20},"GB2-08":{"draws":105,"losses":25,"wins":2}}},"per_game_raw_elo_all":{"GB2-01":1621.8501608463894,"GB2-02":1478.9741338063986,"GB2-03":1443.5949133993374,"GB2-04":1502.2052826025845,"GB2-05":1400.4139263298487,"GB2-06":1481.499567101874,"GB2-07":1485.6269256692167,"GB2-08":1479.4983170391397},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1854.3786077597374,"GB2-02":1486.958195948396,"GB2-03":1379.7892085139326,"GB2-04":1504.0415678282136,"GB2-05":1621.153408374177,"GB2-06":1791.117462946414,"GB2-07":1804.4339757540693,"GB2-08":1606.092096601223},"medium":{"GB2-01":1716.9606343725054,"GB2-02":1474.2956909913066,"GB2-03":1474.7736263454274,"GB2-04":1509.7853187158266,"GB2-05":1613.976425086682,"GB2-06":1642.207296864758,"GB2-07":1511.5918102941107,"GB2-08":1419.1245896868447},"none":{"GB2-01":1294.2112404069253,"GB2-02":1475.6685144794933,"GB2-03":1476.2219053386525,"GB2-04":1492.788961263713,"GB2-05":966.111945528687,"GB2-06":1011.1739414944491,"GB2-07":1140.8549909594703,"GB2-08":1413.2782648293512}},"per_game_tracks":{"highest":{"GB2-01":78.7550562000012,"GB2-02":23.8282677671406,"GB2-03":22.061882688196544,"GB2-04":31.676324126516743,"GB2-05":54.59451105913189,"GB2-06":79.30739463261588,"GB2-07":73.56738030887553,"GB2-08":49.12291169798428},"medium":{"GB2-01":65.2569227596586,"GB2-02":20.419129829006703,"GB2-03":35.95312226500334,"GB2-04":32.82673440407081,"GB2-05":54.10379418968867,"GB2-06":65.53875120306154,"GB2-07":47.58530359916948,"GB2-08":28.09490742966929},"none":{"GB2-01":24.602289135184463,"GB2-02":21.375595771095142,"GB2-03":36.47520283021661,"GB2-04":29.724504900603456,"GB2-05":0.0,"GB2-06":5.362618665013622,"GB2-07":14.402666706405672,"GB2-08":27.37599577178315}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":50.11655440056413,"medium":42.45366602652019,"none":19.914859222537768},"reasoning_agg":{"highest":{"max":79.30739463261588,"mean":50.11655440056413,"min":22.061882688196544},"medium":{"max":65.53875120306154,"mean":42.45366602652019,"min":20.419129829006703},"none":{"max":36.47520283021661,"mean":19.914859222537768,"min":0.0}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":79.30739463261588,"expected_score":35.183169911741935,"reasoning_variance":30.20169517802636,"reliability_score":96.58487334783705,"uncertainty_avg":3.4151266521629564,"uncertainty_penalty":-2.3118566381320917},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":79.30739463261588,"expected_score":42.195178409153286,"reliability_score":96.54508974566386,"uncertainty_avg":3.454910254336145,"uncertainty_penalty":-7.921375991410841},"medium":{"ceiling_score":65.53875120306154,"expected_score":44.430307076714065,"reliability_score":96.74765733958078,"uncertainty_avg":3.2523426604192105,"uncertainty_penalty":1.9766410501938765},"none":{"ceiling_score":36.47520283021661,"expected_score":18.92402424935845,"reliability_score":96.46187295826648,"uncertainty_avg":3.5381270417335116,"uncertainty_penalty":-0.990834973179318}}},{"codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":18},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.226689264,"mean":0.16037539425,"median":0.140728509,"min":0.10689655,"recorded_attempt_count":18,"run_count":8,"total":1.283003154}},"codegen_cost_usd":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":18},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.226689264,"mean":0.16037539425,"median":0.140728509,"min":0.10689655,"recorded_attempt_count":18,"run_count":8,"total":1.283003154},"codegen_latency_ms":{"attempt_count":18,"max_ms":1108247,"mean_ms":850298.125,"min_ms":548194,"run_count":8},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":18,"max_ms":1108247,"mean_ms":850298.125,"min_ms":548194,"run_count":8}},"codegen_output_tokens":{"attempt_count":18,"output_max":56063,"output_mean":38535.375,"output_min":23283,"run_count":8},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":18,"output_max":56063,"output_mean":38535.375,"output_min":23283,"run_count":8}},"display_name":"Kimi K2.7 Code","economics":{"medium":39.809027678930654},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":18,"finish_reasons":["length","stop"],"indexed_attempts":18,"output_token_observations":18,"total_output_tokens":308283},"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":"mixed","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":"9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999","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":"2026-08-05T05:26:41Z","match_totals_all":{"draws":213,"losses":262,"wins":291},"match_totals_tracks":{"medium":{"draws":213,"losses":262,"wins":291}},"model_slug":"moonshotai-kimi-k2-7-code","overall":{"max":54.35480356946494,"mean":37.04647459414284,"min":20.78553102586511},"per_game_match_totals_all":{"GB2-01":{"draws":4,"losses":57,"wins":63},"GB2-02":{"draws":108,"losses":24,"wins":6},"GB2-04":{"draws":91,"losses":17,"wins":10},"GB2-05":{"draws":0,"losses":61,"wins":67},"GB2-07":{"draws":0,"losses":57,"wins":75},"GB2-08":{"draws":10,"losses":46,"wins":70}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":4,"losses":57,"wins":63},"GB2-02":{"draws":108,"losses":24,"wins":6},"GB2-04":{"draws":91,"losses":17,"wins":10},"GB2-05":{"draws":0,"losses":61,"wins":67},"GB2-07":{"draws":0,"losses":57,"wins":75},"GB2-08":{"draws":10,"losses":46,"wins":70}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1483.6894964558528,"GB2-02":1482.3687742528214,"GB2-04":1458.6472427180993,"GB2-05":1612.6015854557863,"GB2-07":1538.7598223575376,"GB2-08":1667.5092199905735}},"per_game_tracks":{"medium":{"GB2-01":41.47617782039243,"GB2-02":20.78553102586511,"GB2-04":20.99855480228331,"GB2-05":52.59419174705676,"GB2-07":48.64490710852141,"GB2-08":54.35480356946494}},"provider_color":"#7C3AED","provider_company":"Moonshot","provider_key":"moonshotai","provider_text_color":"#faf5ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":37.04647459414284},"reasoning_agg":{"medium":{"max":54.35480356946494,"mean":37.04647459414284,"min":20.78553102586511}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Setting not tested"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":54.35480356946494},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":54.35480356946494,"expected_score":41.79520995753837,"reliability_score":80.54345314480375,"uncertainty_avg":19.456546855196255,"uncertainty_penalty":4.748735363395525}}},{"codegen_cost_by_reasoning":{"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":11},"evidence_basis":"Standard list-price estimate","max":0.09459400000000001,"mean":0.0571955,"median":0.043012,"min":0.032534,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":11},"run_count":8,"token_priced_attempt_count":11,"total":0.457564}},"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":11},"evidence_basis":"Standard list-price estimate","max":0.09459400000000001,"mean":0.0571955,"median":0.043012,"min":0.032534,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":11},"run_count":8,"token_priced_attempt_count":11,"total":0.457564},"codegen_latency_ms":{"attempt_count":11,"max_ms":57255,"mean_ms":36267.375,"min_ms":22935,"run_count":8},"codegen_latency_ms_by_reasoning":{"none":{"attempt_count":11,"max_ms":57255,"mean_ms":36267.375,"min_ms":22935,"run_count":8}},"codegen_output_tokens":{"attempt_count":11,"output_max":7568,"output_mean":4433.625,"output_min":2259,"run_count":8},"codegen_output_tokens_by_reasoning":{"none":{"attempt_count":11,"output_max":7568,"output_mean":4433.625,"output_min":2259,"run_count":8}},"display_name":"GPT 4.1","economics":{"none":36.39316993293498},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":11,"finish_reasons":["stop"],"indexed_attempts":11,"output_token_observations":11,"total_output_tokens":35469},"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":"stop","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":"9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999","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":5,"first_pass_rate":0.625,"model_code_failure_rate":0.0,"model_code_failures":0,"repaired_admitted":3,"repaired_rate":0.375}},"id":"gpt-4.1","is_recent_addition":false,"last_measured_at":"2026-08-05T05:41:31Z","match_totals_all":{"draws":324,"losses":336,"wins":273},"match_totals_tracks":{"none":{"draws":324,"losses":336,"wins":273}},"model_slug":"gpt-4-1","overall":{"max":56.63398289929676,"mean":36.39316993293499,"min":14.75877111394388},"per_game_match_totals_all":{"GB2-01":{"draws":6,"losses":61,"wins":72},"GB2-02":{"draws":99,"losses":13,"wins":2},"GB2-03":{"draws":29,"losses":39,"wins":30},"GB2-04":{"draws":81,"losses":15,"wins":6},"GB2-05":{"draws":0,"losses":87,"wins":33},"GB2-06":{"draws":10,"losses":45,"wins":55},"GB2-07":{"draws":0,"losses":58,"wins":54},"GB2-08":{"draws":99,"losses":18,"wins":21}},"per_game_match_totals_tracks":{"none":{"GB2-01":{"draws":6,"losses":61,"wins":72},"GB2-02":{"draws":99,"losses":13,"wins":2},"GB2-03":{"draws":29,"losses":39,"wins":30},"GB2-04":{"draws":81,"losses":15,"wins":6},"GB2-05":{"draws":0,"losses":87,"wins":33},"GB2-06":{"draws":10,"losses":45,"wins":55},"GB2-07":{"draws":0,"losses":58,"wins":54},"GB2-08":{"draws":99,"losses":18,"wins":21}}},"per_game_raw_elo_tracks":{"none":{"GB2-01":1559.2246913986785,"GB2-02":1474.1067750294355,"GB2-03":1514.5513087187508,"GB2-04":1467.8750459371463,"GB2-05":1142.4053752159446,"GB2-06":1551.1182735858504,"GB2-07":1569.68608538996,"GB2-08":1422.4172481872668}},"per_game_tracks":{"none":{"GB2-01":50.447789575371836,"GB2-02":21.259905179055554,"GB2-03":41.96266756353682,"GB2-04":25.006731116118797,"GB2-05":14.75877111394388,"GB2-06":56.63398289929676,"GB2-07":52.58029710675838,"GB2-08":28.495214909397852}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"none":36.39316993293499},"reasoning_agg":{"none":{"max":56.63398289929676,"mean":36.39316993293499,"min":14.75877111394388}},"reasoning_labels":{"highest":"Setting not tested","medium":"Setting not tested","none":"None"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":56.63398289929676},"score_diagnostics_by_reasoning":{"none":{"ceiling_score":56.63398289929676,"expected_score":38.192417378382075,"reliability_score":97.05098953193234,"uncertainty_avg":2.949010468067652,"uncertainty_penalty":1.7992474454470866}}},{"codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":19,"cell_count":8,"cost_basis_counts":{"estimated":32,"local_standard_estimate":8},"evidence_basis":"Mixed: Recorded attempt + Standard list-price estimate","failed_cell_count":13,"max":0.1097735,"mean":0.091486,"median":0.08840574999999999,"min":0.07737849999999999,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":40},"recorded_attempt_count":32,"run_count":32,"token_priced_attempt_count":8,"total":2.9275519999999995},"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":0.037309999999999996,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":8},"run_count":8,"token_priced_attempt_count":8,"total":0.390976},"none":{"admitted_cell_count":4,"cell_count":8,"cost_basis_counts":{"estimated":8,"local_standard_estimate":13},"evidence_basis":"Mixed: Recorded attempt + Standard list-price estimate","failed_cell_count":4,"max":0.17217,"mean":0.11039474999999999,"median":0.10846,"min":0.07562,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":13,"boardgame-list-prices-2026-07-30":8},"recorded_attempt_count":8,"run_count":8,"token_priced_attempt_count":13,"total":0.8831579999999999}},"codegen_cost_usd":{"admitted_cell_count":29,"cell_count":24,"cost_basis_counts":{"estimated":40,"local_standard_estimate":29},"evidence_basis":"Mixed: Recorded attempt + Standard list-price estimate","failed_cell_count":19,"max":0.17217,"mean":0.08358424999999998,"median":0.08653749999999999,"min":0.037309999999999996,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":13,"boardgame-list-prices-2026-07-30":56},"recorded_attempt_count":40,"run_count":48,"token_priced_attempt_count":29,"total":4.201686},"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":69,"output_max":15813,"output_mean":8194.3125,"output_min":2653,"run_count":48},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":40,"output_max":15813,"output_mean":9014.65625,"output_min":4501,"run_count":32},"medium":{"attempt_count":8,"output_max":6616,"output_mean":4172.125,"output_min":2653,"run_count":8},"none":{"attempt_count":21,"output_max":14517,"output_mean":8935.125,"output_min":5431,"run_count":8}},"display_name":"O3","economics":{"all":40.54627359887832,"highest":40.42513666720264,"medium":43.180486700957516,"none":32.47551028903298},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":29,"finish_reasons":["stop"],"indexed_attempts":93,"output_token_observations":69,"reasoning_token_observations":13,"total_output_tokens":393327,"total_reasoning_output_tokens":26752,"total_visible_output_tokens":24077,"visible_token_observations":13},"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":"9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999","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":4,"evaluated_cells":8,"failed_game_aliases":["GB2-02","GB2-03","GB2-04","GB2-05"],"first_pass_admitted":4,"first_pass_rate":0.5,"model_code_failure_rate":0.5,"model_code_failures":4},"intensive":{"admitted_plugins":19,"evaluated_cells":32,"failed_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-08"],"first_pass_admitted":19,"first_pass_rate":0.59375,"model_code_failure_rate":0.40625,"model_code_failures":13}},"id":"o3","is_recent_addition":false,"last_measured_at":"2026-08-05T05:41:08Z","match_totals_all":{"draws":473,"losses":1192,"wins":1090},"match_totals_tracks":{"highest":{"draws":156,"losses":751,"wins":714},"medium":{"draws":194,"losses":281,"wins":301},"none":{"draws":123,"losses":160,"wins":75}},"model_slug":"o3","overall":{"max":57.446840898177854,"mean":34.32604377644525,"min":24.48313253075837},"per_game":{"GB2-01":47.24502914491117,"GB2-03":32.4038428924734,"GB2-05":42.512279064156786,"GB2-06":46.82771632283495,"GB2-07":41.07624386646105,"GB2-08":32.48570871237849},"per_game_all":{"GB2-01":39.2678360346653,"GB2-06":45.599593023942894,"GB2-07":47.98160187354282,"GB2-08":29.33606346336229},"per_game_match_totals_all":{"GB2-01":{"draws":76,"losses":203,"wins":193},"GB2-03":{"draws":23,"losses":13,"wins":14},"GB2-04":{"draws":85,"losses":16,"wins":13},"GB2-05":{"draws":0,"losses":233,"wins":267},"GB2-06":{"draws":43,"losses":240,"wins":215},"GB2-07":{"draws":0,"losses":328,"wins":268},"GB2-08":{"draws":246,"losses":159,"wins":120}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":21,"losses":99,"wins":136},"GB2-03":{"draws":23,"losses":13,"wins":14},"GB2-05":{"draws":0,"losses":174,"wins":190},"GB2-06":{"draws":8,"losses":140,"wins":138},"GB2-07":{"draws":0,"losses":230,"wins":150},"GB2-08":{"draws":104,"losses":95,"wins":86}},"medium":{"GB2-01":{"draws":23,"losses":56,"wins":47},"GB2-04":{"draws":85,"losses":16,"wins":13},"GB2-05":{"draws":0,"losses":59,"wins":77},"GB2-06":{"draws":14,"losses":56,"wins":56},"GB2-07":{"draws":0,"losses":51,"wins":75},"GB2-08":{"draws":72,"losses":43,"wins":33}},"none":{"GB2-01":{"draws":32,"losses":48,"wins":10},"GB2-06":{"draws":21,"losses":44,"wins":21},"GB2-07":{"draws":0,"losses":47,"wins":43},"GB2-08":{"draws":70,"losses":21,"wins":1}}},"per_game_raw_elo_all":{"GB2-01":1463.4438058893948,"GB2-06":1451.2573674011428,"GB2-07":1532.479736341028,"GB2-08":1449.493690654536},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1556.3675251085415,"GB2-03":1486.0723605102608,"GB2-05":1502.1809824903353,"GB2-06":1476.1954291728616,"GB2-07":1463.3414112535602,"GB2-08":1491.2886959682157},"medium":{"GB2-01":1497.4090782162627,"GB2-04":1463.5159546573475,"GB2-05":1510.2714896969158,"GB2-06":1544.3048803307256,"GB2-07":1622.3477234865395,"GB2-08":1443.7534965706259},"none":{"GB2-01":1336.5548143433798,"GB2-06":1333.2717926998414,"GB2-07":1511.7500742829843,"GB2-08":1413.438879424766}},"per_game_tracks":{"highest":{"GB2-01":47.24502914491117,"GB2-03":32.4038428924734,"GB2-05":42.512279064156786,"GB2-06":46.82771632283495,"GB2-07":41.07624386646105,"GB2-08":32.48570871237849},"medium":{"GB2-01":44.31034547609485,"GB2-04":24.604745440205885,"GB2-05":45.45963078171682,"GB2-06":56.22200846259964,"GB2-07":57.446840898177854,"GB2-08":31.039349146950016},"none":{"GB2-01":26.248133482989893,"GB2-06":33.7490542863941,"GB2-07":45.42172085598957,"GB2-08":24.48313253075837}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":35.48562040144815,"medium":40.18397074230465,"none":27.308540185582956},"reasoning_agg":{"highest":{"max":47.24502914491117,"mean":35.48562040144815,"min":32.4038428924734},"medium":{"max":57.446840898177854,"mean":40.18397074230465,"min":24.604745440205885},"none":{"max":45.42172085598957,"mean":27.308540185582956,"min":24.48313253075837}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"baseline":"low","intensive":"high"},"score_diagnostics":{"ceiling_score":57.446840898177854,"expected_score":35.808683146092825,"reasoning_variance":12.875430556721696,"reliability_score":76.6863481846369,"uncertainty_avg":23.313651815363094,"uncertainty_penalty":1.482639369647572},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":47.24502914491117,"expected_score":29.71059993155824,"reliability_score":60.64545705768576,"uncertainty_avg":39.35454294231424,"uncertainty_penalty":-5.775020469889913},"medium":{"ceiling_score":57.446840898177854,"expected_score":42.3592882152203,"reliability_score":99.21188052926121,"uncertainty_avg":0.7881194707387943,"uncertainty_penalty":2.1753174729156513},"none":{"ceiling_score":45.42172085598957,"expected_score":30.96508517955574,"reliability_score":67.64798628782094,"uncertainty_avg":32.35201371217905,"uncertainty_penalty":3.6565449939727834}}},{"codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":15,"cell_count":8,"cost_basis_counts":{"estimated":2,"local_standard_estimate":29},"evidence_basis":"Mixed: Recorded attempt + Standard list-price estimate","failed_cell_count":2,"max":0.38568888333333334,"mean":0.288318396875,"median":0.28604548333333335,"min":0.22385259999999998,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":2,"boardgame-list-prices-2026-07-30":29},"recorded_attempt_count":2,"run_count":20,"token_priced_attempt_count":29,"total":5.92105485},"medium":{"admitted_cell_count":25,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":49},"evidence_basis":"Standard list-price estimate","failed_cell_count":7,"max":0.036200562500000005,"mean":0.024352715625,"median":0.02520601875,"min":0.0165820625,"pricing_table_versions":{"boardgame-list-prices-2026-07-30":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-2026-07-30":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":{"estimated":2,"local_standard_estimate":134},"evidence_basis":"Mixed: Recorded attempt + Standard list-price estimate","failed_cell_count":16,"max":0.38568888333333334,"mean":0.10722314947916667,"median":0.02520601875,"min":0.0058062875,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":2,"boardgame-list-prices-2026-07-30":134},"recorded_attempt_count":2,"run_count":84,"token_priced_attempt_count":134,"total":6.988288499999999},"codegen_latency_ms":{"attempt_count":134,"max_ms":4769864,"mean_ms":425200.4285714286,"min_ms":20868,"run_count":84},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":29,"max_ms":4769864,"mean_ms":1524489.3,"min_ms":584445,"run_count":20},"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":134,"output_max":316330,"output_mean":62913.92857142857,"output_min":2711,"run_count":84},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":29,"output_max":316330,"output_mean":227606.45,"output_min":128000,"run_count":20},"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":35.08249882713626,"highest":42.57151928445829,"medium":31.30438245280745,"none":31.371594744143064},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":133,"finish_reasons":["incomplete","stop"],"indexed_attempts":143,"output_token_observations":136,"reasoning_token_observations":2,"total_output_tokens":5284770,"total_reasoning_output_tokens":128000,"visible_token_observations":2},"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":"9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999","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":0.11764705882352941,"model_code_failures":2,"repaired_admitted":5,"repaired_rate":0.29411764705882354}},"id":"gpt-5.4-nano","is_recent_addition":false,"last_measured_at":"2026-08-05T06:55:07Z","match_totals_all":{"draws":2368,"losses":3032,"wins":2075},"match_totals_tracks":{"highest":{"draws":510,"losses":649,"wins":568},"medium":{"draws":728,"losses":1330,"wins":802},"none":{"draws":1130,"losses":1053,"wins":705}},"model_slug":"gpt-5-4-nano","overall":{"max":88.3001049099167,"mean":33.3949723013493,"min":15.510539068363032},"per_game":{"GB2-01":21.661903263791142,"GB2-02":25.174862159682817,"GB2-03":27.49558535920104,"GB2-04":18.002828160874977,"GB2-05":63.045401528569364,"GB2-06":88.3001049099167,"GB2-07":51.56133301083614,"GB2-08":45.330135882794195},"per_game_all":{"GB2-01":24.01386883621781,"GB2-02":21.212893320277175,"GB2-03":24.63374951847371,"GB2-04":28.469618865103502,"GB2-05":40.80731914667939,"GB2-06":67.08534536944174,"GB2-07":35.463065213355435,"GB2-08":38.97413034754138},"per_game_match_totals_all":{"GB2-01":{"draws":304,"losses":637,"wins":234},"GB2-02":{"draws":823,"losses":76,"wins":22},"GB2-03":{"draws":156,"losses":174,"wins":104},"GB2-04":{"draws":373,"losses":168,"wins":119},"GB2-05":{"draws":0,"losses":665,"wins":439},"GB2-06":{"draws":42,"losses":412,"wins":510},"GB2-07":{"draws":0,"losses":590,"wins":341},"GB2-08":{"draws":670,"losses":310,"wins":306}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":79,"losses":137,"wins":27},"GB2-02":{"draws":165,"losses":25,"wins":10},"GB2-03":{"draws":20,"losses":34,"wins":20},"GB2-04":{"draws":70,"losses":96,"wins":52},"GB2-05":{"draws":0,"losses":109,"wins":139},"GB2-06":{"draws":7,"losses":23,"wins":78},"GB2-07":{"draws":0,"losses":134,"wins":116},"GB2-08":{"draws":169,"losses":91,"wins":126}},"medium":{"GB2-01":{"draws":82,"losses":284,"wins":72},"GB2-02":{"draws":260,"losses":22,"wins":5},"GB2-03":{"draws":35,"losses":31,"wins":12},"GB2-04":{"draws":150,"losses":35,"wins":49},"GB2-05":{"draws":0,"losses":294,"wins":202},"GB2-06":{"draws":31,"losses":232,"wins":227},"GB2-07":{"draws":0,"losses":318,"wins":139},"GB2-08":{"draws":170,"losses":114,"wins":96}},"none":{"GB2-01":{"draws":143,"losses":216,"wins":135},"GB2-02":{"draws":398,"losses":29,"wins":7},"GB2-03":{"draws":101,"losses":109,"wins":72},"GB2-04":{"draws":153,"losses":37,"wins":18},"GB2-05":{"draws":0,"losses":262,"wins":98},"GB2-06":{"draws":4,"losses":157,"wins":205},"GB2-07":{"draws":0,"losses":138,"wins":86},"GB2-08":{"draws":331,"losses":105,"wins":84}}},"per_game_raw_elo_all":{"GB2-01":1288.6482793629204,"GB2-02":1476.1705577345467,"GB2-03":1397.4240953068029,"GB2-04":1485.8187438880298,"GB2-05":1456.023685753925,"GB2-06":1660.0980177874883,"GB2-07":1376.2402921794567,"GB2-08":1516.436544808371},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1263.7243618026978,"GB2-02":1495.187976281611,"GB2-03":1419.4866662482673,"GB2-04":1427.466947435084,"GB2-05":1723.859615334493,"GB2-06":1885.1585395368777,"GB2-07":1556.3211884250354,"GB2-08":1572.4716211595342},"medium":{"GB2-01":1202.111678705965,"GB2-02":1466.1689433354313,"GB2-03":1343.0197207211138,"GB2-04":1548.0156907933451,"GB2-05":1406.1825662737183,"GB2-06":1545.721116470262,"GB2-07":1285.053507576868,"GB2-08":1518.9622489746218},"none":{"GB2-01":1400.1087975800988,"GB2-02":1467.154753586598,"GB2-03":1429.7658989510273,"GB2-04":1481.9735934356604,"GB2-05":1238.0288756535647,"GB2-06":1549.4143973553253,"GB2-07":1287.3461805364666,"GB2-08":1457.8757642909575}},"per_game_tracks":{"highest":{"GB2-01":21.661903263791142,"GB2-02":25.174862159682817,"GB2-03":27.49558535920104,"GB2-04":18.002828160874977,"GB2-05":63.045401528569364,"GB2-06":88.3001049099167,"GB2-07":51.56133301083614,"GB2-08":45.330135882794195},"medium":{"GB2-01":15.510539068363032,"GB2-02":18.87263301066557,"GB2-03":16.71770471751947,"GB2-04":39.808585407262754,"GB2-05":36.68541016863408,"GB2-06":56.30542073431529,"GB2-07":27.32895163665409,"GB2-08":39.20581487904527},"none":{"GB2-01":34.869164176499254,"GB2-02":19.59118479048314,"GB2-03":29.687958478700622,"GB2-04":27.59744302717278,"GB2-05":22.69114574283472,"GB2-06":56.65051046409322,"GB2-07":27.498910992576068,"GB2-08":32.38644028078468}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":41.26004847678181,"medium":29.430839369796775,"none":29.494029057469312},"reasoning_agg":{"highest":{"max":88.3001049099167,"mean":41.26004847678181,"min":18.002828160874977},"medium":{"max":56.30542073431529,"mean":29.430839369796775,"min":15.510539068363032},"none":{"max":56.65051046409322,"mean":29.494029057469312,"min":19.59118479048314}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":88.3001049099167,"expected_score":30.73298474481104,"reasoning_variance":11.829209106985036,"reliability_score":96.20314296944665,"uncertainty_avg":3.796857030553351,"uncertainty_penalty":-2.661987556538257},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":88.3001049099167,"expected_score":31.999591359656087,"reliability_score":95.97221075264919,"uncertainty_avg":4.02778924735081,"uncertainty_penalty":-9.260457117125725},"medium":{"ceiling_score":56.30542073431529,"expected_score":29.479970006389568,"reliability_score":95.759427556268,"uncertainty_avg":4.240572443732008,"uncertainty_penalty":0.0491306365927926},"none":{"ceiling_score":56.65051046409322,"expected_score":30.719392868387473,"reliability_score":96.87779059942277,"uncertainty_avg":3.1222094005772347,"uncertainty_penalty":1.2253638109181608}}},{"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":32.351974454550025},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":17,"finish_reasons":["stop"],"indexed_attempts":17,"output_token_observations":17,"total_output_tokens":179458},"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":"stop","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":"9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999","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":"2026-08-05T05:34:43Z","match_totals_all":{"draws":369,"losses":345,"wins":266},"match_totals_tracks":{"medium":{"draws":369,"losses":345,"wins":266}},"model_slug":"x-ai-grok-build-0-1","overall":{"max":53.061970706152835,"mean":32.35197445455003,"min":19.32369832555091},"per_game_match_totals_all":{"GB2-01":{"draws":32,"losses":52,"wins":48},"GB2-02":{"draws":98,"losses":4,"wins":4},"GB2-03":{"draws":35,"losses":28,"wins":23},"GB2-04":{"draws":99,"losses":9,"wins":6},"GB2-05":{"draws":0,"losses":72,"wins":74},"GB2-06":{"draws":0,"losses":80,"wins":60},"GB2-07":{"draws":0,"losses":79,"wins":45},"GB2-08":{"draws":105,"losses":21,"wins":6}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":32,"losses":52,"wins":48},"GB2-02":{"draws":98,"losses":4,"wins":4},"GB2-03":{"draws":35,"losses":28,"wins":23},"GB2-04":{"draws":99,"losses":9,"wins":6},"GB2-05":{"draws":0,"losses":72,"wins":74},"GB2-06":{"draws":0,"losses":80,"wins":60},"GB2-07":{"draws":0,"losses":79,"wins":45},"GB2-08":{"draws":105,"losses":21,"wins":6}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1485.891033713489,"GB2-02":1482.927138599855,"GB2-03":1430.5628668819243,"GB2-04":1479.3940832357684,"GB2-05":1614.9703793474673,"GB2-06":1384.6428600108695,"GB2-07":1300.427688695992,"GB2-08":1413.3196679470848}},"per_game_tracks":{"medium":{"GB2-01":41.86454300140991,"GB2-02":19.32369832555091,"GB2-03":27.045539172534085,"GB2-04":24.474165233139676,"GB2-05":53.061970706152835,"GB2-06":39.92205480031329,"GB2-07":27.47064359767043,"GB2-08":25.653180799629084}},"provider_color":"#9CA3AF","provider_company":"xAI","provider_key":"x-ai","provider_text_color":"#0b1120","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":32.35197445455003},"reasoning_agg":{"medium":{"max":53.061970706152835,"mean":32.35197445455003,"min":19.32369832555091}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Setting not tested"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":53.061970706152835},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":53.061970706152835,"expected_score":30.814506124249124,"reliability_score":78.93750222916515,"uncertainty_avg":21.062497770834845,"uncertainty_penalty":-1.5374683303009071}}},{"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":0.43500896000000006},"none":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.0154064,"mean":0.00874386,"median":0.0064215999999999995,"min":0.00524064,"recorded_attempt_count":13,"run_count":9,"total":0.08145696000000001}},"codegen_cost_usd":{"admitted_cell_count":12,"cell_count":16,"cost_basis_counts":{"provider_reported":29},"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.08827968,"mean":0.03155999,"median":0.01479536,"min":0.00524064,"recorded_attempt_count":29,"run_count":17,"total":0.51646592},"codegen_latency_ms":{"attempt_count":29,"max_ms":1361767,"mean_ms":422352.64705882355,"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":42.51498698617433,"none":27.21481384964496},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":29,"finish_reasons":["stop"],"indexed_attempts":29,"output_token_observations":29,"total_output_tokens":343242},"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":"stop","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":"9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999","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":"2026-08-05T03:48:47Z","match_totals_all":{"draws":477,"losses":558,"wins":420},"match_totals_tracks":{"medium":{"draws":253,"losses":259,"wins":268},"none":{"draws":224,"losses":299,"wins":152}},"model_slug":"qwen-qwen3-7-plus","overall":{"max":69.54336053342072,"mean":32.07800689820225,"min":10.523618948427423},"per_game_match_totals_all":{"GB2-01":{"draws":53,"losses":119,"wins":78},"GB2-02":{"draws":213,"losses":6,"wins":1},"GB2-04":{"draws":81,"losses":9,"wins":6},"GB2-05":{"draws":0,"losses":136,"wins":134},"GB2-06":{"draws":14,"losses":123,"wins":102},"GB2-07":{"draws":0,"losses":141,"wins":99},"GB2-08":{"draws":116,"losses":24,"wins":0}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":25,"losses":53,"wins":50},"GB2-02":{"draws":100,"losses":5,"wins":1},"GB2-05":{"draws":0,"losses":73,"wins":73},"GB2-06":{"draws":12,"losses":39,"wins":71},"GB2-07":{"draws":0,"losses":65,"wins":73},"GB2-08":{"draws":116,"losses":24,"wins":0}},"none":{"GB2-01":{"draws":28,"losses":66,"wins":28},"GB2-02":{"draws":113,"losses":1,"wins":0},"GB2-04":{"draws":81,"losses":9,"wins":6},"GB2-05":{"draws":0,"losses":63,"wins":61},"GB2-06":{"draws":2,"losses":84,"wins":31},"GB2-07":{"draws":0,"losses":76,"wins":26}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1540.3642738682056,"GB2-02":1485.1566233238045,"GB2-05":1575.6588656258828,"GB2-06":1700.6031514919032,"GB2-07":1465.0315415173136,"GB2-08":1420.2115047229668},"none":{"GB2-01":1344.949051352309,"GB2-02":1460.4026985942367,"GB2-04":1482.7609209020502,"GB2-05":1534.5681458624933,"GB2-06":1270.1028923436827,"GB2-07":1097.921478157074}},"per_game_tracks":{"medium":{"GB2-01":47.08179953707419,"GB2-02":19.793619316293615,"GB2-05":49.73802589876419,"GB2-06":69.54336053342072,"GB2-07":42.3549780388027,"GB2-08":26.57813859269058},"none":{"GB2-01":29.520204387389295,"GB2-02":18.371420182291875,"GB2-04":27.455964717492304,"GB2-05":47.34237964243975,"GB2-06":30.075295219829112,"GB2-07":10.523618948427423}},"provider_color":"#FF6A00","provider_company":"Alibaba","provider_key":"qwen","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":39.56465347399636,"none":24.591360322408136},"reasoning_agg":{"medium":{"max":69.54336053342072,"mean":39.56465347399636,"min":19.793619316293615},"none":{"max":47.34237964243975,"mean":24.591360322408136,"min":10.523618948427423}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":69.54336053342072,"reasoning_variance":14.973293151588223},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":69.54336053342072,"expected_score":43.89758440663678,"reliability_score":80.98608506445909,"uncertainty_avg":19.013914935540907,"uncertainty_penalty":4.332930932640423},"none":{"ceiling_score":47.34237964243975,"expected_score":26.676243230167746,"reliability_score":96.66790254080085,"uncertainty_avg":3.332097459199145,"uncertainty_penalty":2.08488290775961}}},{"codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":11,"cell_count":8,"cost_basis_counts":{"provider_reported":35},"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.0068074,"mean":0.0034371900000000006,"median":0.00326368,"min":0.00211404,"recorded_attempt_count":35,"run_count":14,"total":0.04917795999999999},"none":{"admitted_cell_count":12,"cell_count":8,"cost_basis_counts":{"provider_reported":33},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.00407402,"mean":0.0029986699999999997,"median":0.00314426,"min":0.0012446800000000002,"recorded_attempt_count":33,"run_count":14,"total":0.04176386}},"codegen_cost_usd":{"admitted_cell_count":23,"cell_count":16,"cost_basis_counts":{"provider_reported":68},"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.0068074,"mean":0.0032179299999999995,"median":0.00314426,"min":0.0012446800000000002,"recorded_attempt_count":68,"run_count":28,"total":0.09094181999999999},"codegen_latency_ms":{"attempt_count":68,"max_ms":490920,"mean_ms":122427.25,"min_ms":29915,"run_count":28},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":35,"max_ms":490920,"mean_ms":129686.92857142857,"min_ms":29915,"run_count":14},"none":{"attempt_count":33,"max_ms":199208,"mean_ms":115167.57142857143,"min_ms":46525,"run_count":14}},"codegen_output_tokens":{"attempt_count":68,"output_max":42038,"output_mean":8274.82142857143,"output_min":1701,"run_count":28},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":35,"output_max":42038,"output_mean":9630.357142857143,"output_min":1701,"run_count":14},"none":{"attempt_count":33,"output_max":12644,"output_mean":6919.285714285715,"output_min":2544,"run_count":14}},"display_name":"Laguna S 2.1","economics":{"medium":27.22318762550223,"none":37.41625726018497},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":68,"finish_reasons":["length","stop"],"indexed_attempts":72,"output_token_observations":68,"reasoning_token_observations":45,"total_output_tokens":231695,"total_reasoning_output_tokens":57724,"total_visible_output_tokens":117243,"visible_token_observations":43},"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":"9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999","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":7,"first_pass_rate":0.5,"infra_excluded_game_aliases":["GB2-04","GB2-06"],"infra_failures_excluded":2,"model_code_failure_rate":0.14285714285714285,"model_code_failures":2,"repaired_admitted":5,"repaired_rate":0.35714285714285715}},"id":"poolside/laguna-s-2.1","is_recent_addition":false,"last_measured_at":"2026-08-05T06:54:33Z","match_totals_all":{"draws":917,"losses":850,"wins":646},"match_totals_tracks":{"medium":{"draws":407,"losses":350,"wins":191},"none":{"draws":510,"losses":500,"wins":455}},"model_slug":"poolside-laguna-s-2-1","overall":{"max":52.809153048377176,"mean":30.81606916124975,"min":15.67108825376102},"per_game_match_totals_all":{"GB2-01":{"draws":79,"losses":161,"wins":120},"GB2-02":{"draws":235,"losses":9,"wins":4},"GB2-03":{"draws":149,"losses":109,"wins":80},"GB2-04":{"draws":54,"losses":25,"wins":7},"GB2-05":{"draws":0,"losses":232,"wins":230},"GB2-06":{"draws":9,"losses":122,"wins":85},"GB2-07":{"draws":0,"losses":134,"wins":108},"GB2-08":{"draws":391,"losses":58,"wins":12}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":15,"losses":31,"wins":30},"GB2-02":{"draws":117,"losses":5,"wins":0},"GB2-03":{"draws":66,"losses":58,"wins":34},"GB2-04":{"draws":54,"losses":25,"wins":7},"GB2-05":{"draws":0,"losses":144,"wins":82},"GB2-06":{"draws":4,"losses":60,"wins":32},"GB2-08":{"draws":151,"losses":27,"wins":6}},"none":{"GB2-01":{"draws":64,"losses":130,"wins":90},"GB2-02":{"draws":118,"losses":4,"wins":4},"GB2-03":{"draws":83,"losses":51,"wins":46},"GB2-05":{"draws":0,"losses":88,"wins":148},"GB2-06":{"draws":5,"losses":62,"wins":53},"GB2-07":{"draws":0,"losses":134,"wins":108},"GB2-08":{"draws":240,"losses":31,"wins":6}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1473.5450833553969,"GB2-02":1484.3113488830672,"GB2-03":1452.9321995857717,"GB2-04":1444.4153901661002,"GB2-05":1367.1260289908478,"GB2-06":1300.0576365585443,"GB2-08":1426.0487153291788},"none":{"GB2-01":1522.0320223634517,"GB2-02":1473.7815159368622,"GB2-03":1463.0805512513246,"GB2-05":1601.3571049572838,"GB2-06":1244.6597352187855,"GB2-07":1556.7113363007984,"GB2-08":1409.6618782515638}},"per_game_tracks":{"medium":{"GB2-01":39.0077721461541,"GB2-02":15.67108825376102,"GB2-03":29.80483322714281,"GB2-04":17.01689741998006,"GB2-05":31.999553826228972,"GB2-06":30.958777248863868,"GB2-08":26.103391256384768},"none":{"GB2-01":46.88673329517897,"GB2-02":21.571994896490278,"GB2-03":34.32865162817713,"GB2-05":52.809153048377176,"GB2-06":27.704436166861854,"GB2-07":51.5535341301958,"GB2-08":27.059297656013577}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":25.630385524065343,"none":36.00175279843416},"reasoning_agg":{"medium":{"max":39.0077721461541,"mean":25.630385524065343,"min":15.67108825376102},"none":{"max":52.809153048377176,"mean":36.00175279843416,"min":21.571994896490278}},"reasoning_labels":{"highest":"Setting not tested","medium":"Enabled","none":"None"},"reasoning_settings":{"balanced":"enabled","baseline":"none"},"score_diagnostics":{"ceiling_score":52.809153048377176,"reasoning_variance":10.371367274368819},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":39.0077721461541,"expected_score":23.36528152461207,"reliability_score":66.23888859206735,"uncertainty_avg":33.76111140793265,"uncertainty_penalty":-2.265103999453274},"none":{"ceiling_score":52.809153048377176,"expected_score":36.93593301541102,"reliability_score":97.89311774263764,"uncertainty_avg":2.106882257362359,"uncertainty_penalty":0.9341802169768556}}},{"codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"provider_reported":50},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0719635,"mean":0.060768406250000004,"median":0.0604727,"min":0.05086675,"recorded_attempt_count":50,"run_count":16,"total":0.9722945000000002},"medium":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"provider_reported":48},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0481474,"mean":0.03800683125,"median":0.037386975,"min":0.02957195,"recorded_attempt_count":48,"run_count":16,"total":0.6081093000000001},"none":{"admitted_cell_count":15,"cell_count":8,"cost_basis_counts":{"provider_reported":34},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.0222516,"mean":0.01697319375,"median":0.015739925000000002,"min":0.012759,"recorded_attempt_count":34,"run_count":16,"total":0.27157109999999995}},"codegen_cost_usd":{"admitted_cell_count":43,"cell_count":24,"cost_basis_counts":{"provider_reported":132},"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.0719635,"mean":0.03858281041666666,"median":0.037386975,"min":0.012759,"recorded_attempt_count":132,"run_count":48,"total":1.8519749},"codegen_latency_ms":{"attempt_count":132,"max_ms":115030,"mean_ms":50137.9375,"min_ms":13430,"run_count":48},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":50,"max_ms":115030,"mean_ms":74972.3125,"min_ms":38302,"run_count":16},"medium":{"attempt_count":48,"max_ms":75176,"mean_ms":48761.1875,"min_ms":19840,"run_count":16},"none":{"attempt_count":34,"max_ms":54024,"mean_ms":26680.3125,"min_ms":13430,"run_count":16}},"codegen_output_tokens":{"attempt_count":132,"output_max":33866,"output_mean":12598.979166666666,"output_min":1476,"run_count":48},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":50,"output_max":33866,"output_mean":21067.4375,"output_min":11641,"run_count":16},"medium":{"attempt_count":48,"output_max":19346,"output_mean":12054.5625,"output_min":4066,"run_count":16},"none":{"attempt_count":34,"output_max":9270,"output_mean":4674.9375,"output_min":1476,"run_count":16}},"display_name":"Gemini 3.5 Flash Lite","economics":{"all":31.53472309901994,"highest":30.677141499448677,"medium":27.357331660578332,"none":36.569696137032814},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":132,"finish_reasons":["stop"],"indexed_attempts":132,"output_token_observations":132,"reasoning_token_observations":89,"total_output_tokens":604751,"total_reasoning_output_tokens":229572,"total_visible_output_tokens":177334,"visible_token_observations":89},"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":"stop","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":"9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999","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":["GB2-02","GB2-07"],"first_pass_admitted":14,"first_pass_rate":0.875,"model_code_failure_rate":0.125,"model_code_failures":2},"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":14,"evaluated_cells":16,"failed_game_aliases":["GB2-01","GB2-02"],"first_pass_admitted":13,"first_pass_rate":0.8125,"model_code_failure_rate":0.125,"model_code_failures":2,"repaired_admitted":1,"repaired_rate":0.0625}},"id":"google/gemini-3.5-flash-lite","is_recent_addition":false,"last_measured_at":"2026-08-05T06:55:18Z","match_totals_all":{"draws":1178,"losses":1314,"wins":858},"match_totals_tracks":{"highest":{"draws":250,"losses":433,"wins":283},"medium":{"draws":452,"losses":478,"wins":229},"none":{"draws":476,"losses":403,"wins":346}},"model_slug":"google-gemini-3-5-flash-lite","overall":{"max":58.42525560215735,"mean":30.70449655724711,"min":16.907630545609305},"per_game":{"GB2-01":33.26480003454013,"GB2-02":18.1638721019117,"GB2-03":35.67859448493501,"GB2-04":23.189651778222867,"GB2-05":26.677731076611366,"GB2-06":44.976480556909316,"GB2-07":42.53688282449636,"GB2-08":20.92911913796267},"per_game_all":{"GB2-01":38.864822266131135,"GB2-02":18.47753162137704,"GB2-03":36.23288158429719,"GB2-04":28.086529636370113,"GB2-05":24.58685205019508,"GB2-06":40.80742944962644,"GB2-07":40.91433723496493,"GB2-08":24.307400949197586},"per_game_match_totals_all":{"GB2-01":{"draws":130,"losses":175,"wins":169},"GB2-02":{"draws":243,"losses":13,"wins":8},"GB2-03":{"draws":110,"losses":113,"wins":99},"GB2-04":{"draws":330,"losses":70,"wins":62},"GB2-05":{"draws":0,"losses":360,"wins":128},"GB2-06":{"draws":15,"losses":276,"wins":171},"GB2-07":{"draws":0,"losses":211,"wins":205},"GB2-08":{"draws":350,"losses":96,"wins":16}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":15,"losses":33,"wins":20},"GB2-02":{"draws":50,"losses":5,"wins":7},"GB2-03":{"draws":23,"losses":41,"wins":38},"GB2-04":{"draws":90,"losses":34,"wins":24},"GB2-05":{"draws":0,"losses":104,"wins":42},"GB2-06":{"draws":10,"losses":75,"wins":61},"GB2-07":{"draws":0,"losses":100,"wins":86},"GB2-08":{"draws":62,"losses":41,"wins":5}},"medium":{"GB2-01":{"draws":58,"losses":73,"wins":81},"GB2-02":{"draws":49,"losses":1,"wins":0},"GB2-03":{"draws":59,"losses":41,"wins":24},"GB2-04":{"draws":155,"losses":19,"wins":15},"GB2-05":{"draws":0,"losses":128,"wins":48},"GB2-06":{"draws":3,"losses":132,"wins":27},"GB2-07":{"draws":0,"losses":55,"wins":29},"GB2-08":{"draws":128,"losses":29,"wins":5}},"none":{"GB2-01":{"draws":57,"losses":69,"wins":68},"GB2-02":{"draws":144,"losses":7,"wins":1},"GB2-03":{"draws":28,"losses":31,"wins":37},"GB2-04":{"draws":85,"losses":17,"wins":23},"GB2-05":{"draws":0,"losses":128,"wins":38},"GB2-06":{"draws":2,"losses":69,"wins":83},"GB2-07":{"draws":0,"losses":56,"wins":90},"GB2-08":{"draws":160,"losses":26,"wins":6}}},"per_game_raw_elo_all":{"GB2-01":1461.2068996302844,"GB2-02":1487.2161730199114,"GB2-03":1497.3080308938734,"GB2-04":1507.5659974206148,"GB2-05":1282.0242355224316,"GB2-06":1404.7044948225455,"GB2-07":1457.6059715859935,"GB2-08":1404.2398633014902},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1416.0011543444123,"GB2-02":1492.8544104693906,"GB2-03":1511.5338748338609,"GB2-04":1490.1431895503845,"GB2-05":1316.6954858769009,"GB2-06":1456.582517561534,"GB2-07":1478.8991729354007,"GB2-08":1378.4925532767802},"medium":{"GB2-01":1482.445425050893,"GB2-02":1488.5534739554275,"GB2-03":1443.7211533982504,"GB2-04":1509.0215300759746,"GB2-05":1283.6228237197265,"GB2-06":1160.9615169384278,"GB2-07":1253.5544921999174,"GB2-08":1402.7950522422157},"none":{"GB2-01":1485.1741194955482,"GB2-02":1480.2406346349167,"GB2-03":1536.6690644495093,"GB2-04":1523.5332726354854,"GB2-05":1245.754396970667,"GB2-06":1596.5694499676742,"GB2-07":1640.364249622662,"GB2-08":1431.4319843854755}},"per_game_tracks":{"highest":{"GB2-01":33.26480003454013,"GB2-02":18.1638721019117,"GB2-03":35.67859448493501,"GB2-04":23.189651778222867,"GB2-05":26.677731076611366,"GB2-06":44.976480556909316,"GB2-07":42.53688282449636,"GB2-08":20.92911913796267},"medium":{"GB2-01":42.286286758943646,"GB2-02":20.36109221661011,"GB2-03":30.36280463053722,"GB2-04":31.75108194933963,"GB2-05":25.9737881632984,"GB2-06":19.020552189812655,"GB2-07":23.992806942856724,"GB2-08":25.11024043322827},"none":{"GB2-01":41.043380004909636,"GB2-02":16.907630545609305,"GB2-03":42.65724563741933,"GB2-04":29.318855181547832,"GB2-05":21.109036910675474,"GB2-06":58.42525560215735,"GB2-07":56.213321937541714,"GB2-08":26.88284327640182}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#f5f9ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":29.66995603604416,"medium":26.459141496199234,"none":35.98439213949794},"reasoning_agg":{"highest":{"max":44.976480556909316,"mean":29.66995603604416,"min":18.1638721019117},"medium":{"max":42.286286758943646,"mean":26.459141496199234,"min":19.020552189812655},"none":{"max":58.42525560215735,"mean":35.98439213949794,"min":16.907630545609305}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Minimal"},"reasoning_settings":{"balanced":"medium","baseline":"minimal","intensive":"high"},"score_diagnostics":{"ceiling_score":58.42525560215735,"expected_score":30.24807824807378,"reasoning_variance":9.525250643298708,"reliability_score":70.30268475225641,"uncertainty_avg":29.697315247743585,"uncertainty_penalty":-0.4564183091733298},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":44.976480556909316,"expected_score":20.835472999933714,"reliability_score":59.04460025800209,"uncertainty_avg":40.95539974199791,"uncertainty_penalty":-8.834483036110445},"medium":{"ceiling_score":42.286286758943646,"expected_score":24.560627113934533,"reliability_score":86.53518031259259,"uncertainty_avg":13.464819687407406,"uncertainty_penalty":-1.8985143822647004},"none":{"ceiling_score":58.42525560215735,"expected_score":45.34813463035309,"reliability_score":65.32827368617455,"uncertainty_avg":34.67172631382545,"uncertainty_penalty":9.363742490855145}}},{"codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.007539277999999999,"mean":0.0032457859375,"median":0.0019568429999999998,"min":0.001266762,"recorded_attempt_count":14,"run_count":9,"total":0.031586439},"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":0.010139173999999999}},"codegen_cost_usd":{"admitted_cell_count":13,"cell_count":16,"cost_basis_counts":{"provider_reported":25},"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.007539277999999999,"mean":0.0022565913437500003,"median":0.0014932259999999998,"min":0.00090937,"recorded_attempt_count":25,"run_count":17,"total":0.041725613},"codegen_latency_ms":{"attempt_count":25,"max_ms":368409,"mean_ms":82415.5294117647,"min_ms":16892,"run_count":17},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":14,"max_ms":368409,"mean_ms":127998.11111111111,"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":25,"output_max":27553,"output_mean":7690.823529411765,"output_min":1430,"run_count":17},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":14,"output_max":27553,"output_mean":12332.666666666666,"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":30.2637506304396,"none":35.38721735351509},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":25,"finish_reasons":["stop"],"indexed_attempts":25,"output_token_observations":25,"total_output_tokens":130744},"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":"stop","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":"9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999","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":"2026-08-05T05:11:51Z","match_totals_all":{"draws":514,"losses":551,"wins":439},"match_totals_tracks":{"highest":{"draws":207,"losses":373,"wins":246},"none":{"draws":307,"losses":178,"wins":193}},"model_slug":"tencent-hy3-preview","overall":{"max":72.251918530255,"mean":30.676169136799764,"min":6.649465460691646},"per_game":{"GB2-01":53.57176981147765,"GB2-02":6.649465460691646,"GB2-04":17.326469166627668,"GB2-05":50.5644545454188,"GB2-06":27.91157848915521,"GB2-07":27.74104627006085,"GB2-08":28.081470669645384},"per_game_match_totals_all":{"GB2-01":{"draws":42,"losses":68,"wins":138},"GB2-02":{"draws":156,"losses":26,"wins":2},"GB2-03":{"draws":34,"losses":34,"wins":40},"GB2-04":{"draws":142,"losses":35,"wins":29},"GB2-05":{"draws":0,"losses":133,"wins":109},"GB2-06":{"draws":0,"losses":79,"wins":29},"GB2-07":{"draws":0,"losses":85,"wins":49},"GB2-08":{"draws":140,"losses":91,"wins":43}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":20,"losses":49,"wins":57},"GB2-02":{"draws":74,"losses":18,"wins":2},"GB2-04":{"draws":82,"losses":21,"wins":7},"GB2-05":{"draws":0,"losses":54,"wins":62},"GB2-06":{"draws":0,"losses":79,"wins":29},"GB2-07":{"draws":0,"losses":85,"wins":49},"GB2-08":{"draws":31,"losses":67,"wins":40}},"none":{"GB2-01":{"draws":22,"losses":19,"wins":81},"GB2-02":{"draws":82,"losses":8,"wins":0},"GB2-03":{"draws":34,"losses":34,"wins":40},"GB2-04":{"draws":60,"losses":14,"wins":22},"GB2-05":{"draws":0,"losses":79,"wins":47},"GB2-08":{"draws":109,"losses":24,"wins":3}}},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1607.7467039236506,"GB2-02":1425.23350130035,"GB2-04":1439.1610541264322,"GB2-05":1590.0681049031327,"GB2-06":1264.4416980243168,"GB2-07":1300.9786118237457,"GB2-08":1432.8212261015778},"none":{"GB2-01":1787.0910986805159,"GB2-02":1441.0350810658178,"GB2-03":1460.96396152062,"GB2-04":1521.5637786917036,"GB2-05":1313.945520868201,"GB2-08":1424.7781869391822}},"per_game_tracks":{"highest":{"GB2-01":53.57176981147765,"GB2-02":6.649465460691646,"GB2-04":17.326469166627668,"GB2-05":50.5644545454188,"GB2-06":27.91157848915521,"GB2-07":27.74104627006085,"GB2-08":28.081470669645384},"none":{"GB2-01":72.251918530255,"GB2-02":13.313054666786927,"GB2-03":34.56114839964518,"GB2-04":34.4004936024422,"GB2-05":29.06235888002087,"GB2-08":28.734330041940417}},"provider_color":"#12B7F5","provider_company":"Tencent","provider_key":"tencent","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":28.420821854316237,"none":32.93151641928329},"reasoning_agg":{"highest":{"max":53.57176981147765,"mean":28.420821854316237,"min":6.649465460691646},"none":{"max":72.251918530255,"mean":32.93151641928329,"min":13.313054666786927}},"reasoning_labels":{"highest":"High","medium":"Setting not tested","none":"None"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":72.251918530255,"reasoning_variance":4.510694564967054},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":53.57176981147765,"expected_score":18.352501142454237,"reliability_score":78.6857426300272,"uncertainty_avg":21.31425736997279,"uncertainty_penalty":-10.068320711862},"none":{"ceiling_score":72.251918530255,"expected_score":36.845937503723654,"reliability_score":96.37097140699804,"uncertainty_avg":3.6290285930019572,"uncertainty_penalty":3.914421084440363}}},{"codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":11,"cell_count":8,"cost_basis_counts":{"provider_reported":29},"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.017371818,"mean":0.00989701923,"median":0.010218342,"min":0.003562685,"recorded_attempt_count":29,"run_count":16,"total":0.15835230767999997},"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":0.0018257240000000001,"recorded_attempt_count":34,"run_count":24,"total":0.053353921299999996}},"codegen_cost_usd":{"admitted_cell_count":30,"cell_count":16,"cost_basis_counts":{"provider_reported":63},"evidence_basis":"Provider-reported","failed_cell_count":9,"max":0.017371818,"mean":0.006060049642083332,"median":0.0031725295999999997,"min":0.0018257240000000001,"recorded_attempt_count":63,"run_count":40,"total":0.21170622898000002},"codegen_latency_ms":{"attempt_count":63,"max_ms":1394682,"mean_ms":272853.575,"min_ms":18361,"run_count":40},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":29,"max_ms":1394682,"mean_ms":577846.5,"min_ms":61403,"run_count":16},"none":{"attempt_count":34,"max_ms":161045,"mean_ms":69524.95833333333,"min_ms":18361,"run_count":24}},"codegen_output_tokens":{"attempt_count":63,"output_max":82048,"output_mean":15129.25,"output_min":1698,"run_count":40},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":29,"output_max":82048,"output_mean":32454.8125,"output_min":4091,"run_count":16},"none":{"attempt_count":34,"output_max":7189,"output_mean":3578.875,"output_min":1698,"run_count":24}},"display_name":"DeepSeek V4 Flash","economics":{"all":31.784336010980308,"highest":34.783090077371796,"medium":30.90438899330132,"none":30.337491687517996},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":63,"finish_reasons":["length","stop"],"indexed_attempts":64,"output_token_observations":63,"total_output_tokens":605170},"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":"9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999","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":0.20833333333333334,"model_code_failures":5,"repaired_admitted":5,"repaired_rate":0.20833333333333334},"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":"2026-08-05T05:41:49Z","match_totals_all":{"draws":1658,"losses":1910,"wins":1204},"match_totals_tracks":{"highest":{"draws":314,"losses":598,"wins":382},"medium":{"draws":476,"losses":515,"wins":317},"none":{"draws":868,"losses":797,"wins":505}},"model_slug":"deepseek-deepseek-v4-flash","overall":{"max":54.873388733034076,"mean":30.569590367410274,"min":18.666770219098307},"per_game":{"GB2-01":37.87228212800732,"GB2-02":21.713702201359574,"GB2-05":34.450305869169036,"GB2-06":31.187597579426182,"GB2-07":54.873388733034076,"GB2-08":28.601263953234557},"per_game_all":{"GB2-01":38.54048527599101,"GB2-02":20.570257851568204,"GB2-05":33.23316198071509,"GB2-06":29.012717164839376,"GB2-07":42.40510236476184,"GB2-08":26.94429142800632},"per_game_match_totals_all":{"GB2-01":{"draws":140,"losses":258,"wins":182},"GB2-02":{"draws":512,"losses":57,"wins":13},"GB2-03":{"draws":94,"losses":89,"wins":71},"GB2-04":{"draws":318,"losses":54,"wins":20},"GB2-05":{"draws":0,"losses":479,"wins":349},"GB2-06":{"draws":7,"losses":425,"wins":192},"GB2-07":{"draws":0,"losses":413,"wins":351},"GB2-08":{"draws":587,"losses":135,"wins":26}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":51,"losses":120,"wins":75},"GB2-02":{"draws":167,"losses":29,"wins":8},"GB2-05":{"draws":0,"losses":146,"wins":96},"GB2-06":{"draws":1,"losses":154,"wins":59},"GB2-07":{"draws":0,"losses":110,"wins":138},"GB2-08":{"draws":95,"losses":39,"wins":6}},"medium":{"GB2-01":{"draws":55,"losses":90,"wins":51},"GB2-02":{"draws":148,"losses":20,"wins":4},"GB2-03":{"draws":19,"losses":23,"wins":20},"GB2-04":{"draws":71,"losses":11,"wins":4},"GB2-05":{"draws":0,"losses":119,"wins":91},"GB2-06":{"draws":2,"losses":117,"wins":67},"GB2-07":{"draws":0,"losses":115,"wins":75},"GB2-08":{"draws":181,"losses":20,"wins":5}},"none":{"GB2-01":{"draws":34,"losses":48,"wins":56},"GB2-02":{"draws":197,"losses":8,"wins":1},"GB2-03":{"draws":75,"losses":66,"wins":51},"GB2-04":{"draws":247,"losses":43,"wins":16},"GB2-05":{"draws":0,"losses":214,"wins":162},"GB2-06":{"draws":4,"losses":154,"wins":66},"GB2-07":{"draws":0,"losses":188,"wins":138},"GB2-08":{"draws":311,"losses":76,"wins":15}}},"per_game_raw_elo_all":{"GB2-01":1438.8981480477414,"GB2-02":1474.0548085050723,"GB2-05":1365.6224683456003,"GB2-06":1261.2221150137268,"GB2-07":1455.7594718596592,"GB2-08":1410.578716021457},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1431.2225647130356,"GB2-02":1478.3783144201457,"GB2-05":1379.6178552902875,"GB2-06":1283.4924627891278,"GB2-07":1593.6677941963164,"GB2-08":1423.1134240521621},"medium":{"GB2-01":1426.0411623944224,"GB2-02":1467.388261077859,"GB2-03":1549.5697459219878,"GB2-04":1463.9162000332021,"GB2-05":1307.71554307816,"GB2-06":1266.102135627474,"GB2-07":1421.8724654180028,"GB2-08":1403.0566857622682},"none":{"GB2-01":1459.4307170357656,"GB2-02":1476.3978500172125,"GB2-03":1472.9147812034898,"GB2-04":1447.841790346759,"GB2-05":1409.534006668353,"GB2-06":1234.071746624579,"GB2-07":1351.7381559646585,"GB2-08":1405.5660382499407}},"per_game_tracks":{"highest":{"GB2-01":37.87228212800732,"GB2-02":21.713702201359574,"GB2-05":34.450305869169036,"GB2-06":31.187597579426182,"GB2-07":54.873388733034076,"GB2-08":28.601263953234557},"medium":{"GB2-01":36.957906696826875,"GB2-02":18.666770219098307,"GB2-03":45.51671696216456,"GB2-04":23.676956043399027,"GB2-05":28.266873714533958,"GB2-06":29.274718681120902,"GB2-07":39.16873173236723,"GB2-08":25.706437896899708},"none":{"GB2-01":40.791267003138834,"GB2-02":21.33030113424673,"GB2-03":35.908955370742355,"GB2-04":21.412909336833845,"GB2-05":36.982306358442266,"GB2-06":26.575835233971056,"GB2-07":33.17318662888423,"GB2-08":26.52517243388469}},"provider_color":"#4C8BF5","provider_company":"DeepSeek","provider_key":"deepseek","provider_text_color":"#f6f9ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":32.18796481877993,"medium":30.904388993301325,"none":28.616417290149577},"reasoning_agg":{"highest":{"max":54.873388733034076,"mean":32.18796481877993,"min":21.713702201359574},"medium":{"max":45.51671696216456,"mean":30.904388993301325,"min":18.666770219098307},"none":{"max":40.791267003138834,"mean":28.616417290149577,"min":21.33030113424673}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":54.873388733034076,"expected_score":24.351938368297652,"reasoning_variance":3.5715475286303544,"reliability_score":96.15374110683621,"uncertainty_avg":3.846258893163793,"uncertainty_penalty":-6.217651999112622},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":54.873388733034076,"expected_score":20.502864224136648,"reliability_score":97.74056513942773,"uncertainty_avg":2.259434860572275,"uncertainty_penalty":-11.685100594643284},"medium":{"ceiling_score":45.51671696216456,"expected_score":26.011988043167484,"reliability_score":91.16747062373179,"uncertainty_avg":8.832529376268209,"uncertainty_penalty":-4.89240095013384},"none":{"ceiling_score":40.791267003138834,"expected_score":29.05506492233477,"reliability_score":96.62460312213427,"uncertainty_avg":3.3753968778657266,"uncertainty_penalty":0.43864763218519087}}},{"codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":20},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.038769960000000006,"mean":0.023744302225,"median":0.0230069837,"min":0.0074361952000000005,"recorded_attempt_count":20,"run_count":9,"total":0.21411433159999999},"none":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0097359,"mean":0.0038356840999999994,"median":0.0020557588,"min":0.0014804776,"recorded_attempt_count":12,"run_count":8,"total":0.030685472800000002}},"codegen_cost_usd":{"admitted_cell_count":13,"cell_count":16,"cost_basis_counts":{"provider_reported":32},"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.038769960000000006,"mean":0.0137899931625,"median":0.009162978799999999,"min":0.0014804776,"recorded_attempt_count":32,"run_count":17,"total":0.2447998044},"codegen_latency_ms":{"attempt_count":32,"max_ms":2480898,"mean_ms":755138.0,"min_ms":19112,"run_count":17},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":20,"max_ms":2480898,"mean_ms":1257942.2222222222,"min_ms":113183,"run_count":9},"none":{"attempt_count":12,"max_ms":1141174,"mean_ms":189483.25,"min_ms":19112,"run_count":8}},"codegen_output_tokens":{"attempt_count":32,"output_max":131072,"output_mean":43207.23529411765,"output_min":1607,"run_count":17},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":20,"output_max":131072,"output_mean":76516.0,"output_min":16030,"run_count":9},"none":{"attempt_count":12,"output_max":24962,"output_mean":5734.875,"output_min":1607,"run_count":8}},"display_name":"MiMo-V2.5","economics":{"all":30.017335423163285,"highest":30.680639185909847,"medium":29.977619677601712,"none":34.33105017629488},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":32,"finish_reasons":["length","stop"],"indexed_attempts":32,"output_token_observations":32,"total_output_tokens":734523},"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":"mixed","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":"9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999","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":9,"failed_game_aliases":["GB2-03","GB2-08"],"model_code_failure_rate":0.2222222222222222,"model_code_failures":2,"repaired_admitted":7,"repaired_rate":0.7777777777777778},"baseline":{"admitted_plugins":6,"evaluated_cells":8,"failed_game_aliases":["GB2-02","GB2-04"],"first_pass_admitted":5,"first_pass_rate":0.625,"model_code_failure_rate":0.25,"model_code_failures":2,"repaired_admitted":1,"repaired_rate":0.125}},"id":"xiaomi/mimo-v2.5","is_recent_addition":false,"last_measured_at":"2026-08-05T05:41:45Z","match_totals_all":{"draws":1539,"losses":1511,"wins":1104},"match_totals_tracks":{"highest":{"draws":302,"losses":102,"wins":58},"medium":{"draws":682,"losses":671,"wins":457},"none":{"draws":555,"losses":738,"wins":589}},"model_slug":"xiaomi-mimo-v2-5","overall":{"max":55.431385487557364,"mean":30.2604654370234,"min":18.203309021107163},"per_game":{"GB2-01":18.203309021107163,"GB2-02":24.606196776104223,"GB2-04":29.200565710939646,"GB2-06":55.431385487557364,"GB2-08":25.961738933840852},"per_game_all":{"GB2-01":32.33799765071344,"GB2-02":21.39954510327829,"GB2-04":26.78481738996592,"GB2-06":46.06840755007216,"GB2-08":23.49590942178662},"per_game_match_totals_all":{"GB2-01":{"draws":169,"losses":330,"wins":233},"GB2-02":{"draws":440,"losses":38,"wins":12},"GB2-03":{"draws":55,"losses":28,"wins":23},"GB2-04":{"draws":472,"losses":86,"wins":54},"GB2-05":{"draws":0,"losses":334,"wins":286},"GB2-06":{"draws":17,"losses":291,"wins":246},"GB2-07":{"draws":0,"losses":243,"wins":213},"GB2-08":{"draws":386,"losses":161,"wins":37}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":59,"losses":37,"wins":2},"GB2-02":{"draws":79,"losses":12,"wins":3},"GB2-04":{"draws":64,"losses":10,"wins":6},"GB2-06":{"draws":8,"losses":38,"wins":44},"GB2-08":{"draws":92,"losses":5,"wins":3}},"medium":{"GB2-01":{"draws":22,"losses":130,"wins":96},"GB2-02":{"draws":270,"losses":25,"wins":9},"GB2-04":{"draws":260,"losses":64,"wins":26},"GB2-05":{"draws":0,"losses":158,"wins":128},"GB2-06":{"draws":5,"losses":85,"wins":48},"GB2-07":{"draws":0,"losses":118,"wins":120},"GB2-08":{"draws":125,"losses":91,"wins":30}},"none":{"GB2-01":{"draws":88,"losses":163,"wins":135},"GB2-02":{"draws":91,"losses":1,"wins":0},"GB2-03":{"draws":55,"losses":28,"wins":23},"GB2-04":{"draws":148,"losses":12,"wins":22},"GB2-05":{"draws":0,"losses":176,"wins":158},"GB2-06":{"draws":4,"losses":168,"wins":154},"GB2-07":{"draws":0,"losses":125,"wins":93},"GB2-08":{"draws":169,"losses":65,"wins":4}}},"per_game_raw_elo_all":{"GB2-01":1380.021461021667,"GB2-02":1483.5039852296297,"GB2-04":1484.3334767766974,"GB2-06":1444.5465188481128,"GB2-08":1386.9787519975828},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1231.9886564398028,"GB2-02":1493.7218026454714,"GB2-04":1496.3395528223577,"GB2-06":1542.4105298643044,"GB2-08":1405.890887252805},"medium":{"GB2-01":1403.0571105645727,"GB2-02":1483.4266020335688,"GB2-04":1472.1427871764781,"GB2-05":1376.9153252902406,"GB2-06":1328.3252491367793,"GB2-07":1463.2899833942533,"GB2-08":1395.6463544370927},"none":{"GB2-01":1505.0186160606256,"GB2-02":1473.363551009849,"GB2-03":1505.0791075326886,"GB2-04":1484.5180903312562,"GB2-05":1430.9556199173985,"GB2-06":1462.9037775432546,"GB2-07":1350.401767487915,"GB2-08":1359.3990143028504}},"per_game_tracks":{"highest":{"GB2-01":18.203309021107163,"GB2-02":24.606196776104223,"GB2-04":29.200565710939646,"GB2-06":55.431385487557364,"GB2-08":25.961738933840852},"medium":{"GB2-01":33.73684260264018,"GB2-02":19.3697810729317,"GB2-04":23.57867696137189,"GB2-05":33.32866694206213,"GB2-06":34.540674524591545,"GB2-07":41.83782119188973,"GB2-08":23.450874447724814},"none":{"GB2-01":45.07384132839297,"GB2-02":20.22265746079894,"GB2-03":40.825908860305795,"GB2-04":27.575209497586215,"GB2-05":38.583428548446186,"GB2-06":48.233162638067576,"GB2-07":33.05907819296716,"GB2-08":21.075114883794193}},"provider_color":"#FF6900","provider_company":"Xiaomi","provider_key":"xiaomi","provider_text_color":"#fff7f1","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":30.680639185909847,"medium":28.15211501302235,"none":31.948642112138003},"reasoning_agg":{"highest":{"max":55.431385487557364,"mean":30.680639185909847,"min":18.203309021107163},"medium":{"max":41.83782119188973,"mean":28.15211501302235,"min":19.3697810729317},"none":{"max":48.233162638067576,"mean":31.948642112138003,"min":20.22265746079894}},"reasoning_labels":{"highest":"High","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":55.431385487557364,"expected_score":23.026529070042375,"reasoning_variance":3.7965270991156537,"reliability_score":88.86197885271446,"uncertainty_avg":11.13802114728554,"uncertainty_penalty":-7.233936366981023},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":55.431385487557364,"expected_score":18.531628894126563,"reliability_score":91.89550694612615,"uncertainty_avg":8.104493053873849,"uncertainty_penalty":-12.149010291783284},"medium":{"ceiling_score":41.83782119188973,"expected_score":28.31625447671681,"reliability_score":80.04093325558001,"uncertainty_avg":19.95906674441999,"uncertainty_penalty":0.16413946369446109},"none":{"ceiling_score":48.233162638067576,"expected_score":35.401959751239744,"reliability_score":95.58471137326397,"uncertainty_avg":4.4152886267360305,"uncertainty_penalty":3.4533176391017406}}},{"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":222264.07142857142,"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":36.64777963132047,"none":29.70875851892183},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":23,"finish_reasons":["stop"],"indexed_attempts":25,"output_token_observations":23,"total_output_tokens":77013},"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":"9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999","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":"2026-08-05T03:57:18Z","match_totals_all":{"draws":335,"losses":526,"wins":407},"match_totals_tracks":{"medium":{"draws":95,"losses":224,"wins":205},"none":{"draws":240,"losses":302,"wins":202}},"model_slug":"google-gemma-4-31b-it","overall":{"max":49.01545827784715,"mean":30.224370973946137,"min":19.625108861534393},"per_game_match_totals_all":{"GB2-01":{"draws":32,"losses":44,"wins":66},"GB2-04":{"draws":184,"losses":21,"wins":21},"GB2-05":{"draws":0,"losses":147,"wins":119},"GB2-06":{"draws":5,"losses":155,"wins":92},"GB2-07":{"draws":0,"losses":134,"wins":106},"GB2-08":{"draws":114,"losses":25,"wins":3}},"per_game_match_totals_tracks":{"medium":{"GB2-04":{"draws":92,"losses":8,"wins":10},"GB2-05":{"draws":0,"losses":67,"wins":81},"GB2-06":{"draws":3,"losses":86,"wins":45},"GB2-07":{"draws":0,"losses":63,"wins":69}},"none":{"GB2-01":{"draws":32,"losses":44,"wins":66},"GB2-04":{"draws":92,"losses":13,"wins":11},"GB2-05":{"draws":0,"losses":80,"wins":38},"GB2-06":{"draws":2,"losses":69,"wins":47},"GB2-07":{"draws":0,"losses":71,"wins":37},"GB2-08":{"draws":114,"losses":25,"wins":3}}},"per_game_raw_elo_tracks":{"medium":{"GB2-04":1477.6340912382486,"GB2-05":1566.1873360530612,"GB2-06":1324.5664254277772,"GB2-07":1431.3500810499045},"none":{"GB2-01":1463.448626577189,"GB2-04":1467.7100792380625,"GB2-05":1201.3664980516578,"GB2-06":1353.9510085269612,"GB2-07":1273.2695604121793,"GB2-08":1415.331625152364}},"per_game_tracks":{"medium":{"GB2-04":24.21197020273949,"GB2-05":49.01545827784715,"GB2-06":34.10425107444389,"GB2-07":39.25943897025135},"none":{"GB2-01":41.22577138332814,"GB2-04":25.412668235568347,"GB2-05":19.625108861534393,"GB2-06":38.046844177408595,"GB2-07":26.19428053874851,"GB2-08":27.747877916943}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#f5f9ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":31.863109432351056,"none":28.585632515541217},"reasoning_agg":{"medium":{"max":49.01545827784715,"mean":31.863109432351056,"min":24.21197020273949},"none":{"max":41.22577138332814,"mean":28.585632515541217,"min":19.625108861534393}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":49.01545827784715,"reasoning_variance":3.2774769168098388},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":49.01545827784715,"expected_score":37.58134636954167,"reliability_score":81.5764629298845,"uncertainty_avg":18.4235370701155,"uncertainty_penalty":5.718236937190614},"none":{"ceiling_score":41.22577138332814,"expected_score":27.858512255296066,"reliability_score":98.20230328066981,"uncertainty_avg":1.7976967193301885,"uncertainty_penalty":-0.727120260245151}}},{"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":0.09705768000000001,"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":0.20304798000000002}},"codegen_cost_usd":{"admitted_cell_count":13,"cell_count":16,"cost_basis_counts":{"provider_reported":30},"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.09803328,"mean":0.049222395,"median":0.05336871,"min":0.00639384,"recorded_attempt_count":30,"run_count":16,"total":0.78755832},"codegen_latency_ms":{"attempt_count":30,"max_ms":689304,"mean_ms":337511.375,"min_ms":47263,"run_count":16},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":17,"max_ms":689304,"mean_ms":510017.125,"min_ms":355427,"run_count":8},"none":{"attempt_count":13,"max_ms":622847,"mean_ms":165005.625,"min_ms":47263,"run_count":8}},"codegen_output_tokens":{"attempt_count":30,"output_max":78058,"output_mean":37255.0,"output_min":3462,"run_count":16},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":17,"output_max":76773,"output_mean":56941.375,"output_min":40677,"run_count":8},"none":{"attempt_count":13,"output_max":78058,"output_mean":17568.625,"output_min":3462,"run_count":8}},"display_name":"Minimax M3","economics":{"medium":24.860989928116304,"none":37.27597496645672},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":30,"finish_reasons":["stop"],"indexed_attempts":30,"output_token_observations":30,"total_output_tokens":596080},"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":"stop","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":"9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999","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":"2026-08-05T05:18:47Z","match_totals_all":{"draws":462,"losses":667,"wins":465},"match_totals_tracks":{"medium":{"draws":292,"losses":401,"wins":181},"none":{"draws":170,"losses":266,"wins":284}},"model_slug":"minimax-minimax-m3","overall":{"max":49.2908922032663,"mean":29.366981281242193,"min":5.922992138645202},"per_game_match_totals_all":{"GB2-01":{"draws":37,"losses":125,"wins":112},"GB2-02":{"draws":179,"losses":18,"wins":1},"GB2-03":{"draws":36,"losses":31,"wins":39},"GB2-04":{"draws":90,"losses":15,"wins":9},"GB2-05":{"draws":0,"losses":182,"wins":80},"GB2-06":{"draws":0,"losses":91,"wins":47},"GB2-07":{"draws":0,"losses":126,"wins":116},"GB2-08":{"draws":120,"losses":79,"wins":61}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":10,"losses":76,"wins":40},"GB2-02":{"draws":86,"losses":15,"wins":1},"GB2-04":{"draws":90,"losses":15,"wins":9},"GB2-05":{"draws":0,"losses":117,"wins":7},"GB2-06":{"draws":0,"losses":91,"wins":47},"GB2-07":{"draws":0,"losses":62,"wins":70},"GB2-08":{"draws":106,"losses":25,"wins":7}},"none":{"GB2-01":{"draws":27,"losses":49,"wins":72},"GB2-02":{"draws":93,"losses":3,"wins":0},"GB2-03":{"draws":36,"losses":31,"wins":39},"GB2-05":{"draws":0,"losses":65,"wins":73},"GB2-07":{"draws":0,"losses":64,"wins":46},"GB2-08":{"draws":14,"losses":54,"wins":54}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1324.6039580133202,"GB2-02":1438.8948469330253,"GB2-04":1485.1287926439377,"GB2-05":1050.902463188506,"GB2-06":1317.550618114029,"GB2-07":1516.9713046631996,"GB2-08":1416.249176342982},"none":{"GB2-01":1546.2174621120816,"GB2-02":1459.554229345278,"GB2-03":1477.4575917303791,"GB2-05":1479.8535519192562,"GB2-07":1398.4735570462385,"GB2-08":1523.6098803293485}},"per_game_tracks":{"medium":{"GB2-01":26.1854385334171,"GB2-02":9.967521810790636,"GB2-04":25.500503430901084,"GB2-05":5.922992138645202,"GB2-06":33.51820706435848,"GB2-07":46.776416361264104,"GB2-08":26.15585015743753},"none":{"GB2-01":49.2908922032663,"GB2-02":17.49414607975783,"GB2-03":36.871448824939826,"GB2-05":42.95654254826272,"GB2-07":37.34465187857206,"GB2-08":39.69816826394159}},"provider_color":"#00BFA5","provider_company":"MiniMax","provider_key":"minimax","provider_text_color":"#f2fffc","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":24.04475913093154,"none":34.68920343155285},"reasoning_agg":{"medium":{"max":46.776416361264104,"mean":24.04475913093154,"min":5.922992138645202},"none":{"max":49.2908922032663,"mean":34.68920343155285,"min":17.49414607975783}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":49.2908922032663,"reasoning_variance":10.64444430062131},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":46.776416361264104,"expected_score":21.324139850923924,"reliability_score":79.8465833154339,"uncertainty_avg":20.1534166845661,"uncertainty_penalty":-2.7206192800076145},"none":{"ceiling_score":49.2908922032663,"expected_score":38.969807229771355,"reliability_score":97.22574762833989,"uncertainty_avg":2.774252371660116,"uncertainty_penalty":4.2806037982185074}}},{"codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":12,"cell_count":8,"cost_basis_counts":{"provider_reported":70},"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.103943664,"mean":0.0866474535,"median":0.088847748,"min":0.062759676,"recorded_attempt_count":70,"run_count":16,"total":1.386359256},"none":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"provider_reported":38},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.021206376000000002,"mean":0.01337795025,"median":0.01381146,"min":0.006392298,"recorded_attempt_count":38,"run_count":16,"total":0.21404720400000002}},"codegen_cost_usd":{"admitted_cell_count":26,"cell_count":16,"cost_basis_counts":{"provider_reported":108},"evidence_basis":"Provider-reported","failed_cell_count":6,"max":0.103943664,"mean":0.050012701874999996,"median":0.041983026,"min":0.006392298,"recorded_attempt_count":108,"run_count":32,"total":1.6004064599999999},"codegen_latency_ms":{"attempt_count":87,"max_ms":1635062,"mean_ms":598630.75,"min_ms":47979,"run_count":32},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":49,"max_ms":1635062,"mean_ms":1021590.9375,"min_ms":525940,"run_count":16},"none":{"attempt_count":38,"max_ms":457140,"mean_ms":175670.5625,"min_ms":47979,"run_count":16}},"codegen_output_tokens":{"attempt_count":97,"output_max":110598,"output_mean":38325.9375,"output_min":2150,"run_count":32},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":59,"output_max":110598,"output_mean":68392.8125,"output_min":16796,"run_count":16},"none":{"attempt_count":38,"output_max":22812,"output_mean":8259.0625,"output_min":2150,"run_count":16}},"display_name":"LongCat 2.0","economics":{"medium":27.9422064022846,"none":32.92807444254993},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":87,"finish_reasons":["length","stop","unknown"],"indexed_attempts":109,"output_token_observations":109,"reasoning_token_observations":57,"total_output_tokens":1226430,"total_reasoning_output_tokens":474156,"total_visible_output_tokens":133629,"visible_token_observations":44},"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":"9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999","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"],"first_pass_admitted":9,"first_pass_rate":0.5625,"model_code_failure_rate":0.25,"model_code_failures":4,"repaired_admitted":3,"repaired_rate":0.1875},"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":"2026-08-05T06:54:28Z","match_totals_all":{"draws":834,"losses":1094,"wins":728},"match_totals_tracks":{"medium":{"draws":212,"losses":449,"wins":271},"none":{"draws":622,"losses":645,"wins":457}},"model_slug":"meituan-longcat-2-0","overall":{"max":48.45429450824968,"mean":28.925069936877264,"min":11.347553349665287},"per_game_match_totals_all":{"GB2-01":{"draws":92,"losses":103,"wins":83},"GB2-02":{"draws":165,"losses":9,"wins":2},"GB2-03":{"draws":109,"losses":81,"wins":68},"GB2-04":{"draws":145,"losses":65,"wins":36},"GB2-05":{"draws":0,"losses":283,"wins":141},"GB2-06":{"draws":31,"losses":231,"wins":170},"GB2-07":{"draws":0,"losses":220,"wins":198},"GB2-08":{"draws":292,"losses":102,"wins":30}},"per_game_match_totals_tracks":{"medium":{"GB2-02":{"draws":51,"losses":4,"wins":1},"GB2-03":{"draws":26,"losses":15,"wins":19},"GB2-04":{"draws":78,"losses":38,"wins":10},"GB2-05":{"draws":0,"losses":111,"wins":85},"GB2-06":{"draws":9,"losses":108,"wins":65},"GB2-07":{"draws":0,"losses":96,"wins":70},"GB2-08":{"draws":48,"losses":77,"wins":21}},"none":{"GB2-01":{"draws":92,"losses":103,"wins":83},"GB2-02":{"draws":114,"losses":5,"wins":1},"GB2-03":{"draws":83,"losses":66,"wins":49},"GB2-04":{"draws":67,"losses":27,"wins":26},"GB2-05":{"draws":0,"losses":172,"wins":56},"GB2-06":{"draws":22,"losses":123,"wins":105},"GB2-07":{"draws":0,"losses":124,"wins":128},"GB2-08":{"draws":244,"losses":25,"wins":9}}},"per_game_raw_elo_tracks":{"medium":{"GB2-02":1485.2658829829716,"GB2-03":1500.648879874152,"GB2-04":1426.817538672456,"GB2-05":1442.8691016822452,"GB2-06":1360.7633259115487,"GB2-07":1428.6835123650214,"GB2-08":1398.6641089407344},"none":{"GB2-01":1407.3980802647104,"GB2-02":1470.8238680319553,"GB2-03":1402.7986598115863,"GB2-04":1595.8397934807497,"GB2-05":1131.6573902393625,"GB2-06":1459.3729776380346,"GB2-07":1449.751951341211,"GB2-08":1421.369819758583}},"per_game_tracks":{"medium":{"GB2-02":15.558477194480595,"GB2-03":35.172389071472274,"GB2-04":11.347553349665287,"GB2-05":37.8518501101937,"GB2-06":36.49351604319952,"GB2-07":37.721339092090396,"GB2-08":21.450319954890443},"none":{"GB2-01":35.772634831663424,"GB2-02":20.765351621675194,"GB2-03":25.99213047697091,"GB2-04":48.45429450824968,"GB2-05":13.789037064172394,"GB2-06":48.14506340139004,"GB2-07":42.11567729374995,"GB2-08":28.390406342527847}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":26.003153051999846,"none":31.84698682175468},"reasoning_agg":{"medium":{"max":37.8518501101937,"mean":26.003153051999846,"min":11.347553349665287},"none":{"max":48.45429450824968,"mean":31.84698682175468,"min":13.789037064172394}},"reasoning_labels":{"highest":"Setting not tested","medium":"Enabled","none":"None"},"reasoning_settings":{"balanced":"enabled","baseline":"none"},"score_diagnostics":{"ceiling_score":48.45429450824968,"reasoning_variance":5.843833769754834},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":37.8518501101937,"expected_score":26.0352756543206,"reliability_score":58.2795089059441,"uncertainty_avg":41.7204910940559,"uncertainty_penalty":0.03212260232075437},"none":{"ceiling_score":48.45429450824968,"expected_score":36.24802406166466,"reliability_score":98.19547111444498,"uncertainty_avg":1.8045288855550132,"uncertainty_penalty":4.401037239909979}}},{"codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":20},"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.11219570000000001,"mean":0.0607572625,"median":0.060057275,"min":0.02174195,"recorded_attempt_count":20,"run_count":8,"total":0.4860581},"medium":{"admitted_cell_count":4,"cell_count":8,"cost_basis_counts":{"provider_reported":19},"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.0711619,"mean":0.039345212500000004,"median":0.033877925,"min":0.02387735,"recorded_attempt_count":19,"run_count":8,"total":0.3147617},"none":{"admitted_cell_count":4,"cell_count":8,"cost_basis_counts":{"provider_reported":20},"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.03772852,"mean":0.024905897500000003,"median":0.026095300000000002,"min":0.00984735,"recorded_attempt_count":20,"run_count":8,"total":0.19924718}},"codegen_cost_usd":{"admitted_cell_count":13,"cell_count":24,"cost_basis_counts":{"provider_reported":59},"evidence_basis":"Provider-reported","failed_cell_count":11,"max":0.11219570000000001,"mean":0.0416694575,"median":0.033877925,"min":0.00984735,"recorded_attempt_count":59,"run_count":24,"total":1.00006698},"codegen_latency_ms":{"attempt_count":59,"max_ms":511905,"mean_ms":204675.625,"min_ms":73907,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":20,"max_ms":511905,"mean_ms":284845.75,"min_ms":132388,"run_count":8},"medium":{"attempt_count":19,"max_ms":302393,"mean_ms":201389.625,"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":59,"output_max":93362,"output_mean":33067.75,"output_min":6729,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":20,"output_max":93362,"output_mean":49316.75,"output_min":16213,"run_count":8},"medium":{"attempt_count":19,"output_max":59186,"output_mean":30987.25,"output_min":18109,"run_count":8},"none":{"attempt_count":20,"output_max":28972,"output_mean":18899.25,"output_min":6729,"run_count":8}},"display_name":"Step 3.7 Flash","economics":{"all":40.61723844369942,"highest":28.683163448529363,"medium":34.82089217872514,"none":36.94089777477116},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":59,"finish_reasons":["stop"],"indexed_attempts":59,"output_token_observations":59,"reasoning_token_observations":20,"total_output_tokens":793626,"total_reasoning_output_tokens":89090,"total_visible_output_tokens":62104,"visible_token_observations":20},"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":"stop","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":"9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999","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":4,"evaluated_cells":8,"failed_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04"],"first_pass_admitted":3,"first_pass_rate":0.375,"model_code_failure_rate":0.5,"model_code_failures":4,"repaired_admitted":1,"repaired_rate":0.125},"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":"2026-08-05T05:41:59Z","match_totals_all":{"draws":351,"losses":688,"wins":430},"match_totals_tracks":{"highest":{"draws":101,"losses":347,"wins":181},"medium":{"draws":183,"losses":186,"wins":117},"none":{"draws":67,"losses":155,"wins":132}},"model_slug":"stepfun-step-3-7-flash","overall":{"max":53.50967288140359,"mean":28.615857137245154,"min":13.030258973366303},"per_game":{"GB2-01":13.030258973366303,"GB2-05":40.06000231216052,"GB2-06":37.06130479180287,"GB2-07":30.214369480459318,"GB2-08":23.049881684857795},"per_game_all":{"GB2-05":40.252192534111686,"GB2-06":40.98228435328715},"per_game_match_totals_all":{"GB2-01":{"draws":10,"losses":83,"wins":19},"GB2-02":{"draws":96,"losses":9,"wins":1},"GB2-04":{"draws":85,"losses":14,"wins":13},"GB2-05":{"draws":0,"losses":190,"wins":160},"GB2-06":{"draws":8,"losses":197,"wins":135},"GB2-07":{"draws":0,"losses":140,"wins":97},"GB2-08":{"draws":152,"losses":55,"wins":5}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":10,"losses":83,"wins":19},"GB2-05":{"draws":0,"losses":67,"wins":67},"GB2-06":{"draws":3,"losses":75,"wins":44},"GB2-07":{"draws":0,"losses":89,"wins":46},"GB2-08":{"draws":88,"losses":33,"wins":5}},"medium":{"GB2-02":{"draws":96,"losses":9,"wins":1},"GB2-04":{"draws":85,"losses":14,"wins":13},"GB2-05":{"draws":0,"losses":77,"wins":63},"GB2-06":{"draws":2,"losses":86,"wins":40}},"none":{"GB2-05":{"draws":0,"losses":46,"wins":30},"GB2-06":{"draws":3,"losses":36,"wins":51},"GB2-07":{"draws":0,"losses":51,"wins":51},"GB2-08":{"draws":64,"losses":22,"wins":0}}},"per_game_raw_elo_all":{"GB2-05":1462.0994420011118,"GB2-06":1397.002888482141},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1191.341446805984,"GB2-05":1459.5233581127313,"GB2-06":1357.7423100535907,"GB2-07":1328.6689853530577,"GB2-08":1391.141283069378},"medium":{"GB2-02":1485.6693600787999,"GB2-04":1527.4642993530238,"GB2-05":1534.4801116415908,"GB2-06":1292.7411627604797},"none":{"GB2-05":1392.2948562490126,"GB2-06":1540.5251926323524,"GB2-07":1425.2617719734535,"GB2-08":1413.6511322068186}},"per_game_tracks":{"highest":{"GB2-01":13.030258973366303,"GB2-05":40.06000231216052,"GB2-06":37.06130479180287,"GB2-07":30.214369480459318,"GB2-08":23.049881684857795},"medium":{"GB2-02":23.408407905328904,"GB2-04":35.99073310635768,"GB2-05":47.50855231655898,"GB2-06":32.375875386655},"none":{"GB2-05":33.188022973615546,"GB2-06":53.50967288140359,"GB2-07":37.895583637620526,"GB2-08":23.170311606444997}},"provider_color":"#F59E0B","provider_company":"StepFun","provider_key":"stepfun","provider_text_color":"#1f1300","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":25.503339487650393,"medium":29.280763409026072,"none":31.063468515058986},"reasoning_agg":{"highest":{"max":40.06000231216052,"mean":25.503339487650393,"min":13.030258973366303},"medium":{"max":47.50855231655898,"mean":29.280763409026072,"min":23.408407905328904},"none":{"max":53.50967288140359,"mean":31.063468515058986,"min":23.170311606444997}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"baseline":"low"},"score_diagnostics":{"ceiling_score":53.50967288140359,"expected_score":34.76423620651212,"reasoning_variance":5.560129027408593,"reliability_score":82.50308499485823,"uncertainty_avg":17.496915005141773,"uncertainty_penalty":6.148379069266969},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":40.06000231216052,"expected_score":13.619092855651829,"reliability_score":80.82996159151539,"uncertainty_avg":19.17003840848462,"uncertainty_penalty":-11.884246631998565},"medium":{"ceiling_score":47.50855231655898,"expected_score":36.41696425973522,"reliability_score":97.96364670306394,"uncertainty_avg":2.0363532969360576,"uncertainty_penalty":7.136200850709145},"none":{"ceiling_score":53.50967288140359,"expected_score":39.64242421746892,"reliability_score":63.99834697018921,"uncertainty_avg":36.00165302981079,"uncertainty_penalty":8.578955702409935}}},{"codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":9,"cell_count":8,"cost_basis_counts":{"provider_reported":35},"evidence_basis":"Provider-reported","failed_cell_count":7,"max":0.0456916,"mean":0.031545040625,"median":0.035551075,"min":0.01864685,"recorded_attempt_count":35,"run_count":16,"total":0.50472065},"medium":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":21},"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.065385,"mean":0.03551179375,"median":0.032728425,"min":0.0200767,"recorded_attempt_count":21,"run_count":9,"total":0.3177278}},"codegen_cost_usd":{"admitted_cell_count":14,"cell_count":16,"cost_basis_counts":{"provider_reported":56},"evidence_basis":"Provider-reported","failed_cell_count":11,"max":0.065385,"mean":0.0335284171875,"median":0.033685425,"min":0.01864685,"recorded_attempt_count":56,"run_count":25,"total":0.82244845},"codegen_latency_ms":{"attempt_count":56,"max_ms":622714,"mean_ms":85345.36,"min_ms":23604,"run_count":25},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":35,"max_ms":622714,"mean_ms":94544.1875,"min_ms":23604,"run_count":16},"medium":{"attempt_count":21,"max_ms":124322,"mean_ms":68991.88888888889,"min_ms":25332,"run_count":9}},"codegen_output_tokens":{"attempt_count":56,"output_max":17712,"output_mean":7782.6,"output_min":2728,"run_count":25},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":35,"output_max":17712,"output_mean":7793.4375,"output_min":2728,"run_count":16},"medium":{"attempt_count":21,"output_max":13873,"output_mean":7763.333333333333,"output_min":4525,"run_count":9}},"display_name":"Nemotron 3 Ultra 550B A55B","economics":{"all":37.59262070761077,"highest":26.514173359772816,"medium":34.03587215566226,"none":32.9209508641027},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":56,"finish_reasons":["error","length","stop"],"indexed_attempts":56,"output_token_observations":56,"total_output_tokens":194565},"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":"mixed","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":"9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999","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":"2026-08-05T04:29:54Z","match_totals_all":{"draws":891,"losses":864,"wins":504},"match_totals_tracks":{"highest":{"draws":441,"losses":403,"wins":195},"medium":{"draws":222,"losses":207,"wins":149},"none":{"draws":228,"losses":254,"wins":160}},"model_slug":"nvidia-nemotron-3-ultra-550b-a55b","overall":{"max":61.2479202482627,"mean":28.422476382747316,"min":12.693314222369741},"per_game":{"GB2-01":29.278226848010597,"GB2-02":16.83981461551393,"GB2-04":16.419946190834704,"GB2-05":35.48028584036205,"GB2-06":38.91324033511728,"GB2-08":22.15352632879835},"per_game_all":{"GB2-01":44.31853594921632,"GB2-06":43.10263678389902,"GB2-08":25.356689389716962},"per_game_match_totals_all":{"GB2-01":{"draws":69,"losses":153,"wins":112},"GB2-02":{"draws":263,"losses":24,"wins":5},"GB2-03":{"draws":52,"losses":12,"wins":4},"GB2-04":{"draws":144,"losses":32,"wins":14},"GB2-05":{"draws":0,"losses":193,"wins":173},"GB2-06":{"draws":15,"losses":174,"wins":124},"GB2-07":{"draws":0,"losses":161,"wins":41},"GB2-08":{"draws":348,"losses":115,"wins":31}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":29,"losses":61,"wins":24},"GB2-02":{"draws":165,"losses":19,"wins":4},"GB2-04":{"draws":80,"losses":24,"wins":6},"GB2-05":{"draws":0,"losses":158,"wins":108},"GB2-06":{"draws":7,"losses":70,"wins":32},"GB2-08":{"draws":160,"losses":71,"wins":21}},"medium":{"GB2-01":{"draws":24,"losses":39,"wins":55},"GB2-02":{"draws":98,"losses":5,"wins":1},"GB2-06":{"draws":8,"losses":46,"wins":58},"GB2-07":{"draws":0,"losses":80,"wins":26},"GB2-08":{"draws":92,"losses":37,"wins":9}},"none":{"GB2-01":{"draws":16,"losses":53,"wins":33},"GB2-03":{"draws":52,"losses":12,"wins":4},"GB2-04":{"draws":64,"losses":8,"wins":8},"GB2-05":{"draws":0,"losses":35,"wins":65},"GB2-06":{"draws":0,"losses":58,"wins":34},"GB2-07":{"draws":0,"losses":81,"wins":15},"GB2-08":{"draws":96,"losses":7,"wins":1}}},"per_game_raw_elo_all":{"GB2-01":1504.9165158673284,"GB2-06":1414.9869966237818,"GB2-08":1401.9988682121987},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1359.0482856713095,"GB2-02":1473.8733711729035,"GB2-04":1434.0958174926009,"GB2-05":1404.6797930025884,"GB2-06":1380.5860385894107,"GB2-08":1383.232126813642},"medium":{"GB2-01":1566.3794692670535,"GB2-02":1457.9978015411527,"GB2-06":1599.4018687999608,"GB2-07":1136.958953317386,"GB2-08":1404.8948685173345},"none":{"GB2-01":1589.3217926636212,"GB2-03":1401.2542607455403,"GB2-04":1502.923140293816,"GB2-05":1611.682762884176,"GB2-06":1264.9730824819735,"GB2-07":1123.552445089051,"GB2-08":1417.8696093056199}},"per_game_tracks":{"highest":{"GB2-01":29.278226848010597,"GB2-02":16.83981461551393,"GB2-04":16.419946190834704,"GB2-05":35.48028584036205,"GB2-06":38.91324033511728,"GB2-08":22.15352632879835},"medium":{"GB2-01":50.86269605014598,"GB2-02":17.498660025504904,"GB2-06":61.2479202482627,"GB2-07":14.05665305055863,"GB2-08":26.513431403839135},"none":{"GB2-01":52.814684949492396,"GB2-03":24.603816053425483,"GB2-04":30.378827209357606,"GB2-05":53.4061534092432,"GB2-06":29.146749768317104,"GB2-07":12.693314222369741,"GB2-08":27.4031104365134}},"provider_color":"#76B900","provider_company":"NVIDIA","provider_key":"nvidia","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":22.96194768990786,"medium":29.384530594231386,"none":32.9209508641027},"reasoning_agg":{"highest":{"max":38.91324033511728,"mean":22.96194768990786,"min":16.419946190834704},"medium":{"max":61.2479202482627,"mean":29.384530594231386,"min":14.05665305055863},"none":{"max":53.4061534092432,"mean":32.9209508641027,"min":12.693314222369741}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":61.2479202482627,"expected_score":29.01291912551952,"reasoning_variance":9.95900317419484,"reliability_score":90.01657707694744,"uncertainty_avg":9.983422923052553,"uncertainty_penalty":0.5904427427722041},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":38.91324033511728,"expected_score":14.915382546510505,"reliability_score":77.46323068002413,"uncertainty_avg":22.53676931997587,"uncertainty_penalty":-8.046565143397354},"medium":{"ceiling_score":61.2479202482627,"expected_score":29.544906374206413,"reliability_score":96.99944072593995,"uncertainty_avg":3.0005592740600537,"uncertainty_penalty":0.16037577997502694},"none":{"ceiling_score":53.4061534092432,"expected_score":33.58107977912953,"reliability_score":91.43904254888812,"uncertainty_avg":8.560957451111877,"uncertainty_penalty":0.6601289150268315}}},{"codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":19},"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.01660212,"mean":0.008820586750000001,"median":0.007023681,"min":0.00271606,"recorded_attempt_count":19,"run_count":8,"total":0.07056469400000001},"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":0.0011302579999999999,"recorded_attempt_count":16,"run_count":8,"total":0.019725259999999998},"none":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.0032939400000000004,"mean":0.0016413085000000001,"median":0.0014119655,"min":0.00045831,"recorded_attempt_count":13,"run_count":8,"total":0.013130468}},"codegen_cost_usd":{"admitted_cell_count":19,"cell_count":24,"cost_basis_counts":{"provider_reported":48},"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.01660212,"mean":0.00430918425,"median":0.0025298300000000003,"min":0.00045831,"recorded_attempt_count":48,"run_count":24,"total":0.10342042200000003},"codegen_latency_ms":{"attempt_count":48,"max_ms":622759,"mean_ms":232922.5,"min_ms":19833,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":19,"max_ms":622759,"mean_ms":483202.0,"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":48,"output_max":43929,"output_mean":12519.625,"output_min":1331,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":19,"output_max":43929,"output_mean":28964.5,"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":30.76172930530861,"highest":31.34390555147243,"medium":31.58613741833025,"none":24.79487793327039},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":48,"finish_reasons":["error","stop"],"indexed_attempts":48,"output_token_observations":48,"reasoning_token_observations":13,"total_output_tokens":300471,"total_reasoning_output_tokens":2697,"total_visible_output_tokens":20666,"visible_token_observations":13},"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":"mixed","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":"9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999","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":7,"evaluated_cells":8,"failed_game_aliases":["GB2-02"],"first_pass_admitted":5,"first_pass_rate":0.625,"model_code_failure_rate":0.125,"model_code_failures":1,"repaired_admitted":2,"repaired_rate":0.25},"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":"2026-08-05T05:11:31Z","match_totals_all":{"draws":755,"losses":823,"wins":438},"match_totals_tracks":{"highest":{"draws":218,"losses":194,"wins":134},"medium":{"draws":377,"losses":280,"wins":174},"none":{"draws":160,"losses":349,"wins":130}},"model_slug":"openai-gpt-oss-120b","overall":{"max":64.6891432709365,"mean":27.466345546443296,"min":9.425383107713568},"per_game":{"GB2-02":10.34354662706081,"GB2-04":23.47104312016287,"GB2-06":64.6891432709365,"GB2-07":36.45926297584206,"GB2-08":21.756531763359927},"per_game_all":{"GB2-04":19.451853023675326,"GB2-06":47.880362531293315,"GB2-08":24.952972360957187},"per_game_match_totals_all":{"GB2-01":{"draws":55,"losses":110,"wins":57},"GB2-02":{"draws":176,"losses":20,"wins":4},"GB2-03":{"draws":93,"losses":47,"wins":20},"GB2-04":{"draws":188,"losses":68,"wins":32},"GB2-05":{"draws":0,"losses":151,"wins":95},"GB2-06":{"draws":8,"losses":187,"wins":147},"GB2-07":{"draws":0,"losses":152,"wins":62},"GB2-08":{"draws":235,"losses":88,"wins":21}},"per_game_match_totals_tracks":{"highest":{"GB2-02":{"draws":81,"losses":15,"wins":0},"GB2-04":{"draws":53,"losses":26,"wins":23},"GB2-06":{"draws":6,"losses":40,"wins":62},"GB2-07":{"draws":0,"losses":79,"wins":41},"GB2-08":{"draws":78,"losses":34,"wins":8}},"medium":{"GB2-01":{"draws":31,"losses":53,"wins":34},"GB2-02":{"draws":95,"losses":5,"wins":4},"GB2-03":{"draws":52,"losses":19,"wins":13},"GB2-04":{"draws":99,"losses":13,"wins":4},"GB2-05":{"draws":0,"losses":72,"wins":64},"GB2-06":{"draws":1,"losses":88,"wins":46},"GB2-08":{"draws":99,"losses":30,"wins":9}},"none":{"GB2-01":{"draws":24,"losses":57,"wins":23},"GB2-03":{"draws":41,"losses":28,"wins":7},"GB2-04":{"draws":36,"losses":29,"wins":5},"GB2-05":{"draws":0,"losses":79,"wins":31},"GB2-06":{"draws":1,"losses":59,"wins":39},"GB2-07":{"draws":0,"losses":73,"wins":21},"GB2-08":{"draws":58,"losses":24,"wins":4}}},"per_game_raw_elo_all":{"GB2-04":1451.8775562247265,"GB2-06":1470.949284599541,"GB2-08":1410.0957223950363},"per_game_raw_elo_tracks":{"highest":{"GB2-02":1442.1938068693948,"GB2-04":1475.9882412604513,"GB2-06":1652.6573877546402,"GB2-07":1402.2791878007524,"GB2-08":1381.5144800797461},"medium":{"GB2-01":1445.4577652758578,"GB2-02":1478.2394028782717,"GB2-03":1405.1218657893382,"GB2-04":1467.9697022578662,"GB2-05":1482.5598725581976,"GB2-06":1344.5848235187086,"GB2-08":1420.861164888524},"none":{"GB2-01":1350.834157637065,"GB2-03":1401.2594736718875,"GB2-04":1411.6747251558618,"GB2-05":1291.0038555913918,"GB2-06":1415.605642525274,"GB2-07":1256.5767702858623,"GB2-08":1427.9115222168389}},"per_game_tracks":{"highest":{"GB2-02":10.34354662706081,"GB2-04":23.47104312016287,"GB2-06":64.6891432709365,"GB2-07":36.45926297584206,"GB2-08":21.756531763359927},"medium":{"GB2-01":39.175972926108116,"GB2-02":21.765095786368434,"GB2-03":25.840176236683952,"GB2-04":25.459132843149533,"GB2-05":43.16059564656367,"GB2-06":37.38276681114314,"GB2-08":28.31922167829491},"none":{"GB2-01":27.947576637723415,"GB2-03":21.457791809431576,"GB2-04":9.425383107713568,"GB2-05":25.543257483194672,"GB2-06":41.569177511800305,"GB2-07":22.83779534181248,"GB2-08":24.78316364121671}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":27.869110936194055,"medium":30.54910799192781,"none":23.980817711208037},"reasoning_agg":{"highest":{"max":64.6891432709365,"mean":27.869110936194055,"min":10.34354662706081},"medium":{"max":43.16059564656367,"mean":30.54910799192781,"min":21.765095786368434},"none":{"max":41.569177511800305,"mean":23.980817711208037,"min":9.425383107713568}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"baseline":"low"},"score_diagnostics":{"ceiling_score":64.6891432709365,"expected_score":23.488659409983978,"reasoning_variance":6.568290280719772,"reliability_score":77.91161235573864,"uncertainty_avg":22.088387644261356,"uncertainty_penalty":-3.977686136459319},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":64.6891432709365,"expected_score":20.95299136957535,"reliability_score":75.68638337813996,"uncertainty_avg":24.313616621860042,"uncertainty_penalty":-6.916119566618704},"medium":{"ceiling_score":43.16059564656367,"expected_score":25.71086853444923,"reliability_score":97.13034867062804,"uncertainty_avg":2.869651329371957,"uncertainty_penalty":-4.838239457478579},"none":{"ceiling_score":41.569177511800305,"expected_score":22.93383458472146,"reliability_score":64.02434574458584,"uncertainty_avg":35.97565425541415,"uncertainty_penalty":-1.0469831264865768}}},{"codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":9,"cell_count":8,"cost_basis_counts":{"provider_reported":53},"evidence_basis":"Provider-reported","failed_cell_count":7,"max":0.302804525,"mean":0.259828169375,"median":0.2529231275,"min":0.22308452,"recorded_attempt_count":53,"run_count":16,"total":4.15725071},"medium":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":53},"evidence_basis":"Provider-reported","failed_cell_count":10,"max":0.11839474,"mean":0.07845433000000002,"median":0.08046371000000001,"min":0.036046930000000005,"recorded_attempt_count":53,"run_count":16,"total":1.2552692799999998},"none":{"admitted_cell_count":12,"cell_count":8,"cost_basis_counts":{"provider_reported":39},"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.0721503,"mean":0.03677837187500001,"median":0.0324098875,"min":0.01945095,"recorded_attempt_count":39,"run_count":16,"total":0.5884539500000001}},"codegen_cost_usd":{"admitted_cell_count":27,"cell_count":24,"cost_basis_counts":{"provider_reported":145},"evidence_basis":"Provider-reported","failed_cell_count":21,"max":0.302804525,"mean":0.12502029041666668,"median":0.082332765,"min":0.01945095,"recorded_attempt_count":145,"run_count":48,"total":6.000973940000001},"codegen_latency_ms":{"attempt_count":145,"max_ms":712912,"mean_ms":234062.20833333334,"min_ms":20774,"run_count":48},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":53,"max_ms":712912,"mean_ms":506639.625,"min_ms":278552,"run_count":16},"medium":{"attempt_count":53,"max_ms":476873,"mean_ms":144633.375,"min_ms":47325,"run_count":16},"none":{"attempt_count":39,"max_ms":118093,"mean_ms":50913.625,"min_ms":20774,"run_count":16}},"codegen_output_tokens":{"attempt_count":145,"output_max":80000,"output_mean":25786.458333333332,"output_min":1372,"run_count":48},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":53,"output_max":80000,"output_mean":58672.9375,"output_min":35008,"run_count":16},"medium":{"attempt_count":53,"output_max":32558,"output_mean":14052.75,"output_min":3762,"run_count":16},"none":{"attempt_count":39,"output_max":11313,"output_mean":4633.6875,"output_min":1372,"run_count":16}},"display_name":"Inkling","economics":{"all":30.840066687416172,"highest":26.89883327152712,"medium":31.819704194896556,"none":34.48501987666433},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":145,"finish_reasons":["length","stop"],"indexed_attempts":145,"output_token_observations":145,"reasoning_token_observations":102,"total_output_tokens":1237750,"total_reasoning_output_tokens":697293,"total_visible_output_tokens":161414,"visible_token_observations":99},"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":"mixed","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":"9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999","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":16,"failed_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-05","GB2-06","GB2-07","GB2-08"],"first_pass_admitted":5,"first_pass_rate":0.3125,"model_code_failure_rate":0.625,"model_code_failures":10,"repaired_admitted":1,"repaired_rate":0.0625},"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":9,"evaluated_cells":16,"failed_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-06","GB2-07","GB2-08"],"first_pass_admitted":4,"first_pass_rate":0.25,"model_code_failure_rate":0.4375,"model_code_failures":7,"repaired_admitted":5,"repaired_rate":0.3125}},"id":"thinkingmachines/inkling","is_recent_addition":false,"last_measured_at":"2026-08-05T05:41:54Z","match_totals_all":{"draws":813,"losses":1156,"wins":689},"match_totals_tracks":{"highest":{"draws":214,"losses":352,"wins":140},"medium":{"draws":131,"losses":235,"wins":125},"none":{"draws":468,"losses":569,"wins":424}},"model_slug":"thinkingmachines-inkling","overall":{"max":62.96894118841835,"mean":26.762421399241273,"min":14.327060935420919},"per_game":{"GB2-01":27.54179636147906,"GB2-02":14.327060935420919,"GB2-03":31.12774530392546,"GB2-04":23.71090838679187,"GB2-05":21.28831645151227,"GB2-06":50.38530962978662,"GB2-07":28.228737245304664,"GB2-08":18.58079185799611},"per_game_all":{"GB2-01":26.123747482919658,"GB2-03":43.72028750432667,"GB2-04":25.88657746368486,"GB2-05":26.890243696367445,"GB2-07":26.627795080406674,"GB2-08":35.79174889679175},"per_game_match_totals_all":{"GB2-01":{"draws":154,"losses":193,"wins":58},"GB2-02":{"draws":165,"losses":14,"wins":3},"GB2-03":{"draws":121,"losses":77,"wins":98},"GB2-04":{"draws":236,"losses":57,"wins":53},"GB2-05":{"draws":0,"losses":373,"wins":189},"GB2-06":{"draws":4,"losses":111,"wins":99},"GB2-07":{"draws":0,"losses":217,"wins":97},"GB2-08":{"draws":133,"losses":114,"wins":92}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":35,"losses":26,"wins":7},"GB2-02":{"draws":59,"losses":4,"wins":1},"GB2-03":{"draws":17,"losses":12,"wins":9},"GB2-04":{"draws":38,"losses":15,"wins":21},"GB2-05":{"draws":0,"losses":120,"wins":36},"GB2-06":{"draws":3,"losses":45,"wins":38},"GB2-07":{"draws":0,"losses":81,"wins":25},"GB2-08":{"draws":62,"losses":49,"wins":3}},"medium":{"GB2-01":{"draws":15,"losses":29,"wins":16},"GB2-03":{"draws":10,"losses":21,"wins":31},"GB2-04":{"draws":45,"losses":4,"wins":5},"GB2-05":{"draws":0,"losses":98,"wins":54},"GB2-07":{"draws":0,"losses":67,"wins":15},"GB2-08":{"draws":61,"losses":16,"wins":4}},"none":{"GB2-01":{"draws":104,"losses":138,"wins":35},"GB2-02":{"draws":106,"losses":10,"wins":2},"GB2-03":{"draws":94,"losses":44,"wins":58},"GB2-04":{"draws":153,"losses":38,"wins":27},"GB2-05":{"draws":0,"losses":155,"wins":99},"GB2-06":{"draws":1,"losses":66,"wins":61},"GB2-07":{"draws":0,"losses":69,"wins":57},"GB2-08":{"draws":10,"losses":49,"wins":85}}},"per_game_raw_elo_all":{"GB2-01":1324.8911766296044,"GB2-03":1548.1455368935713,"GB2-04":1488.9277192297006,"GB2-05":1296.1950427011432,"GB2-07":1285.3759087031485,"GB2-08":1497.0731353496624},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1356.7856369791552,"GB2-02":1474.4301694661972,"GB2-03":1492.6289635368048,"GB2-04":1495.7663160414843,"GB2-05":1248.8221416706815,"GB2-06":1509.0877615675836,"GB2-07":1315.0784435685223,"GB2-08":1355.6468603917838},"medium":{"GB2-01":1394.4793311113017,"GB2-03":1637.788138173864,"GB2-04":1498.810743470332,"GB2-05":1295.4437942097927,"GB2-07":1190.757908767719,"GB2-08":1409.0575438734552},"none":{"GB2-01":1223.4085617983565,"GB2-02":1498.7314778179798,"GB2-03":1514.0195089700449,"GB2-04":1472.2060981772852,"GB2-05":1344.3191922229553,"GB2-06":1326.421769500473,"GB2-07":1350.2913737732042,"GB2-08":1726.5150017837482}},"per_game_tracks":{"highest":{"GB2-01":27.54179636147906,"GB2-02":14.327060935420919,"GB2-03":31.12774530392546,"GB2-04":23.71090838679187,"GB2-05":21.28831645151227,"GB2-06":50.38530962978662,"GB2-07":28.228737245304664,"GB2-08":18.58079185799611},"medium":{"GB2-01":32.84315271799331,"GB2-03":58.14658525183732,"GB2-04":27.944136333040866,"GB2-05":27.78924812766465,"GB2-07":18.369589094882354,"GB2-08":25.825513643960814},"none":{"GB2-01":17.986293369286603,"GB2-02":26.58345519069338,"GB2-03":41.88653195721722,"GB2-04":26.004687671221845,"GB2-05":31.593166509925418,"GB2-06":35.572024225518824,"GB2-07":33.285058901033004,"GB2-08":62.96894118841835}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":23.295072945304565,"medium":24.90026418896294,"none":32.09192706345631},"reasoning_agg":{"highest":{"max":50.38530962978662,"mean":23.295072945304565,"min":14.327060935420919},"medium":{"max":58.14658525183732,"mean":24.90026418896294,"min":18.369589094882354},"none":{"max":62.96894118841835,"mean":32.09192706345631,"min":17.986293369286603}},"reasoning_labels":{"highest":"Max","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"max"},"score_diagnostics":{"ceiling_score":62.96894118841835,"expected_score":30.066714380392497,"reasoning_variance":8.796854118151746,"reliability_score":80.49558253061858,"uncertainty_avg":19.50441746938142,"uncertainty_penalty":3.3042929811512245},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":50.38530962978662,"expected_score":16.44804444920455,"reliability_score":58.54905420921306,"uncertainty_avg":41.45094579078694,"uncertainty_penalty":-6.847028496100016},"medium":{"ceiling_score":58.14658525183732,"expected_score":31.542966656102653,"reliability_score":85.70326698668136,"uncertainty_avg":14.296733013318642,"uncertainty_penalty":6.6427024671397135},"none":{"ceiling_score":62.96894118841835,"expected_score":40.3207319214053,"reliability_score":98.25962647422786,"uncertainty_avg":1.7403735257721413,"uncertainty_penalty":8.228804857948987}}},{"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":0.10247140625000001,"median":0.113468875,"min":0.061553000000000004,"recorded_attempt_count":17,"run_count":8,"total":0.81977125},"none":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":36},"evidence_basis":"Provider-reported","failed_cell_count":9,"max":0.215758025,"mean":0.16162675,"median":0.1594081875,"min":0.098579625,"recorded_attempt_count":36,"run_count":16,"total":2.5860279999999998}},"codegen_cost_usd":{"admitted_cell_count":12,"cell_count":16,"cost_basis_counts":{"provider_reported":53},"evidence_basis":"Provider-reported","failed_cell_count":12,"max":0.215758025,"mean":0.132049078125,"median":0.1281735,"min":0.061553000000000004,"recorded_attempt_count":53,"run_count":24,"total":3.40579925},"codegen_latency_ms":{"attempt_count":53,"max_ms":1200477,"mean_ms":895711.875,"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":36,"max_ms":1200477,"mean_ms":932489.0,"min_ms":390884,"run_count":16}},"codegen_output_tokens":{"attempt_count":53,"output_max":142709,"output_mean":109998.5,"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":36,"output_max":142709,"output_mean":117464.375,"output_min":55627,"run_count":16}},"display_name":"Nex N2 Pro","economics":{"medium":23.578339590965378,"none":32.49225562048957},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":53,"finish_reasons":["length","stop"],"indexed_attempts":53,"output_token_observations":53,"total_output_tokens":2639964},"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":"mixed","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":"9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999","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":"2026-08-05T05:35:20Z","match_totals_all":{"draws":431,"losses":603,"wins":356},"match_totals_tracks":{"medium":{"draws":71,"losses":362,"wins":157},"none":{"draws":360,"losses":241,"wins":199}},"model_slug":"nex-agi-nex-n2-pro","overall":{"max":59.67122908962842,"mean":23.69500431162519,"min":3.5186261065286026},"per_game_match_totals_all":{"GB2-02":{"draws":92,"losses":13,"wins":5},"GB2-03":{"draws":96,"losses":58,"wins":26},"GB2-04":{"draws":101,"losses":9,"wins":6},"GB2-05":{"draws":0,"losses":149,"wins":105},"GB2-06":{"draws":14,"losses":158,"wins":54},"GB2-07":{"draws":0,"losses":106,"wins":150},"GB2-08":{"draws":128,"losses":110,"wins":10}},"per_game_match_totals_tracks":{"medium":{"GB2-03":{"draws":43,"losses":35,"wins":16},"GB2-05":{"draws":0,"losses":87,"wins":41},"GB2-06":{"draws":12,"losses":81,"wins":25},"GB2-07":{"draws":0,"losses":70,"wins":66},"GB2-08":{"draws":16,"losses":89,"wins":9}},"none":{"GB2-02":{"draws":92,"losses":13,"wins":5},"GB2-03":{"draws":53,"losses":23,"wins":10},"GB2-04":{"draws":101,"losses":9,"wins":6},"GB2-05":{"draws":0,"losses":62,"wins":64},"GB2-06":{"draws":2,"losses":77,"wins":29},"GB2-07":{"draws":0,"losses":36,"wins":84},"GB2-08":{"draws":112,"losses":21,"wins":1}}},"per_game_raw_elo_tracks":{"medium":{"GB2-03":1408.4812698372175,"GB2-05":1279.0180447312632,"GB2-06":1236.8582485470383,"GB2-07":1436.4833878281063,"GB2-08":1221.5615690949933},"none":{"GB2-02":1456.370338353978,"GB2-03":1386.1018350385903,"GB2-04":1477.005582006335,"GB2-05":1501.8798297824787,"GB2-06":1252.718659169334,"GB2-07":1648.2632211454757,"GB2-08":1411.3766557322458}},"per_game_tracks":{"medium":{"GB2-03":24.26550399898632,"GB2-05":24.956093569257188,"GB2-06":25.357692904131554,"GB2-07":39.79378137592323,"GB2-08":3.5186261065286026},"none":{"GB2-02":17.38109358780758,"GB2-03":23.18896644366903,"GB2-04":27.076279916551638,"GB2-05":44.653927467729666,"GB2-06":28.28420303224434,"GB2-07":59.67122908962842,"GB2-08":27.19008980579632}},"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":20.964437908759642,"none":26.42557071449074},"reasoning_agg":{"medium":{"max":39.79378137592323,"mean":20.964437908759642,"min":3.5186261065286026},"none":{"max":59.67122908962842,"mean":26.42557071449074,"min":17.38109358780758}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":59.67122908962842,"reasoning_variance":5.461132805731097},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":39.79378137592323,"expected_score":18.178270973879336,"reliability_score":77.89857593004386,"uncertainty_avg":22.101424069956135,"uncertainty_penalty":-2.786166934880306},"none":{"ceiling_score":59.67122908962842,"expected_score":31.508565233401583,"reliability_score":96.78539599028203,"uncertainty_avg":3.2146040097179776,"uncertainty_penalty":5.082994518910844}}},{"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":30},"evidence_basis":"Provider-reported","failed_cell_count":11,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":30,"run_count":16,"total":0.0}},"codegen_cost_usd":{"admitted_cell_count":11,"cell_count":16,"cost_basis_counts":{"provider_reported":45},"evidence_basis":"Provider-reported","failed_cell_count":13,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":45,"run_count":24,"total":0.0},"codegen_latency_ms":{"attempt_count":45,"max_ms":905283,"mean_ms":194374.625,"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":30,"max_ms":62079,"mean_ms":37002.75,"min_ms":21975,"run_count":16}},"codegen_output_tokens":{"attempt_count":45,"output_max":52275,"output_mean":12297.333333333334,"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":30,"output_max":6330,"output_mean":3393.0625,"output_min":1733,"run_count":16}},"display_name":"North Mini Code","economics":{"medium":29.640975194339735,"none":25.618760741182353},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":45,"finish_reasons":["stop"],"indexed_attempts":45,"output_token_observations":45,"total_output_tokens":295136},"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":"stop","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":"unknown_legacy","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999","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":"2026-08-05T05:19:01Z","match_totals_all":{"draws":471,"losses":610,"wins":337},"match_totals_tracks":{"medium":{"draws":239,"losses":300,"wins":227},"none":{"draws":232,"losses":310,"wins":110}},"model_slug":"cohere-north-mini-code","overall":{"max":45.91779335384322,"mean":23.36926343486995,"min":19.154491325362542},"per_game_match_totals_all":{"GB2-01":{"draws":116,"losses":128,"wins":30},"GB2-03":{"draws":36,"losses":31,"wins":13},"GB2-04":{"draws":104,"losses":19,"wins":9},"GB2-05":{"draws":0,"losses":65,"wins":89},"GB2-06":{"draws":1,"losses":88,"wins":37},"GB2-07":{"draws":0,"losses":225,"wins":155},"GB2-08":{"draws":214,"losses":54,"wins":4}},"per_game_match_totals_tracks":{"medium":{"GB2-03":{"draws":36,"losses":31,"wins":13},"GB2-04":{"draws":104,"losses":19,"wins":9},"GB2-05":{"draws":0,"losses":65,"wins":89},"GB2-06":{"draws":1,"losses":88,"wins":37},"GB2-07":{"draws":0,"losses":69,"wins":79},"GB2-08":{"draws":98,"losses":28,"wins":0}},"none":{"GB2-01":{"draws":116,"losses":128,"wins":30},"GB2-07":{"draws":0,"losses":156,"wins":76},"GB2-08":{"draws":116,"losses":26,"wins":4}}},"per_game_raw_elo_tracks":{"medium":{"GB2-03":1389.16540861595,"GB2-04":1457.701938811887,"GB2-05":1527.9643907366299,"GB2-06":1263.978424801378,"GB2-07":1457.7290822266407,"GB2-08":1361.4513228516012},"none":{"GB2-01":1269.590378771029,"GB2-07":1276.7241426466258,"GB2-08":1415.5203475276332}},"per_game_tracks":{"medium":{"GB2-03":20.815666165261234,"GB2-04":21.44671790523425,"GB2-05":45.91779335384322,"GB2-06":28.167965147210907,"GB2-07":41.83692106824891,"GB2-08":19.660787526239893},"none":{"GB2-01":22.417196747929975,"GB2-07":26.618036428605613,"GB2-08":27.82104904701147}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":27.584035544377357,"none":19.154491325362542},"reasoning_agg":{"medium":{"max":45.91779335384322,"mean":27.584035544377357,"min":19.660787526239893},"none":{"max":27.82104904701147,"mean":19.154491325362542,"min":22.417196747929975}},"reasoning_labels":{"highest":"Setting not tested","medium":"Setting not tested","none":"Setting not tested"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":45.91779335384322,"reasoning_variance":8.429544219014815},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":45.91779335384322,"expected_score":26.196286029551114,"reliability_score":79.89320227431948,"uncertainty_avg":20.106797725680526,"uncertainty_penalty":-1.3877495148262433},"none":{"ceiling_score":27.82104904701147,"expected_score":18.87297372823018,"reliability_score":98.94598823215051,"uncertainty_avg":1.0540117678494882,"uncertainty_penalty":-0.281517597132364}}},{"codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":19},"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.0422995,"mean":0.027492531250000004,"median":0.025548,"min":0.0204145,"recorded_attempt_count":19,"run_count":8,"total":0.21994025},"medium":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":18},"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0149315,"mean":0.0101355,"median":0.010566625,"min":0.00402875,"recorded_attempt_count":18,"run_count":8,"total":0.08108399999999999}},"codegen_cost_usd":{"admitted_cell_count":11,"cell_count":16,"cost_basis_counts":{"provider_reported":37},"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.0422995,"mean":0.018814015625,"median":0.017673,"min":0.00402875,"recorded_attempt_count":37,"run_count":16,"total":0.30102425},"codegen_latency_ms":{"attempt_count":37,"max_ms":98448,"mean_ms":43627.1875,"min_ms":14244,"run_count":16},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":19,"max_ms":98448,"mean_ms":63383.0,"min_ms":47134,"run_count":8},"medium":{"attempt_count":18,"max_ms":33720,"mean_ms":23871.375,"min_ms":14244,"run_count":8}},"codegen_output_tokens":{"attempt_count":37,"output_max":22966,"output_mean":9375.1875,"output_min":1329,"run_count":16},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":19,"output_max":22966,"output_mean":14948.625,"output_min":10673,"run_count":8},"medium":{"attempt_count":18,"output_max":5938,"output_mean":3801.75,"output_min":1329,"run_count":8}},"display_name":"Gemini 3.1 Flash Lite","economics":{"all":22.87406327710457,"highest":25.333116741442588,"medium":27.748939787173324,"none":17.319128239553702},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":37,"finish_reasons":["stop"],"indexed_attempts":37,"output_token_observations":37,"total_output_tokens":150003},"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":"stop","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":"9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999","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":"2026-08-05T05:18:42Z","match_totals_all":{"draws":484,"losses":965,"wins":386},"match_totals_tracks":{"highest":{"draws":169,"losses":321,"wins":111},"medium":{"draws":203,"losses":377,"wins":182},"none":{"draws":112,"losses":267,"wins":93}},"model_slug":"google-gemini-3-1-flash-lite","overall":{"max":41.949273557550775,"mean":21.88903546237954,"min":0.0},"per_game":{"GB2-04":21.40588512859002,"GB2-05":16.34618234965383,"GB2-06":28.463532438701474,"GB2-07":38.95277949062936,"GB2-08":21.497204299638256},"per_game_all":{"GB2-05":16.878773670354416,"GB2-06":37.20355086618398,"GB2-07":14.53986529477533},"per_game_match_totals_all":{"GB2-01":{"draws":91,"losses":94,"wins":39},"GB2-02":{"draws":75,"losses":3,"wins":2},"GB2-04":{"draws":177,"losses":29,"wins":18},"GB2-05":{"draws":0,"losses":253,"wins":77},"GB2-06":{"draws":2,"losses":214,"wins":137},"GB2-07":{"draws":0,"losses":273,"wins":63},"GB2-08":{"draws":139,"losses":99,"wins":50}},"per_game_match_totals_tracks":{"highest":{"GB2-04":{"draws":84,"losses":22,"wins":8},"GB2-05":{"draws":0,"losses":95,"wins":19},"GB2-06":{"draws":0,"losses":79,"wins":34},"GB2-07":{"draws":0,"losses":86,"wins":42},"GB2-08":{"draws":85,"losses":39,"wins":8}},"medium":{"GB2-01":{"draws":56,"losses":44,"wins":26},"GB2-04":{"draws":93,"losses":7,"wins":10},"GB2-05":{"draws":0,"losses":76,"wins":36},"GB2-06":{"draws":0,"losses":93,"wins":53},"GB2-07":{"draws":0,"losses":97,"wins":15},"GB2-08":{"draws":54,"losses":60,"wins":42}},"none":{"GB2-01":{"draws":35,"losses":50,"wins":13},"GB2-02":{"draws":75,"losses":3,"wins":2},"GB2-05":{"draws":0,"losses":82,"wins":22},"GB2-06":{"draws":2,"losses":42,"wins":50},"GB2-07":{"draws":0,"losses":90,"wins":6}}},"per_game_raw_elo_all":{"GB2-05":1174.7545002020693,"GB2-06":1350.6693723399078,"GB2-07":1146.4023895526732},"per_game_raw_elo_tracks":{"highest":{"GB2-04":1460.9173614142396,"GB2-05":1177.988284897323,"GB2-06":1269.0832415302018,"GB2-07":1428.3878157010372,"GB2-08":1375.8979860686834},"medium":{"GB2-01":1449.9213024915678,"GB2-04":1489.9113112622058,"GB2-05":1234.4309794055496,"GB2-06":1391.3978131432787,"GB2-07":1030.1908334918917,"GB2-08":1421.8590805710878},"none":{"GB2-01":1181.758735531149,"GB2-02":1475.4985994938952,"GB2-05":1111.844236303335,"GB2-06":1391.5270623462427,"GB2-07":980.6285194650904}},"per_game_tracks":{"highest":{"GB2-04":21.40588512859002,"GB2-05":16.34618234965383,"GB2-06":28.463532438701474,"GB2-07":38.95277949062936,"GB2-08":21.497204299638256},"medium":{"GB2-01":39.72079315957007,"GB2-04":29.209493257271063,"GB2-05":22.28851435525645,"GB2-06":41.949273557550775,"GB2-07":4.666816393696632,"GB2-08":28.65874799969496},"none":{"GB2-01":13.34873652645807,"GB2-02":20.047433762857775,"GB2-05":12.001624306152966,"GB2-06":41.19784660229971,"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":22.524679946709842,"medium":25.823298200875076,"none":17.319128239553702},"reasoning_agg":{"highest":{"max":38.95277949062936,"mean":22.524679946709842,"min":16.34618234965383},"medium":{"max":41.949273557550775,"mean":25.823298200875076,"min":4.666816393696632},"none":{"max":41.19784660229971,"mean":17.319128239553702,"min":0.0}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":41.949273557550775,"expected_score":14.19336817197854,"reasoning_variance":8.504169961321374,"reliability_score":90.0943749292959,"uncertainty_avg":9.905625070704104,"uncertainty_penalty":-7.6956672904009995},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":38.95277949062936,"expected_score":9.668745314170744,"reliability_score":79.44200491249327,"uncertainty_avg":20.55799508750672,"uncertainty_penalty":-12.855934632539098},"medium":{"ceiling_score":41.949273557550775,"expected_score":24.234564522129773,"reliability_score":98.18369798386827,"uncertainty_avg":1.8163020161317271,"uncertainty_penalty":-1.588733678745303},"none":{"ceiling_score":41.19784660229971,"expected_score":13.683282600273628,"reliability_score":92.4162648346237,"uncertainty_avg":7.5837351653762965,"uncertainty_penalty":-3.635845639280074}}},{"codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":52},"evidence_basis":"Provider-reported","failed_cell_count":9,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":52,"run_count":16,"total":0.0},"none":{"admitted_cell_count":10,"cell_count":8,"cost_basis_counts":{"provider_reported":40},"evidence_basis":"Provider-reported","failed_cell_count":6,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":40,"run_count":16,"total":0.0}},"codegen_cost_usd":{"admitted_cell_count":16,"cell_count":16,"cost_basis_counts":{"provider_reported":92},"evidence_basis":"Provider-reported","failed_cell_count":15,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":92,"run_count":32,"total":0.0},"codegen_latency_ms":{"attempt_count":93,"max_ms":410978,"mean_ms":158095.9375,"min_ms":18717,"run_count":32},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":53,"max_ms":410978,"mean_ms":269539.1875,"min_ms":161500,"run_count":16},"none":{"attempt_count":40,"max_ms":90441,"mean_ms":46652.6875,"min_ms":18717,"run_count":16}},"codegen_output_tokens":{"attempt_count":92,"output_max":92074,"output_mean":33594.125,"output_min":2036,"run_count":32},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":52,"output_max":92074,"output_mean":60516.0,"output_min":20000,"run_count":16},"none":{"attempt_count":40,"output_max":17378,"output_mean":6672.25,"output_min":2036,"run_count":16}},"display_name":"Ling 3.0 Flash","economics":{"medium":25.282192800215764,"none":25.94707410067487},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":93,"finish_reasons":["length","stop","unknown"],"indexed_attempts":94,"output_token_observations":93,"reasoning_token_observations":65,"total_output_tokens":1075012,"total_reasoning_output_tokens":626571,"total_visible_output_tokens":109787,"visible_token_observations":55},"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":"unknown_legacy","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999","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":15,"failed_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-05","GB2-06","GB2-08"],"first_pass_admitted":1,"first_pass_rate":0.06666666666666667,"infra_excluded_game_aliases":["GB2-05"],"infra_failures_excluded":1,"model_code_failure_rate":0.6,"model_code_failures":9,"repaired_admitted":5,"repaired_rate":0.3333333333333333},"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":"2026-08-05T05:41:59Z","match_totals_all":{"draws":972,"losses":765,"wins":379},"match_totals_tracks":{"medium":{"draws":147,"losses":255,"wins":136},"none":{"draws":825,"losses":510,"wins":243}},"model_slug":"inclusionai-ling-3-0-flash","overall":{"max":43.52220457729294,"mean":21.588380852524416,"min":11.744571555937974},"per_game_match_totals_all":{"GB2-01":{"draws":132,"losses":180,"wins":118},"GB2-02":{"draws":196,"losses":17,"wins":3},"GB2-03":{"draws":106,"losses":97,"wins":49},"GB2-04":{"draws":204,"losses":25,"wins":13},"GB2-06":{"draws":5,"losses":293,"wins":96},"GB2-07":{"draws":0,"losses":113,"wins":95},"GB2-08":{"draws":329,"losses":40,"wins":5}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":18,"losses":41,"wins":5},"GB2-02":{"draws":54,"losses":10,"wins":2},"GB2-04":{"draws":74,"losses":18,"wins":6},"GB2-06":{"draws":1,"losses":73,"wins":28},"GB2-07":{"draws":0,"losses":113,"wins":95}},"none":{"GB2-01":{"draws":114,"losses":139,"wins":113},"GB2-02":{"draws":142,"losses":7,"wins":1},"GB2-03":{"draws":106,"losses":97,"wins":49},"GB2-04":{"draws":130,"losses":7,"wins":7},"GB2-06":{"draws":4,"losses":220,"wins":68},"GB2-08":{"draws":329,"losses":40,"wins":5}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1338.2033465124364,"GB2-02":1460.4630623113085,"GB2-04":1441.8532139778922,"GB2-06":1270.5021457048715,"GB2-07":1485.2957378785},"none":{"GB2-01":1436.404832296831,"GB2-02":1459.0305995079593,"GB2-03":1371.5273535246738,"GB2-04":1494.684673413206,"GB2-06":1130.0626959606705,"GB2-08":1407.8180210731284}},"per_game_tracks":{"medium":{"GB2-01":25.615070134982144,"GB2-02":11.744571555937974,"GB2-04":17.203835010961818,"GB2-06":28.325282721903957,"GB2-07":43.52220457729294},"none":{"GB2-01":38.9946317420071,"GB2-02":19.08311558138147,"GB2-03":22.15995528948202,"GB2-04":30.91354977203183,"GB2-06":17.149445622957767,"GB2-08":27.381746596189068}},"provider_color":"#1677FF","provider_company":"InclusionAI","provider_key":"inclusionai","provider_text_color":"#f8fbff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":20.10618789305667,"none":23.070573811992162},"reasoning_agg":{"medium":{"max":43.52220457729294,"mean":20.10618789305667,"min":11.744571555937974},"none":{"max":38.9946317420071,"mean":23.070573811992162,"min":17.149445622957767}},"reasoning_labels":{"highest":"Setting not tested","medium":"Setting not tested","none":"Setting not tested"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":43.52220457729294,"reasoning_variance":2.9643859189354913},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":43.52220457729294,"expected_score":19.794324092511058,"reliability_score":67.14682213962466,"uncertainty_avg":32.85317786037534,"uncertainty_penalty":-0.3118638005456127},"none":{"ceiling_score":38.9946317420071,"expected_score":19.27140964080414,"reliability_score":99.89634126114359,"uncertainty_avg":0.10365873885641586,"uncertainty_penalty":-3.7991641711880213}}},{"codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":4,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.3927285,"mean":0.1902770625,"median":0.16804049999999998,"min":0.08751,"recorded_attempt_count":14,"run_count":9,"total":1.914945},"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":0.042994687499999996,"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":28},"evidence_basis":"Provider-reported","failed_cell_count":9,"max":0.3927285,"mean":0.116635875,"median":0.0747585,"min":0.0223935,"recorded_attempt_count":28,"run_count":17,"total":2.2589025},"codegen_latency_ms":{"attempt_count":28,"max_ms":776640,"mean_ms":218770.82352941178,"min_ms":28440,"run_count":17},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":14,"max_ms":776640,"mean_ms":364061.1111111111,"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":28,"output_max":52664,"output_mean":15146.29411764706,"output_min":1452,"run_count":17},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":14,"output_max":52664,"output_mean":25839.666666666668,"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":21.467686926657944,"none":30.201677973699127},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":28,"finish_reasons":["stop"],"indexed_attempts":28,"output_token_observations":28,"total_output_tokens":257487},"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":"stop","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":"9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999","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":"2026-08-05T05:02:41Z","match_totals_all":{"draws":159,"losses":549,"wins":261},"match_totals_tracks":{"highest":{"draws":29,"losses":332,"wins":109},"none":{"draws":130,"losses":217,"wins":152}},"model_slug":"mistralai-mistral-medium-3-5","overall":{"max":37.07858798158563,"mean":21.46238785938686,"min":15.89051825604416},"per_game":{"GB2-01":15.89051825604416,"GB2-05":21.668950001695563,"GB2-06":28.85019218818374,"GB2-07":19.461087260708307},"per_game_match_totals_all":{"GB2-01":{"draws":39,"losses":143,"wins":67},"GB2-05":{"draws":0,"losses":147,"wins":91},"GB2-06":{"draws":10,"losses":134,"wins":74},"GB2-07":{"draws":0,"losses":98,"wins":26},"GB2-08":{"draws":110,"losses":27,"wins":3}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":29,"losses":74,"wins":17},"GB2-05":{"draws":0,"losses":85,"wins":33},"GB2-06":{"draws":0,"losses":75,"wins":33},"GB2-07":{"draws":0,"losses":98,"wins":26}},"none":{"GB2-01":{"draws":10,"losses":69,"wins":50},"GB2-05":{"draws":0,"losses":62,"wins":58},"GB2-06":{"draws":10,"losses":59,"wins":41},"GB2-08":{"draws":110,"losses":27,"wins":3}}},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1219.0922738248978,"GB2-05":1241.2401742692932,"GB2-06":1274.548733487929,"GB2-07":1210.0225762192022},"none":{"GB2-01":1349.8251838934389,"GB2-05":1337.1021659225844,"GB2-06":1345.0460288080308,"GB2-08":1371.202537480436}},"per_game_tracks":{"highest":{"GB2-01":15.89051825604416,"GB2-05":21.668950001695563,"GB2-06":28.85019218818374,"GB2-07":19.461087260708307},"none":{"GB2-01":30.086613675695194,"GB2-05":30.911374561641104,"GB2-06":37.07858798158563,"GB2-08":22.730135675874582}},"provider_color":"#FF7000","provider_company":"Mistral","provider_key":"mistral","provider_text_color":"#fff8f3","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":17.528292976043055,"none":25.396482742730665},"reasoning_agg":{"highest":{"max":28.85019218818374,"mean":17.528292976043055,"min":15.89051825604416},"none":{"max":37.07858798158563,"mean":25.396482742730665,"min":22.730135675874582}},"reasoning_labels":{"highest":"High","medium":"Setting not tested","none":"None"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":37.07858798158563,"reasoning_variance":7.86818976668761},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":28.85019218818374,"expected_score":2.840602689126707,"reliability_score":78.68732431934882,"uncertainty_avg":21.31267568065119,"uncertainty_penalty":-14.687690286916348},"none":{"ceiling_score":37.07858798158563,"expected_score":23.086096703371624,"reliability_score":98.62116344811953,"uncertainty_avg":1.378836551880469,"uncertainty_penalty":-2.3103860393590416}}}],"public_release_id":"gb2-20260806-59b3356f5989","results_cut_id":"gb2-20260806-59b3356f5989","snapshot_id":"20260806_094024","suite_line_id":"gamebench2","suite_version":"2-known8-r3","version_display":"2026-08-06 09:40 UTC","versus_totals_all":{"claude-fable-5":{"claude-fable-5":{"draws":4,"losses":12,"wins":12},"claude-opus-4-5":{"draws":7,"losses":8,"wins":45},"claude-opus-4-8":{"draws":6,"losses":26,"wins":28},"claude-opus-5":{"draws":25,"losses":58,"wins":57},"claude-sonnet-5":{"draws":11,"losses":1,"wins":34},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":9},"deepseek/deepseek-v4-flash":{"draws":4,"losses":3,"wins":31},"deepseek/deepseek-v4-pro":{"draws":1,"losses":2,"wins":21},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":22},"google/gemini-3.5-flash":{"draws":10,"losses":10,"wins":28},"google/gemini-3.5-flash-lite":{"draws":1,"losses":0,"wins":7},"google/gemini-3.6-flash":{"draws":2,"losses":14,"wins":22},"google/gemma-4-31b-it":{"draws":1,"losses":1,"wins":8},"gpt-4.1":{"draws":2,"losses":2,"wins":0},"gpt-5":{"draws":2,"losses":2,"wins":34},"gpt-5.4":{"draws":8,"losses":28,"wins":30},"gpt-5.4-mini":{"draws":22,"losses":12,"wins":60},"gpt-5.4-nano":{"draws":13,"losses":18,"wins":99},"gpt-5.5":{"draws":8,"losses":22,"wins":24},"gpt-5.6-luna":{"draws":6,"losses":7,"wins":33},"gpt-5.6-sol":{"draws":13,"losses":20,"wins":41},"gpt-5.6-terra":{"draws":7,"losses":5,"wins":48},"meituan/longcat-2.0":{"draws":1,"losses":1,"wins":6},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":16},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":16},"moonshotai/kimi-k3":{"draws":2,"losses":0,"wins":18},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":14},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":1,"wins":27},"o3":{"draws":1,"losses":2,"wins":31},"openai/gpt-oss-120b":{"draws":4,"losses":1,"wins":19},"poolside/laguna-s-2.1":{"draws":0,"losses":6,"wins":4},"qwen/qwen3.7-max":{"draws":3,"losses":4,"wins":17},"qwen/qwen3.7-plus":{"draws":1,"losses":1,"wins":14},"stepfun/step-3.7-flash":{"draws":3,"losses":0,"wins":19},"tencent/hy3-preview":{"draws":1,"losses":5,"wins":20},"thinkingmachines/inkling":{"draws":4,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":15,"losses":23,"wins":58},"x-ai/grok-build-0.1":{"draws":2,"losses":3,"wins":11},"xiaomi/mimo-v2.5":{"draws":5,"losses":2,"wins":41},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":20},"z-ai/glm-5.2":{"draws":10,"losses":19,"wins":71}},"claude-opus-4-5":{"claude-fable-5":{"draws":7,"losses":45,"wins":8},"claude-opus-4-5":{"draws":38,"losses":29,"wins":29},"claude-opus-4-8":{"draws":17,"losses":52,"wins":25},"claude-opus-5":{"draws":35,"losses":170,"wins":27},"claude-sonnet-5":{"draws":49,"losses":43,"wins":30},"cohere/north-mini-code":{"draws":9,"losses":3,"wins":22},"deepseek/deepseek-v4-flash":{"draws":56,"losses":19,"wins":51},"deepseek/deepseek-v4-pro":{"draws":19,"losses":12,"wins":19},"google/gemini-3.1-flash-lite":{"draws":18,"losses":2,"wins":40},"google/gemini-3.5-flash":{"draws":18,"losses":22,"wins":16},"google/gemini-3.5-flash-lite":{"draws":47,"losses":23,"wins":42},"google/gemini-3.6-flash":{"draws":29,"losses":49,"wins":34},"google/gemma-4-31b-it":{"draws":11,"losses":14,"wins":13},"gpt-4.1":{"draws":12,"losses":7,"wins":3},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":25,"losses":20,"wins":21},"gpt-5.4":{"draws":28,"losses":37,"wins":25},"gpt-5.4-mini":{"draws":84,"losses":53,"wins":105},"gpt-5.4-nano":{"draws":83,"losses":60,"wins":109},"gpt-5.5":{"draws":31,"losses":33,"wins":24},"gpt-5.6-luna":{"draws":37,"losses":30,"wins":27},"gpt-5.6-sol":{"draws":27,"losses":54,"wins":15},"gpt-5.6-terra":{"draws":42,"losses":37,"wins":29},"inclusionai/ling-3.0-flash":{"draws":18,"losses":7,"wins":13},"meituan/longcat-2.0":{"draws":28,"losses":17,"wins":30},"minimax/minimax-m3":{"draws":11,"losses":7,"wins":28},"mistralai/mistral-medium-3-5":{"draws":4,"losses":0,"wins":20},"moonshotai/kimi-k2.7-code":{"draws":10,"losses":11,"wins":13},"moonshotai/kimi-k3":{"draws":45,"losses":75,"wins":36},"nex-agi/nex-n2-pro":{"draws":9,"losses":7,"wins":20},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":35,"losses":16,"wins":29},"o3":{"draws":18,"losses":30,"wins":58},"openai/gpt-oss-120b":{"draws":27,"losses":9,"wins":44},"poolside/laguna-s-2.1":{"draws":29,"losses":5,"wins":24},"qwen/qwen3.7-max":{"draws":22,"losses":14,"wins":28},"qwen/qwen3.7-plus":{"draws":23,"losses":11,"wins":18},"stepfun/step-3.7-flash":{"draws":14,"losses":10,"wins":36},"tencent/hy3-preview":{"draws":17,"losses":8,"wins":19},"thinkingmachines/inkling":{"draws":28,"losses":11,"wins":43},"x-ai/grok-4.5":{"draws":65,"losses":106,"wins":55},"x-ai/grok-build-0.1":{"draws":13,"losses":6,"wins":11},"xiaomi/mimo-v2.5":{"draws":62,"losses":33,"wins":55},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":21,"wins":21},"z-ai/glm-5.2":{"draws":67,"losses":91,"wins":90}},"claude-opus-4-8":{"claude-fable-5":{"draws":6,"losses":28,"wins":26},"claude-opus-4-5":{"draws":17,"losses":25,"wins":52},"claude-opus-4-8":{"draws":8,"losses":10,"wins":10},"claude-opus-5":{"draws":21,"losses":66,"wins":31},"claude-sonnet-5":{"draws":17,"losses":18,"wins":37},"cohere/north-mini-code":{"draws":7,"losses":2,"wins":15},"deepseek/deepseek-v4-flash":{"draws":25,"losses":12,"wins":53},"deepseek/deepseek-v4-pro":{"draws":11,"losses":12,"wins":23},"google/gemini-3.1-flash-lite":{"draws":9,"losses":4,"wins":27},"google/gemini-3.5-flash":{"draws":13,"losses":18,"wins":11},"google/gemini-3.5-flash-lite":{"draws":13,"losses":9,"wins":24},"google/gemini-3.6-flash":{"draws":19,"losses":27,"wins":16},"google/gemma-4-31b-it":{"draws":10,"losses":2,"wins":16},"gpt-4.1":{"draws":4,"losses":3,"wins":11},"gpt-5":{"draws":11,"losses":13,"wins":26},"gpt-5.4":{"draws":15,"losses":32,"wins":23},"gpt-5.4-mini":{"draws":56,"losses":39,"wins":83},"gpt-5.4-nano":{"draws":40,"losses":36,"wins":102},"gpt-5.5":{"draws":19,"losses":35,"wins":22},"gpt-5.6-luna":{"draws":17,"losses":19,"wins":26},"gpt-5.6-sol":{"draws":15,"losses":40,"wins":23},"gpt-5.6-terra":{"draws":22,"losses":17,"wins":27},"inclusionai/ling-3.0-flash":{"draws":18,"losses":0,"wins":4},"meituan/longcat-2.0":{"draws":8,"losses":7,"wins":17},"minimax/minimax-m3":{"draws":11,"losses":4,"wins":19},"mistralai/mistral-medium-3-5":{"draws":2,"losses":2,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":4,"wins":8},"moonshotai/kimi-k3":{"draws":16,"losses":23,"wins":15},"nex-agi/nex-n2-pro":{"draws":14,"losses":3,"wins":21},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":11,"wins":31},"o3":{"draws":4,"losses":6,"wins":34},"openai/gpt-oss-120b":{"draws":13,"losses":6,"wins":23},"poolside/laguna-s-2.1":{"draws":12,"losses":5,"wins":23},"qwen/qwen3.7-max":{"draws":12,"losses":11,"wins":17},"qwen/qwen3.7-plus":{"draws":12,"losses":6,"wins":20},"stepfun/step-3.7-flash":{"draws":7,"losses":8,"wins":21},"tencent/hy3-preview":{"draws":11,"losses":10,"wins":17},"thinkingmachines/inkling":{"draws":8,"losses":6,"wins":24},"x-ai/grok-4.5":{"draws":21,"losses":59,"wins":38},"x-ai/grok-build-0.1":{"draws":9,"losses":6,"wins":9},"xiaomi/mimo-v2.5":{"draws":38,"losses":12,"wins":46},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":11,"wins":18},"z-ai/glm-5.2":{"draws":46,"losses":49,"wins":81}},"claude-opus-5":{"claude-fable-5":{"draws":25,"losses":57,"wins":58},"claude-opus-4-5":{"draws":35,"losses":27,"wins":170},"claude-opus-4-8":{"draws":21,"losses":31,"wins":66},"claude-opus-5":{"draws":48,"losses":172,"wins":172},"claude-sonnet-5":{"draws":37,"losses":17,"wins":118},"cohere/north-mini-code":{"draws":4,"losses":2,"wins":20},"deepseek/deepseek-v4-flash":{"draws":16,"losses":8,"wins":74},"deepseek/deepseek-v4-pro":{"draws":6,"losses":3,"wins":55},"google/gemini-3.1-flash-lite":{"draws":4,"losses":1,"wins":27},"google/gemini-3.5-flash":{"draws":11,"losses":11,"wins":60},"google/gemini-3.5-flash-lite":{"draws":17,"losses":9,"wins":84},"google/gemini-3.6-flash":{"draws":14,"losses":33,"wins":99},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":20},"gpt-4.1":{"draws":10,"losses":2,"wins":41},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":10,"losses":5,"wins":51},"gpt-5.4":{"draws":23,"losses":48,"wins":83},"gpt-5.4-mini":{"draws":37,"losses":23,"wins":180},"gpt-5.4-nano":{"draws":32,"losses":27,"wins":143},"gpt-5.5":{"draws":21,"losses":33,"wins":94},"gpt-5.6-luna":{"draws":16,"losses":14,"wins":68},"gpt-5.6-sol":{"draws":29,"losses":35,"wins":122},"gpt-5.6-terra":{"draws":37,"losses":18,"wins":107},"inclusionai/ling-3.0-flash":{"draws":12,"losses":2,"wins":22},"meituan/longcat-2.0":{"draws":10,"losses":10,"wins":48},"minimax/minimax-m3":{"draws":3,"losses":4,"wins":33},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":1,"wins":29},"moonshotai/kimi-k3":{"draws":21,"losses":18,"wins":115},"nex-agi/nex-n2-pro":{"draws":0,"losses":1,"wins":15},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":0,"wins":43},"o3":{"draws":2,"losses":6,"wins":68},"openai/gpt-oss-120b":{"draws":4,"losses":3,"wins":21},"poolside/laguna-s-2.1":{"draws":8,"losses":8,"wins":66},"qwen/qwen3.7-max":{"draws":12,"losses":7,"wins":55},"qwen/qwen3.7-plus":{"draws":4,"losses":2,"wins":20},"stepfun/step-3.7-flash":{"draws":5,"losses":1,"wins":26},"tencent/hy3-preview":{"draws":11,"losses":7,"wins":48},"thinkingmachines/inkling":{"draws":9,"losses":11,"wins":52},"x-ai/grok-4.5":{"draws":31,"losses":60,"wins":165},"x-ai/grok-build-0.1":{"draws":6,"losses":2,"wins":10},"xiaomi/mimo-v2.5":{"draws":9,"losses":3,"wins":50},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":1,"wins":40},"z-ai/glm-5.2":{"draws":40,"losses":27,"wins":207}},"claude-sonnet-5":{"claude-fable-5":{"draws":11,"losses":34,"wins":1},"claude-opus-4-5":{"draws":49,"losses":30,"wins":43},"claude-opus-4-8":{"draws":17,"losses":37,"wins":18},"claude-opus-5":{"draws":37,"losses":118,"wins":17},"claude-sonnet-5":{"draws":24,"losses":20,"wins":20},"cohere/north-mini-code":{"draws":12,"losses":3,"wins":15},"deepseek/deepseek-v4-flash":{"draws":50,"losses":18,"wins":50},"deepseek/deepseek-v4-pro":{"draws":15,"losses":10,"wins":19},"google/gemini-3.1-flash-lite":{"draws":14,"losses":6,"wins":22},"google/gemini-3.5-flash":{"draws":21,"losses":15,"wins":16},"google/gemini-3.5-flash-lite":{"draws":34,"losses":15,"wins":27},"google/gemini-3.6-flash":{"draws":28,"losses":37,"wins":19},"google/gemma-4-31b-it":{"draws":11,"losses":4,"wins":9},"gpt-4.1":{"draws":9,"losses":12,"wins":15},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":24,"losses":20,"wins":18},"gpt-5.4":{"draws":27,"losses":38,"wins":9},"gpt-5.4-mini":{"draws":79,"losses":44,"wins":63},"gpt-5.4-nano":{"draws":76,"losses":41,"wins":57},"gpt-5.5":{"draws":29,"losses":23,"wins":18},"gpt-5.6-luna":{"draws":32,"losses":26,"wins":12},"gpt-5.6-sol":{"draws":14,"losses":49,"wins":17},"gpt-5.6-terra":{"draws":28,"losses":26,"wins":30},"inclusionai/ling-3.0-flash":{"draws":23,"losses":3,"wins":22},"meituan/longcat-2.0":{"draws":21,"losses":10,"wins":37},"minimax/minimax-m3":{"draws":11,"losses":7,"wins":16},"mistralai/mistral-medium-3-5":{"draws":2,"losses":6,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":6,"wins":8},"moonshotai/kimi-k3":{"draws":23,"losses":23,"wins":18},"nex-agi/nex-n2-pro":{"draws":8,"losses":7,"wins":19},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":38,"losses":15,"wins":25},"o3":{"draws":12,"losses":30,"wins":28},"openai/gpt-oss-120b":{"draws":20,"losses":7,"wins":17},"poolside/laguna-s-2.1":{"draws":24,"losses":10,"wins":26},"qwen/qwen3.7-max":{"draws":23,"losses":11,"wins":10},"qwen/qwen3.7-plus":{"draws":11,"losses":5,"wins":8},"stepfun/step-3.7-flash":{"draws":13,"losses":5,"wins":22},"tencent/hy3-preview":{"draws":16,"losses":10,"wins":12},"thinkingmachines/inkling":{"draws":27,"losses":9,"wins":28},"x-ai/grok-4.5":{"draws":33,"losses":51,"wins":22},"x-ai/grok-build-0.1":{"draws":9,"losses":1,"wins":14},"xiaomi/mimo-v2.5":{"draws":61,"losses":14,"wins":41},"xiaomi/mimo-v2.5-pro":{"draws":13,"losses":16,"wins":13},"z-ai/glm-5.2":{"draws":74,"losses":78,"wins":72}},"cohere/north-mini-code":{"claude-fable-5":{"draws":1,"losses":9,"wins":0},"claude-opus-4-5":{"draws":9,"losses":22,"wins":3},"claude-opus-4-8":{"draws":7,"losses":15,"wins":2},"claude-opus-5":{"draws":4,"losses":20,"wins":2},"claude-sonnet-5":{"draws":12,"losses":15,"wins":3},"cohere/north-mini-code":{"draws":2,"losses":7,"wins":7},"deepseek/deepseek-v4-flash":{"draws":27,"losses":19,"wins":32},"deepseek/deepseek-v4-pro":{"draws":6,"losses":10,"wins":2},"google/gemini-3.1-flash-lite":{"draws":6,"losses":13,"wins":13},"google/gemini-3.5-flash":{"draws":5,"losses":14,"wins":1},"google/gemini-3.5-flash-lite":{"draws":19,"losses":0,"wins":11},"google/gemini-3.6-flash":{"draws":12,"losses":14,"wins":6},"google/gemma-4-31b-it":{"draws":5,"losses":8,"wins":5},"gpt-4.1":{"draws":7,"losses":4,"wins":1},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":7,"losses":17,"wins":4},"gpt-5.4":{"draws":8,"losses":19,"wins":7},"gpt-5.4-mini":{"draws":30,"losses":36,"wins":20},"gpt-5.4-nano":{"draws":38,"losses":53,"wins":31},"gpt-5.5":{"draws":14,"losses":11,"wins":3},"gpt-5.6-luna":{"draws":5,"losses":7,"wins":16},"gpt-5.6-sol":{"draws":7,"losses":20,"wins":1},"gpt-5.6-terra":{"draws":7,"losses":21,"wins":4},"inclusionai/ling-3.0-flash":{"draws":18,"losses":10,"wins":6},"meituan/longcat-2.0":{"draws":22,"losses":18,"wins":8},"minimax/minimax-m3":{"draws":3,"losses":15,"wins":10},"mistralai/mistral-medium-3-5":{"draws":7,"losses":7,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":3,"wins":4},"moonshotai/kimi-k3":{"draws":8,"losses":18,"wins":8},"nex-agi/nex-n2-pro":{"draws":9,"losses":13,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":10,"wins":13},"o3":{"draws":12,"losses":6,"wins":4},"openai/gpt-oss-120b":{"draws":16,"losses":6,"wins":8},"poolside/laguna-s-2.1":{"draws":21,"losses":2,"wins":15},"qwen/qwen3.7-max":{"draws":9,"losses":17,"wins":4},"qwen/qwen3.7-plus":{"draws":7,"losses":14,"wins":9},"stepfun/step-3.7-flash":{"draws":4,"losses":11,"wins":3},"tencent/hy3-preview":{"draws":3,"losses":9,"wins":2},"thinkingmachines/inkling":{"draws":9,"losses":11,"wins":16},"x-ai/grok-4.5":{"draws":11,"losses":27,"wins":2},"x-ai/grok-build-0.1":{"draws":4,"losses":7,"wins":3},"xiaomi/mimo-v2.5":{"draws":27,"losses":24,"wins":15},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":11,"wins":6},"z-ai/glm-5.2":{"draws":26,"losses":17,"wins":13}},"deepseek/deepseek-v4-flash":{"claude-fable-5":{"draws":4,"losses":31,"wins":3},"claude-opus-4-5":{"draws":56,"losses":51,"wins":19},"claude-opus-4-8":{"draws":25,"losses":53,"wins":12},"claude-opus-5":{"draws":16,"losses":74,"wins":8},"claude-sonnet-5":{"draws":50,"losses":50,"wins":18},"cohere/north-mini-code":{"draws":27,"losses":32,"wins":19},"deepseek/deepseek-v4-flash":{"draws":90,"losses":103,"wins":103},"deepseek/deepseek-v4-pro":{"draws":29,"losses":46,"wins":19},"google/gemini-3.1-flash-lite":{"draws":30,"losses":38,"wins":50},"google/gemini-3.5-flash":{"draws":22,"losses":24,"wins":6},"google/gemini-3.5-flash-lite":{"draws":34,"losses":18,"wins":18},"google/gemini-3.6-flash":{"draws":37,"losses":37,"wins":12},"google/gemma-4-31b-it":{"draws":25,"losses":32,"wins":25},"gpt-4.1":{"draws":17,"losses":18,"wins":13},"gpt-4.1-nano":{"draws":0,"losses":1,"wins":1},"gpt-5":{"draws":21,"losses":28,"wins":5},"gpt-5.4":{"draws":39,"losses":51,"wins":16},"gpt-5.4-mini":{"draws":133,"losses":132,"wins":81},"gpt-5.4-nano":{"draws":142,"losses":87,"wins":117},"gpt-5.5":{"draws":40,"losses":51,"wins":3},"gpt-5.6-luna":{"draws":49,"losses":33,"wins":40},"gpt-5.6-sol":{"draws":16,"losses":69,"wins":15},"gpt-5.6-terra":{"draws":38,"losses":64,"wins":16},"inclusionai/ling-3.0-flash":{"draws":44,"losses":17,"wins":37},"meituan/longcat-2.0":{"draws":32,"losses":27,"wins":33},"minimax/minimax-m3":{"draws":19,"losses":33,"wins":26},"mistralai/mistral-medium-3-5":{"draws":13,"losses":28,"wins":35},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":7,"wins":4},"moonshotai/kimi-k3":{"draws":27,"losses":55,"wins":6},"nex-agi/nex-n2-pro":{"draws":30,"losses":37,"wins":25},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":60,"losses":32,"wins":38},"o3":{"draws":14,"losses":36,"wins":28},"openai/gpt-oss-120b":{"draws":36,"losses":36,"wins":24},"poolside/laguna-s-2.1":{"draws":33,"losses":30,"wins":15},"qwen/qwen3.7-max":{"draws":26,"losses":24,"wins":12},"qwen/qwen3.7-plus":{"draws":22,"losses":28,"wins":30},"stepfun/step-3.7-flash":{"draws":18,"losses":39,"wins":31},"tencent/hy3-preview":{"draws":35,"losses":34,"wins":23},"thinkingmachines/inkling":{"draws":34,"losses":35,"wins":35},"x-ai/grok-4.5":{"draws":21,"losses":68,"wins":15},"x-ai/grok-build-0.1":{"draws":16,"losses":11,"wins":9},"xiaomi/mimo-v2.5":{"draws":82,"losses":80,"wins":58},"xiaomi/mimo-v2.5-pro":{"draws":22,"losses":29,"wins":23},"z-ai/glm-5.2":{"draws":129,"losses":101,"wins":78}},"deepseek/deepseek-v4-pro":{"claude-fable-5":{"draws":1,"losses":21,"wins":2},"claude-opus-4-5":{"draws":19,"losses":19,"wins":12},"claude-opus-4-8":{"draws":11,"losses":23,"wins":12},"claude-opus-5":{"draws":6,"losses":55,"wins":3},"claude-sonnet-5":{"draws":15,"losses":19,"wins":10},"cohere/north-mini-code":{"draws":6,"losses":2,"wins":10},"deepseek/deepseek-v4-flash":{"draws":29,"losses":19,"wins":46},"deepseek/deepseek-v4-pro":{"draws":0,"losses":4,"wins":4},"google/gemini-3.1-flash-lite":{"draws":8,"losses":4,"wins":10},"google/gemini-3.5-flash":{"draws":2,"losses":8,"wins":4},"google/gemini-3.5-flash-lite":{"draws":14,"losses":6,"wins":14},"google/gemini-3.6-flash":{"draws":13,"losses":16,"wins":7},"google/gemma-4-31b-it":{"draws":7,"losses":3,"wins":10},"gpt-4.1":{"draws":6,"losses":9,"wins":3},"gpt-4.1-nano":{"draws":1,"losses":1,"wins":0},"gpt-5":{"draws":4,"losses":6,"wins":14},"gpt-5.4":{"draws":9,"losses":28,"wins":5},"gpt-5.4-mini":{"draws":38,"losses":25,"wins":43},"gpt-5.4-nano":{"draws":37,"losses":31,"wins":36},"gpt-5.5":{"draws":15,"losses":16,"wins":3},"gpt-5.6-luna":{"draws":16,"losses":14,"wins":14},"gpt-5.6-sol":{"draws":2,"losses":20,"wins":10},"gpt-5.6-terra":{"draws":17,"losses":17,"wins":10},"inclusionai/ling-3.0-flash":{"draws":14,"losses":4,"wins":12},"meituan/longcat-2.0":{"draws":5,"losses":7,"wins":16},"minimax/minimax-m3":{"draws":3,"losses":9,"wins":4},"mistralai/mistral-medium-3-5":{"draws":4,"losses":3,"wins":13},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":1,"wins":3},"moonshotai/kimi-k3":{"draws":6,"losses":21,"wins":7},"nex-agi/nex-n2-pro":{"draws":6,"losses":8,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":7,"wins":14},"o3":{"draws":11,"losses":15,"wins":16},"openai/gpt-oss-120b":{"draws":8,"losses":8,"wins":8},"poolside/laguna-s-2.1":{"draws":6,"losses":10,"wins":8},"qwen/qwen3.7-max":{"draws":11,"losses":6,"wins":11},"qwen/qwen3.7-plus":{"draws":6,"losses":0,"wins":8},"stepfun/step-3.7-flash":{"draws":6,"losses":3,"wins":13},"tencent/hy3-preview":{"draws":7,"losses":8,"wins":11},"thinkingmachines/inkling":{"draws":12,"losses":4,"wins":14},"x-ai/grok-4.5":{"draws":10,"losses":39,"wins":9},"x-ai/grok-build-0.1":{"draws":8,"losses":1,"wins":3},"xiaomi/mimo-v2.5":{"draws":16,"losses":11,"wins":25},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":6,"wins":7},"z-ai/glm-5.2":{"draws":29,"losses":33,"wins":50}},"google/gemini-3.1-flash-lite":{"claude-fable-5":{"draws":2,"losses":22,"wins":0},"claude-opus-4-5":{"draws":18,"losses":40,"wins":2},"claude-opus-4-8":{"draws":9,"losses":27,"wins":4},"claude-opus-5":{"draws":4,"losses":27,"wins":1},"claude-sonnet-5":{"draws":14,"losses":22,"wins":6},"cohere/north-mini-code":{"draws":6,"losses":13,"wins":13},"deepseek/deepseek-v4-flash":{"draws":30,"losses":50,"wins":38},"deepseek/deepseek-v4-pro":{"draws":8,"losses":10,"wins":4},"google/gemini-3.1-flash-lite":{"draws":0,"losses":12,"wins":12},"google/gemini-3.5-flash":{"draws":6,"losses":17,"wins":1},"google/gemini-3.5-flash-lite":{"draws":12,"losses":10,"wins":12},"google/gemini-3.6-flash":{"draws":6,"losses":17,"wins":1},"google/gemma-4-31b-it":{"draws":8,"losses":16,"wins":14},"gpt-4.1":{"draws":6,"losses":6,"wins":4},"gpt-5":{"draws":14,"losses":18,"wins":2},"gpt-5.4":{"draws":6,"losses":24,"wins":0},"gpt-5.4-mini":{"draws":34,"losses":73,"wins":21},"gpt-5.4-nano":{"draws":34,"losses":79,"wins":39},"gpt-5.5":{"draws":11,"losses":22,"wins":3},"gpt-5.6-luna":{"draws":15,"losses":22,"wins":15},"gpt-5.6-sol":{"draws":6,"losses":22,"wins":6},"gpt-5.6-terra":{"draws":8,"losses":25,"wins":5},"inclusionai/ling-3.0-flash":{"draws":9,"losses":8,"wins":13},"meituan/longcat-2.0":{"draws":10,"losses":24,"wins":16},"minimax/minimax-m3":{"draws":5,"losses":10,"wins":13},"mistralai/mistral-medium-3-5":{"draws":6,"losses":11,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":8,"wins":0},"moonshotai/kimi-k3":{"draws":5,"losses":8,"wins":1},"nex-agi/nex-n2-pro":{"draws":4,"losses":15,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":24,"wins":13},"o3":{"draws":10,"losses":24,"wins":2},"openai/gpt-oss-120b":{"draws":11,"losses":14,"wins":7},"poolside/laguna-s-2.1":{"draws":8,"losses":8,"wins":12},"qwen/qwen3.7-max":{"draws":9,"losses":10,"wins":5},"qwen/qwen3.7-plus":{"draws":9,"losses":17,"wins":6},"stepfun/step-3.7-flash":{"draws":6,"losses":19,"wins":5},"tencent/hy3-preview":{"draws":4,"losses":10,"wins":6},"thinkingmachines/inkling":{"draws":11,"losses":24,"wins":11},"x-ai/grok-4.5":{"draws":12,"losses":29,"wins":1},"x-ai/grok-build-0.1":{"draws":9,"losses":13,"wins":2},"xiaomi/mimo-v2.5":{"draws":35,"losses":42,"wins":25},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":19,"wins":2},"z-ai/glm-5.2":{"draws":37,"losses":54,"wins":17}},"google/gemini-3.5-flash":{"claude-fable-5":{"draws":10,"losses":28,"wins":10},"claude-opus-4-5":{"draws":18,"losses":16,"wins":22},"claude-opus-4-8":{"draws":13,"losses":11,"wins":18},"claude-opus-5":{"draws":11,"losses":60,"wins":11},"claude-sonnet-5":{"draws":21,"losses":16,"wins":15},"cohere/north-mini-code":{"draws":5,"losses":1,"wins":14},"deepseek/deepseek-v4-flash":{"draws":22,"losses":6,"wins":24},"deepseek/deepseek-v4-pro":{"draws":2,"losses":4,"wins":8},"google/gemini-3.1-flash-lite":{"draws":6,"losses":1,"wins":17},"google/gemini-3.5-flash":{"draws":4,"losses":4,"wins":4},"google/gemini-3.5-flash-lite":{"draws":8,"losses":4,"wins":14},"google/gemini-3.6-flash":{"draws":7,"losses":13,"wins":12},"google/gemma-4-31b-it":{"draws":3,"losses":6,"wins":7},"gpt-4.1":{"draws":2,"losses":2,"wins":6},"gpt-5":{"draws":8,"losses":8,"wins":18},"gpt-5.4":{"draws":15,"losses":17,"wins":10},"gpt-5.4-mini":{"draws":29,"losses":25,"wins":38},"gpt-5.4-nano":{"draws":29,"losses":24,"wins":45},"gpt-5.5":{"draws":11,"losses":21,"wins":16},"gpt-5.6-luna":{"draws":17,"losses":13,"wins":12},"gpt-5.6-sol":{"draws":12,"losses":21,"wins":11},"gpt-5.6-terra":{"draws":14,"losses":16,"wins":18},"inclusionai/ling-3.0-flash":{"draws":6,"losses":2,"wins":2},"meituan/longcat-2.0":{"draws":7,"losses":3,"wins":2},"minimax/minimax-m3":{"draws":5,"losses":1,"wins":12},"mistralai/mistral-medium-3-5":{"draws":4,"losses":0,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":6,"wins":4},"moonshotai/kimi-k3":{"draws":15,"losses":8,"wins":7},"nex-agi/nex-n2-pro":{"draws":4,"losses":4,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":3,"wins":20},"o3":{"draws":8,"losses":18,"wins":10},"openai/gpt-oss-120b":{"draws":13,"losses":5,"wins":12},"poolside/laguna-s-2.1":{"draws":10,"losses":7,"wins":7},"qwen/qwen3.7-max":{"draws":8,"losses":9,"wins":9},"qwen/qwen3.7-plus":{"draws":4,"losses":1,"wins":13},"stepfun/step-3.7-flash":{"draws":5,"losses":3,"wins":10},"tencent/hy3-preview":{"draws":4,"losses":2,"wins":10},"thinkingmachines/inkling":{"draws":10,"losses":4,"wins":18},"x-ai/grok-4.5":{"draws":11,"losses":24,"wins":29},"x-ai/grok-build-0.1":{"draws":8,"losses":1,"wins":9},"xiaomi/mimo-v2.5":{"draws":28,"losses":9,"wins":25},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":4,"wins":9},"z-ai/glm-5.2":{"draws":22,"losses":38,"wins":42}},"google/gemini-3.5-flash-lite":{"claude-fable-5":{"draws":1,"losses":7,"wins":0},"claude-opus-4-5":{"draws":47,"losses":42,"wins":23},"claude-opus-4-8":{"draws":13,"losses":24,"wins":9},"claude-opus-5":{"draws":17,"losses":84,"wins":9},"claude-sonnet-5":{"draws":34,"losses":27,"wins":15},"cohere/north-mini-code":{"draws":19,"losses":11,"wins":0},"deepseek/deepseek-v4-flash":{"draws":34,"losses":18,"wins":18},"deepseek/deepseek-v4-pro":{"draws":14,"losses":14,"wins":6},"google/gemini-3.1-flash-lite":{"draws":12,"losses":12,"wins":10},"google/gemini-3.5-flash":{"draws":8,"losses":14,"wins":4},"google/gemini-3.5-flash-lite":{"draws":82,"losses":81,"wins":81},"google/gemini-3.6-flash":{"draws":93,"losses":93,"wins":49},"google/gemma-4-31b-it":{"draws":7,"losses":15,"wins":4},"gpt-4.1":{"draws":6,"losses":6,"wins":10},"gpt-4.1-nano":{"draws":1,"losses":5,"wins":4},"gpt-5":{"draws":19,"losses":10,"wins":7},"gpt-5.4":{"draws":15,"losses":18,"wins":1},"gpt-5.4-mini":{"draws":63,"losses":59,"wins":28},"gpt-5.4-nano":{"draws":62,"losses":32,"wins":48},"gpt-5.5":{"draws":30,"losses":18,"wins":6},"gpt-5.6-luna":{"draws":25,"losses":13,"wins":6},"gpt-5.6-sol":{"draws":11,"losses":13,"wins":6},"gpt-5.6-terra":{"draws":26,"losses":17,"wins":7},"inclusionai/ling-3.0-flash":{"draws":50,"losses":15,"wins":39},"meituan/longcat-2.0":{"draws":38,"losses":47,"wins":54},"minimax/minimax-m3":{"draws":9,"losses":6,"wins":11},"mistralai/mistral-medium-3-5":{"draws":4,"losses":7,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":0,"wins":4},"moonshotai/kimi-k3":{"draws":99,"losses":133,"wins":52},"nex-agi/nex-n2-pro":{"draws":13,"losses":8,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":11,"wins":8},"o3":{"draws":27,"losses":105,"wins":50},"openai/gpt-oss-120b":{"draws":22,"losses":18,"wins":38},"poolside/laguna-s-2.1":{"draws":60,"losses":44,"wins":38},"qwen/qwen3.7-max":{"draws":7,"losses":4,"wins":7},"qwen/qwen3.7-plus":{"draws":12,"losses":9,"wins":3},"stepfun/step-3.7-flash":{"draws":11,"losses":25,"wins":18},"tencent/hy3-preview":{"draws":9,"losses":8,"wins":3},"thinkingmachines/inkling":{"draws":48,"losses":43,"wins":63},"x-ai/grok-4.5":{"draws":57,"losses":132,"wins":59},"x-ai/grok-build-0.1":{"draws":10,"losses":10,"wins":2},"xiaomi/mimo-v2.5":{"draws":11,"losses":17,"wins":12},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":9,"wins":11},"z-ai/glm-5.2":{"draws":33,"losses":30,"wins":17}},"google/gemini-3.6-flash":{"claude-fable-5":{"draws":2,"losses":22,"wins":14},"claude-opus-4-5":{"draws":29,"losses":34,"wins":49},"claude-opus-4-8":{"draws":19,"losses":16,"wins":27},"claude-opus-5":{"draws":14,"losses":99,"wins":33},"claude-sonnet-5":{"draws":28,"losses":19,"wins":37},"cohere/north-mini-code":{"draws":12,"losses":6,"wins":14},"deepseek/deepseek-v4-flash":{"draws":37,"losses":12,"wins":37},"deepseek/deepseek-v4-pro":{"draws":13,"losses":7,"wins":16},"google/gemini-3.1-flash-lite":{"draws":6,"losses":1,"wins":17},"google/gemini-3.5-flash":{"draws":7,"losses":12,"wins":13},"google/gemini-3.5-flash-lite":{"draws":93,"losses":49,"wins":93},"google/gemini-3.6-flash":{"draws":58,"losses":71,"wins":71},"google/gemma-4-31b-it":{"draws":10,"losses":9,"wins":7},"gpt-4.1":{"draws":9,"losses":4,"wins":7},"gpt-4.1-nano":{"draws":5,"losses":3,"wins":2},"gpt-5":{"draws":5,"losses":12,"wins":21},"gpt-5.4":{"draws":25,"losses":26,"wins":17},"gpt-5.4-mini":{"draws":56,"losses":30,"wins":63},"gpt-5.4-nano":{"draws":60,"losses":23,"wins":59},"gpt-5.5":{"draws":25,"losses":23,"wins":26},"gpt-5.6-luna":{"draws":24,"losses":16,"wins":30},"gpt-5.6-sol":{"draws":15,"losses":28,"wins":21},"gpt-5.6-terra":{"draws":21,"losses":19,"wins":30},"inclusionai/ling-3.0-flash":{"draws":67,"losses":19,"wins":46},"meituan/longcat-2.0":{"draws":45,"losses":28,"wins":59},"minimax/minimax-m3":{"draws":11,"losses":6,"wins":17},"mistralai/mistral-medium-3-5":{"draws":3,"losses":3,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":2,"wins":9},"moonshotai/kimi-k3":{"draws":70,"losses":120,"wins":136},"nex-agi/nex-n2-pro":{"draws":15,"losses":4,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":4,"wins":21},"o3":{"draws":30,"losses":56,"wins":76},"openai/gpt-oss-120b":{"draws":16,"losses":4,"wins":33},"poolside/laguna-s-2.1":{"draws":63,"losses":26,"wins":49},"qwen/qwen3.7-max":{"draws":6,"losses":3,"wins":21},"qwen/qwen3.7-plus":{"draws":12,"losses":3,"wins":21},"stepfun/step-3.7-flash":{"draws":5,"losses":4,"wins":22},"tencent/hy3-preview":{"draws":11,"losses":11,"wins":18},"thinkingmachines/inkling":{"draws":64,"losses":23,"wins":67},"x-ai/grok-4.5":{"draws":62,"losses":142,"wins":132},"x-ai/grok-build-0.1":{"draws":6,"losses":0,"wins":6},"xiaomi/mimo-v2.5":{"draws":20,"losses":11,"wins":17},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":5,"wins":16},"z-ai/glm-5.2":{"draws":27,"losses":22,"wins":35}},"google/gemma-4-31b-it":{"claude-fable-5":{"draws":1,"losses":8,"wins":1},"claude-opus-4-5":{"draws":11,"losses":13,"wins":14},"claude-opus-4-8":{"draws":10,"losses":16,"wins":2},"claude-opus-5":{"draws":4,"losses":20,"wins":0},"claude-sonnet-5":{"draws":11,"losses":9,"wins":4},"cohere/north-mini-code":{"draws":5,"losses":5,"wins":8},"deepseek/deepseek-v4-flash":{"draws":25,"losses":25,"wins":32},"deepseek/deepseek-v4-pro":{"draws":7,"losses":10,"wins":3},"google/gemini-3.1-flash-lite":{"draws":8,"losses":14,"wins":16},"google/gemini-3.5-flash":{"draws":3,"losses":7,"wins":6},"google/gemini-3.5-flash-lite":{"draws":7,"losses":4,"wins":15},"google/gemini-3.6-flash":{"draws":10,"losses":7,"wins":9},"google/gemma-4-31b-it":{"draws":4,"losses":4,"wins":4},"gpt-4.1":{"draws":5,"losses":3,"wins":2},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":3,"losses":8,"wins":3},"gpt-5.4":{"draws":5,"losses":13,"wins":4},"gpt-5.4-mini":{"draws":27,"losses":31,"wins":32},"gpt-5.4-nano":{"draws":19,"losses":35,"wins":38},"gpt-5.5":{"draws":7,"losses":11,"wins":2},"gpt-5.6-luna":{"draws":8,"losses":8,"wins":12},"gpt-5.6-sol":{"draws":8,"losses":16,"wins":2},"gpt-5.6-terra":{"draws":7,"losses":21,"wins":2},"inclusionai/ling-3.0-flash":{"draws":12,"losses":5,"wins":19},"meituan/longcat-2.0":{"draws":6,"losses":13,"wins":11},"minimax/minimax-m3":{"draws":6,"losses":12,"wins":8},"mistralai/mistral-medium-3-5":{"draws":3,"losses":8,"wins":9},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":10,"wins":0},"moonshotai/kimi-k3":{"draws":7,"losses":20,"wins":7},"nex-agi/nex-n2-pro":{"draws":4,"losses":9,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":7,"wins":13},"o3":{"draws":8,"losses":7,"wins":3},"openai/gpt-oss-120b":{"draws":9,"losses":4,"wins":13},"poolside/laguna-s-2.1":{"draws":4,"losses":9,"wins":11},"qwen/qwen3.7-max":{"draws":3,"losses":14,"wins":5},"qwen/qwen3.7-plus":{"draws":1,"losses":7,"wins":12},"stepfun/step-3.7-flash":{"draws":3,"losses":13,"wins":2},"tencent/hy3-preview":{"draws":7,"losses":7,"wins":4},"thinkingmachines/inkling":{"draws":4,"losses":10,"wins":14},"x-ai/grok-4.5":{"draws":8,"losses":20,"wins":2},"x-ai/grok-build-0.1":{"draws":7,"losses":8,"wins":5},"xiaomi/mimo-v2.5":{"draws":17,"losses":26,"wins":27},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":13,"wins":5},"z-ai/glm-5.2":{"draws":21,"losses":16,"wins":13}},"gpt-4.1":{"claude-fable-5":{"draws":2,"losses":0,"wins":2},"claude-opus-4-5":{"draws":12,"losses":3,"wins":7},"claude-opus-4-8":{"draws":4,"losses":11,"wins":3},"claude-opus-5":{"draws":10,"losses":41,"wins":2},"claude-sonnet-5":{"draws":9,"losses":15,"wins":12},"cohere/north-mini-code":{"draws":7,"losses":1,"wins":4},"deepseek/deepseek-v4-flash":{"draws":17,"losses":13,"wins":18},"deepseek/deepseek-v4-pro":{"draws":6,"losses":3,"wins":9},"google/gemini-3.1-flash-lite":{"draws":6,"losses":4,"wins":6},"google/gemini-3.5-flash":{"draws":2,"losses":6,"wins":2},"google/gemini-3.5-flash-lite":{"draws":6,"losses":10,"wins":6},"google/gemini-3.6-flash":{"draws":9,"losses":7,"wins":4},"google/gemma-4-31b-it":{"draws":5,"losses":2,"wins":3},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":5,"losses":3,"wins":4},"gpt-5.4":{"draws":8,"losses":9,"wins":1},"gpt-5.4-mini":{"draws":36,"losses":26,"wins":16},"gpt-5.4-nano":{"draws":24,"losses":22,"wins":20},"gpt-5.5":{"draws":10,"losses":9,"wins":7},"gpt-5.6-luna":{"draws":12,"losses":10,"wins":4},"gpt-5.6-sol":{"draws":3,"losses":13,"wins":2},"gpt-5.6-terra":{"draws":10,"losses":3,"wins":7},"inclusionai/ling-3.0-flash":{"draws":10,"losses":0,"wins":10},"meituan/longcat-2.0":{"draws":4,"losses":4,"wins":12},"minimax/minimax-m3":{"draws":4,"losses":5,"wins":7},"mistralai/mistral-medium-3-5":{"draws":0,"losses":4,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":1,"wins":1},"moonshotai/kimi-k3":{"draws":7,"losses":2,"wins":5},"nex-agi/nex-n2-pro":{"draws":3,"losses":3,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":5,"wins":7},"o3":{"draws":4,"losses":2,"wins":4},"openai/gpt-oss-120b":{"draws":5,"losses":7,"wins":2},"poolside/laguna-s-2.1":{"draws":6,"losses":6,"wins":10},"qwen/qwen3.7-max":{"draws":7,"losses":3,"wins":0},"qwen/qwen3.7-plus":{"draws":2,"losses":2,"wins":2},"stepfun/step-3.7-flash":{"draws":0,"losses":3,"wins":3},"tencent/hy3-preview":{"draws":11,"losses":3,"wins":6},"thinkingmachines/inkling":{"draws":4,"losses":9,"wins":5},"x-ai/grok-4.5":{"draws":9,"losses":24,"wins":7},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":13,"losses":10,"wins":13},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":6,"wins":12},"z-ai/glm-5.2":{"draws":20,"losses":26,"wins":22}},"gpt-4.1-nano":{"claude-opus-4-5":{"draws":2,"losses":0,"wins":0},"claude-opus-5":{"draws":2,"losses":2,"wins":0},"claude-sonnet-5":{"draws":2,"losses":2,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":0},"deepseek/deepseek-v4-flash":{"draws":0,"losses":1,"wins":1},"deepseek/deepseek-v4-pro":{"draws":1,"losses":0,"wins":1},"google/gemini-3.5-flash-lite":{"draws":1,"losses":4,"wins":5},"google/gemini-3.6-flash":{"draws":5,"losses":2,"wins":3},"google/gemma-4-31b-it":{"draws":0,"losses":2,"wins":0},"gpt-4.1":{"draws":0,"losses":2,"wins":0},"gpt-5.4-mini":{"draws":1,"losses":0,"wins":1},"gpt-5.4-nano":{"draws":3,"losses":1,"wins":0},"gpt-5.5":{"draws":2,"losses":0,"wins":0},"inclusionai/ling-3.0-flash":{"draws":1,"losses":1,"wins":4},"meituan/longcat-2.0":{"draws":1,"losses":0,"wins":3},"minimax/minimax-m3":{"draws":0,"losses":1,"wins":1},"moonshotai/kimi-k3":{"draws":5,"losses":3,"wins":0},"o3":{"draws":0,"losses":2,"wins":4},"openai/gpt-oss-120b":{"draws":0,"losses":1,"wins":1},"poolside/laguna-s-2.1":{"draws":0,"losses":4,"wins":2},"thinkingmachines/inkling":{"draws":0,"losses":0,"wins":8},"x-ai/grok-4.5":{"draws":2,"losses":4,"wins":0},"xiaomi/mimo-v2.5":{"draws":0,"losses":0,"wins":2}},"gpt-5":{"claude-fable-5":{"draws":2,"losses":34,"wins":2},"claude-opus-4-5":{"draws":25,"losses":21,"wins":20},"claude-opus-4-8":{"draws":11,"losses":26,"wins":13},"claude-opus-5":{"draws":10,"losses":51,"wins":5},"claude-sonnet-5":{"draws":24,"losses":18,"wins":20},"cohere/north-mini-code":{"draws":7,"losses":4,"wins":17},"deepseek/deepseek-v4-flash":{"draws":21,"losses":5,"wins":28},"deepseek/deepseek-v4-pro":{"draws":4,"losses":14,"wins":6},"google/gemini-3.1-flash-lite":{"draws":14,"losses":2,"wins":18},"google/gemini-3.5-flash":{"draws":8,"losses":18,"wins":8},"google/gemini-3.5-flash-lite":{"draws":19,"losses":7,"wins":10},"google/gemini-3.6-flash":{"draws":5,"losses":21,"wins":12},"google/gemma-4-31b-it":{"draws":3,"losses":3,"wins":8},"gpt-4.1":{"draws":5,"losses":4,"wins":3},"gpt-5":{"draws":0,"losses":4,"wins":4},"gpt-5.4":{"draws":11,"losses":28,"wins":7},"gpt-5.4-mini":{"draws":38,"losses":34,"wins":32},"gpt-5.4-nano":{"draws":37,"losses":32,"wins":49},"gpt-5.5":{"draws":11,"losses":21,"wins":10},"gpt-5.6-luna":{"draws":19,"losses":16,"wins":17},"gpt-5.6-sol":{"draws":10,"losses":31,"wins":11},"gpt-5.6-terra":{"draws":12,"losses":23,"wins":11},"inclusionai/ling-3.0-flash":{"draws":6,"losses":8,"wins":6},"meituan/longcat-2.0":{"draws":8,"losses":6,"wins":16},"minimax/minimax-m3":{"draws":7,"losses":6,"wins":11},"mistralai/mistral-medium-3-5":{"draws":0,"losses":4,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":5,"wins":9},"moonshotai/kimi-k3":{"draws":7,"losses":8,"wins":5},"nex-agi/nex-n2-pro":{"draws":4,"losses":2,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":17,"losses":6,"wins":15},"o3":{"draws":6,"losses":16,"wins":20},"openai/gpt-oss-120b":{"draws":14,"losses":2,"wins":6},"poolside/laguna-s-2.1":{"draws":11,"losses":9,"wins":6},"qwen/qwen3.7-max":{"draws":10,"losses":4,"wins":10},"qwen/qwen3.7-plus":{"draws":2,"losses":5,"wins":5},"stepfun/step-3.7-flash":{"draws":8,"losses":0,"wins":14},"tencent/hy3-preview":{"draws":5,"losses":8,"wins":9},"thinkingmachines/inkling":{"draws":12,"losses":5,"wins":13},"x-ai/grok-4.5":{"draws":15,"losses":40,"wins":11},"x-ai/grok-build-0.1":{"draws":7,"losses":4,"wins":11},"xiaomi/mimo-v2.5":{"draws":31,"losses":18,"wins":23},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":5,"wins":8},"z-ai/glm-5.2":{"draws":48,"losses":49,"wins":47}},"gpt-5.4":{"claude-fable-5":{"draws":8,"losses":30,"wins":28},"claude-opus-4-5":{"draws":28,"losses":25,"wins":37},"claude-opus-4-8":{"draws":15,"losses":23,"wins":32},"claude-opus-5":{"draws":23,"losses":83,"wins":48},"claude-sonnet-5":{"draws":27,"losses":9,"wins":38},"cohere/north-mini-code":{"draws":8,"losses":7,"wins":19},"deepseek/deepseek-v4-flash":{"draws":39,"losses":16,"wins":51},"deepseek/deepseek-v4-pro":{"draws":9,"losses":5,"wins":28},"google/gemini-3.1-flash-lite":{"draws":6,"losses":0,"wins":24},"google/gemini-3.5-flash":{"draws":15,"losses":10,"wins":17},"google/gemini-3.5-flash-lite":{"draws":15,"losses":1,"wins":18},"google/gemini-3.6-flash":{"draws":25,"losses":17,"wins":26},"google/gemma-4-31b-it":{"draws":5,"losses":4,"wins":13},"gpt-4.1":{"draws":8,"losses":1,"wins":9},"gpt-5":{"draws":11,"losses":7,"wins":28},"gpt-5.4":{"draws":14,"losses":19,"wins":19},"gpt-5.4-mini":{"draws":54,"losses":26,"wins":96},"gpt-5.4-nano":{"draws":55,"losses":27,"wins":106},"gpt-5.5":{"draws":29,"losses":23,"wins":32},"gpt-5.6-luna":{"draws":33,"losses":10,"wins":43},"gpt-5.6-sol":{"draws":15,"losses":25,"wins":50},"gpt-5.6-terra":{"draws":30,"losses":19,"wins":43},"inclusionai/ling-3.0-flash":{"draws":17,"losses":2,"wins":9},"meituan/longcat-2.0":{"draws":13,"losses":10,"wins":11},"minimax/minimax-m3":{"draws":10,"losses":7,"wins":19},"mistralai/mistral-medium-3-5":{"draws":1,"losses":0,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":6,"wins":6},"moonshotai/kimi-k3":{"draws":18,"losses":17,"wins":23},"nex-agi/nex-n2-pro":{"draws":10,"losses":5,"wins":21},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":3,"wins":27},"o3":{"draws":7,"losses":7,"wins":28},"openai/gpt-oss-120b":{"draws":12,"losses":3,"wins":29},"poolside/laguna-s-2.1":{"draws":12,"losses":3,"wins":17},"qwen/qwen3.7-max":{"draws":9,"losses":7,"wins":26},"qwen/qwen3.7-plus":{"draws":10,"losses":3,"wins":19},"stepfun/step-3.7-flash":{"draws":5,"losses":4,"wins":15},"tencent/hy3-preview":{"draws":17,"losses":4,"wins":23},"thinkingmachines/inkling":{"draws":16,"losses":9,"wins":15},"x-ai/grok-4.5":{"draws":25,"losses":31,"wins":54},"x-ai/grok-build-0.1":{"draws":8,"losses":5,"wins":13},"xiaomi/mimo-v2.5":{"draws":36,"losses":9,"wins":45},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":9,"wins":27},"z-ai/glm-5.2":{"draws":74,"losses":36,"wins":68}},"gpt-5.4-mini":{"claude-fable-5":{"draws":22,"losses":60,"wins":12},"claude-opus-4-5":{"draws":84,"losses":105,"wins":53},"claude-opus-4-8":{"draws":56,"losses":83,"wins":39},"claude-opus-5":{"draws":37,"losses":180,"wins":23},"claude-sonnet-5":{"draws":79,"losses":63,"wins":44},"cohere/north-mini-code":{"draws":30,"losses":20,"wins":36},"deepseek/deepseek-v4-flash":{"draws":133,"losses":81,"wins":132},"deepseek/deepseek-v4-pro":{"draws":38,"losses":43,"wins":25},"google/gemini-3.1-flash-lite":{"draws":34,"losses":21,"wins":73},"google/gemini-3.5-flash":{"draws":29,"losses":38,"wins":25},"google/gemini-3.5-flash-lite":{"draws":63,"losses":28,"wins":59},"google/gemini-3.6-flash":{"draws":56,"losses":63,"wins":30},"google/gemma-4-31b-it":{"draws":27,"losses":32,"wins":31},"gpt-4.1":{"draws":36,"losses":16,"wins":26},"gpt-4.1-nano":{"draws":1,"losses":1,"wins":0},"gpt-5":{"draws":38,"losses":32,"wins":34},"gpt-5.4":{"draws":54,"losses":96,"wins":26},"gpt-5.4-mini":{"draws":146,"losses":103,"wins":103},"gpt-5.4-nano":{"draws":158,"losses":153,"wins":188},"gpt-5.5":{"draws":60,"losses":56,"wins":26},"gpt-5.6-luna":{"draws":68,"losses":47,"wins":43},"gpt-5.6-sol":{"draws":39,"losses":88,"wins":27},"gpt-5.6-terra":{"draws":71,"losses":81,"wins":42},"inclusionai/ling-3.0-flash":{"draws":59,"losses":21,"wins":44},"meituan/longcat-2.0":{"draws":53,"losses":39,"wins":58},"minimax/minimax-m3":{"draws":41,"losses":41,"wins":40},"mistralai/mistral-medium-3-5":{"draws":12,"losses":17,"wins":37},"moonshotai/kimi-k2.7-code":{"draws":17,"losses":29,"wins":10},"moonshotai/kimi-k3":{"draws":71,"losses":68,"wins":29},"nex-agi/nex-n2-pro":{"draws":34,"losses":28,"wins":42},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":68,"losses":25,"wins":49},"o3":{"draws":19,"losses":52,"wins":55},"openai/gpt-oss-120b":{"draws":45,"losses":33,"wins":52},"poolside/laguna-s-2.1":{"draws":53,"losses":28,"wins":43},"qwen/qwen3.7-max":{"draws":44,"losses":51,"wins":33},"qwen/qwen3.7-plus":{"draws":41,"losses":40,"wins":21},"stepfun/step-3.7-flash":{"draws":29,"losses":29,"wins":38},"tencent/hy3-preview":{"draws":32,"losses":25,"wins":35},"thinkingmachines/inkling":{"draws":55,"losses":44,"wins":59},"x-ai/grok-4.5":{"draws":63,"losses":132,"wins":33},"x-ai/grok-build-0.1":{"draws":20,"losses":23,"wins":21},"xiaomi/mimo-v2.5":{"draws":139,"losses":103,"wins":88},"xiaomi/mimo-v2.5-pro":{"draws":26,"losses":32,"wins":32},"z-ai/glm-5.2":{"draws":162,"losses":145,"wins":117}},"gpt-5.4-nano":{"claude-fable-5":{"draws":13,"losses":99,"wins":18},"claude-opus-4-5":{"draws":83,"losses":109,"wins":60},"claude-opus-4-8":{"draws":40,"losses":102,"wins":36},"claude-opus-5":{"draws":32,"losses":143,"wins":27},"claude-sonnet-5":{"draws":76,"losses":57,"wins":41},"cohere/north-mini-code":{"draws":38,"losses":31,"wins":53},"deepseek/deepseek-v4-flash":{"draws":142,"losses":117,"wins":87},"deepseek/deepseek-v4-pro":{"draws":37,"losses":36,"wins":31},"google/gemini-3.1-flash-lite":{"draws":34,"losses":39,"wins":79},"google/gemini-3.5-flash":{"draws":29,"losses":45,"wins":24},"google/gemini-3.5-flash-lite":{"draws":62,"losses":48,"wins":32},"google/gemini-3.6-flash":{"draws":60,"losses":59,"wins":23},"google/gemma-4-31b-it":{"draws":19,"losses":38,"wins":35},"gpt-4.1":{"draws":24,"losses":20,"wins":22},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":1},"gpt-5":{"draws":37,"losses":49,"wins":32},"gpt-5.4":{"draws":55,"losses":106,"wins":27},"gpt-5.4-mini":{"draws":158,"losses":188,"wins":153},"gpt-5.4-nano":{"draws":134,"losses":183,"wins":183},"gpt-5.5":{"draws":51,"losses":81,"wins":30},"gpt-5.6-luna":{"draws":65,"losses":77,"wins":74},"gpt-5.6-sol":{"draws":32,"losses":111,"wins":35},"gpt-5.6-terra":{"draws":51,"losses":73,"wins":54},"inclusionai/ling-3.0-flash":{"draws":78,"losses":30,"wins":32},"meituan/longcat-2.0":{"draws":47,"losses":54,"wins":61},"minimax/minimax-m3":{"draws":48,"losses":48,"wins":50},"mistralai/mistral-medium-3-5":{"draws":13,"losses":32,"wins":43},"moonshotai/kimi-k2.7-code":{"draws":13,"losses":29,"wins":14},"moonshotai/kimi-k3":{"draws":45,"losses":88,"wins":21},"nex-agi/nex-n2-pro":{"draws":33,"losses":39,"wins":38},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":73,"losses":32,"wins":51},"o3":{"draws":26,"losses":62,"wins":42},"openai/gpt-oss-120b":{"draws":63,"losses":36,"wins":43},"poolside/laguna-s-2.1":{"draws":48,"losses":37,"wins":21},"qwen/qwen3.7-max":{"draws":52,"losses":49,"wins":21},"qwen/qwen3.7-plus":{"draws":35,"losses":57,"wins":30},"stepfun/step-3.7-flash":{"draws":33,"losses":24,"wins":39},"tencent/hy3-preview":{"draws":43,"losses":39,"wins":20},"thinkingmachines/inkling":{"draws":42,"losses":48,"wins":43},"x-ai/grok-4.5":{"draws":44,"losses":169,"wins":57},"x-ai/grok-build-0.1":{"draws":21,"losses":24,"wins":25},"xiaomi/mimo-v2.5":{"draws":141,"losses":110,"wins":113},"xiaomi/mimo-v2.5-pro":{"draws":30,"losses":55,"wins":29},"z-ai/glm-5.2":{"draws":165,"losses":159,"wins":125}},"gpt-5.5":{"claude-fable-5":{"draws":8,"losses":24,"wins":22},"claude-opus-4-5":{"draws":31,"losses":24,"wins":33},"claude-opus-4-8":{"draws":19,"losses":22,"wins":35},"claude-opus-5":{"draws":21,"losses":94,"wins":33},"claude-sonnet-5":{"draws":29,"losses":18,"wins":23},"cohere/north-mini-code":{"draws":14,"losses":3,"wins":11},"deepseek/deepseek-v4-flash":{"draws":40,"losses":3,"wins":51},"deepseek/deepseek-v4-pro":{"draws":15,"losses":3,"wins":16},"google/gemini-3.1-flash-lite":{"draws":11,"losses":3,"wins":22},"google/gemini-3.5-flash":{"draws":11,"losses":16,"wins":21},"google/gemini-3.5-flash-lite":{"draws":30,"losses":6,"wins":18},"google/gemini-3.6-flash":{"draws":25,"losses":26,"wins":23},"google/gemma-4-31b-it":{"draws":7,"losses":2,"wins":11},"gpt-4.1":{"draws":10,"losses":7,"wins":9},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":11,"losses":10,"wins":21},"gpt-5.4":{"draws":29,"losses":32,"wins":23},"gpt-5.4-mini":{"draws":60,"losses":26,"wins":56},"gpt-5.4-nano":{"draws":51,"losses":30,"wins":81},"gpt-5.5":{"draws":16,"losses":16,"wins":16},"gpt-5.6-luna":{"draws":17,"losses":18,"wins":29},"gpt-5.6-sol":{"draws":17,"losses":31,"wins":36},"gpt-5.6-terra":{"draws":28,"losses":16,"wins":26},"inclusionai/ling-3.0-flash":{"draws":27,"losses":4,"wins":7},"meituan/longcat-2.0":{"draws":16,"losses":12,"wins":12},"minimax/minimax-m3":{"draws":9,"losses":10,"wins":21},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":9,"losses":6,"wins":5},"moonshotai/kimi-k3":{"draws":27,"losses":15,"wins":14},"nex-agi/nex-n2-pro":{"draws":8,"losses":3,"wins":15},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":22,"losses":5,"wins":23},"o3":{"draws":12,"losses":6,"wins":34},"openai/gpt-oss-120b":{"draws":21,"losses":3,"wins":18},"poolside/laguna-s-2.1":{"draws":15,"losses":14,"wins":13},"qwen/qwen3.7-max":{"draws":17,"losses":11,"wins":16},"qwen/qwen3.7-plus":{"draws":13,"losses":4,"wins":13},"stepfun/step-3.7-flash":{"draws":6,"losses":2,"wins":18},"tencent/hy3-preview":{"draws":24,"losses":5,"wins":17},"thinkingmachines/inkling":{"draws":15,"losses":11,"wins":22},"x-ai/grok-4.5":{"draws":38,"losses":48,"wins":34},"x-ai/grok-build-0.1":{"draws":15,"losses":6,"wins":5},"xiaomi/mimo-v2.5":{"draws":37,"losses":10,"wins":33},"xiaomi/mimo-v2.5-pro":{"draws":12,"losses":8,"wins":12},"z-ai/glm-5.2":{"draws":54,"losses":38,"wins":68}},"gpt-5.6-luna":{"claude-fable-5":{"draws":6,"losses":33,"wins":7},"claude-opus-4-5":{"draws":37,"losses":27,"wins":30},"claude-opus-4-8":{"draws":17,"losses":26,"wins":19},"claude-opus-5":{"draws":16,"losses":68,"wins":14},"claude-sonnet-5":{"draws":32,"losses":12,"wins":26},"cohere/north-mini-code":{"draws":5,"losses":16,"wins":7},"deepseek/deepseek-v4-flash":{"draws":49,"losses":40,"wins":33},"deepseek/deepseek-v4-pro":{"draws":16,"losses":14,"wins":14},"google/gemini-3.1-flash-lite":{"draws":15,"losses":15,"wins":22},"google/gemini-3.5-flash":{"draws":17,"losses":12,"wins":13},"google/gemini-3.5-flash-lite":{"draws":25,"losses":6,"wins":13},"google/gemini-3.6-flash":{"draws":24,"losses":30,"wins":16},"google/gemma-4-31b-it":{"draws":8,"losses":12,"wins":8},"gpt-4.1":{"draws":12,"losses":4,"wins":10},"gpt-5":{"draws":19,"losses":17,"wins":16},"gpt-5.4":{"draws":33,"losses":43,"wins":10},"gpt-5.4-mini":{"draws":68,"losses":43,"wins":47},"gpt-5.4-nano":{"draws":65,"losses":74,"wins":77},"gpt-5.5":{"draws":17,"losses":29,"wins":18},"gpt-5.6-luna":{"draws":16,"losses":16,"wins":16},"gpt-5.6-sol":{"draws":11,"losses":40,"wins":21},"gpt-5.6-terra":{"draws":21,"losses":34,"wins":23},"inclusionai/ling-3.0-flash":{"draws":30,"losses":11,"wins":5},"meituan/longcat-2.0":{"draws":26,"losses":11,"wins":15},"minimax/minimax-m3":{"draws":16,"losses":10,"wins":14},"mistralai/mistral-medium-3-5":{"draws":4,"losses":9,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":10,"wins":5},"moonshotai/kimi-k3":{"draws":17,"losses":23,"wins":18},"nex-agi/nex-n2-pro":{"draws":18,"losses":14,"wins":14},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":32,"losses":9,"wins":23},"o3":{"draws":7,"losses":16,"wins":23},"openai/gpt-oss-120b":{"draws":20,"losses":15,"wins":19},"poolside/laguna-s-2.1":{"draws":23,"losses":12,"wins":7},"qwen/qwen3.7-max":{"draws":22,"losses":11,"wins":15},"qwen/qwen3.7-plus":{"draws":11,"losses":11,"wins":10},"stepfun/step-3.7-flash":{"draws":7,"losses":10,"wins":17},"tencent/hy3-preview":{"draws":13,"losses":15,"wins":16},"thinkingmachines/inkling":{"draws":18,"losses":10,"wins":14},"x-ai/grok-4.5":{"draws":22,"losses":57,"wins":25},"x-ai/grok-build-0.1":{"draws":19,"losses":1,"wins":12},"xiaomi/mimo-v2.5":{"draws":37,"losses":37,"wins":30},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":16,"wins":7},"z-ai/glm-5.2":{"draws":56,"losses":57,"wins":49}},"gpt-5.6-sol":{"claude-fable-5":{"draws":13,"losses":41,"wins":20},"claude-opus-4-5":{"draws":27,"losses":15,"wins":54},"claude-opus-4-8":{"draws":15,"losses":23,"wins":40},"claude-opus-5":{"draws":29,"losses":122,"wins":35},"claude-sonnet-5":{"draws":14,"losses":17,"wins":49},"cohere/north-mini-code":{"draws":7,"losses":1,"wins":20},"deepseek/deepseek-v4-flash":{"draws":16,"losses":15,"wins":69},"deepseek/deepseek-v4-pro":{"draws":2,"losses":10,"wins":20},"google/gemini-3.1-flash-lite":{"draws":6,"losses":6,"wins":22},"google/gemini-3.5-flash":{"draws":12,"losses":11,"wins":21},"google/gemini-3.5-flash-lite":{"draws":11,"losses":6,"wins":13},"google/gemini-3.6-flash":{"draws":15,"losses":21,"wins":28},"google/gemma-4-31b-it":{"draws":8,"losses":2,"wins":16},"gpt-4.1":{"draws":3,"losses":2,"wins":13},"gpt-5":{"draws":10,"losses":11,"wins":31},"gpt-5.4":{"draws":15,"losses":50,"wins":25},"gpt-5.4-mini":{"draws":39,"losses":27,"wins":88},"gpt-5.4-nano":{"draws":32,"losses":35,"wins":111},"gpt-5.5":{"draws":17,"losses":36,"wins":31},"gpt-5.6-luna":{"draws":11,"losses":21,"wins":40},"gpt-5.6-sol":{"draws":6,"losses":19,"wins":19},"gpt-5.6-terra":{"draws":16,"losses":27,"wins":41},"inclusionai/ling-3.0-flash":{"draws":7,"losses":2,"wins":11},"meituan/longcat-2.0":{"draws":5,"losses":9,"wins":8},"minimax/minimax-m3":{"draws":11,"losses":2,"wins":23},"mistralai/mistral-medium-3-5":{"draws":0,"losses":1,"wins":19},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":3,"wins":11},"moonshotai/kimi-k3":{"draws":13,"losses":15,"wins":32},"nex-agi/nex-n2-pro":{"draws":5,"losses":4,"wins":19},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":8,"wins":38},"o3":{"draws":4,"losses":10,"wins":28},"openai/gpt-oss-120b":{"draws":14,"losses":4,"wins":28},"poolside/laguna-s-2.1":{"draws":0,"losses":12,"wins":16},"qwen/qwen3.7-max":{"draws":6,"losses":9,"wins":23},"qwen/qwen3.7-plus":{"draws":10,"losses":7,"wins":13},"stepfun/step-3.7-flash":{"draws":3,"losses":4,"wins":23},"tencent/hy3-preview":{"draws":13,"losses":10,"wins":25},"thinkingmachines/inkling":{"draws":10,"losses":8,"wins":16},"x-ai/grok-4.5":{"draws":20,"losses":56,"wins":56},"x-ai/grok-build-0.1":{"draws":6,"losses":6,"wins":14},"xiaomi/mimo-v2.5":{"draws":27,"losses":14,"wins":53},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":5,"wins":21},"z-ai/glm-5.2":{"draws":34,"losses":51,"wins":87}},"gpt-5.6-terra":{"claude-fable-5":{"draws":7,"losses":48,"wins":5},"claude-opus-4-5":{"draws":42,"losses":29,"wins":37},"claude-opus-4-8":{"draws":22,"losses":27,"wins":17},"claude-opus-5":{"draws":37,"losses":107,"wins":18},"claude-sonnet-5":{"draws":28,"losses":30,"wins":26},"cohere/north-mini-code":{"draws":7,"losses":4,"wins":21},"deepseek/deepseek-v4-flash":{"draws":38,"losses":16,"wins":64},"deepseek/deepseek-v4-pro":{"draws":17,"losses":10,"wins":17},"google/gemini-3.1-flash-lite":{"draws":8,"losses":5,"wins":25},"google/gemini-3.5-flash":{"draws":14,"losses":18,"wins":16},"google/gemini-3.5-flash-lite":{"draws":26,"losses":7,"wins":17},"google/gemini-3.6-flash":{"draws":21,"losses":30,"wins":19},"google/gemma-4-31b-it":{"draws":7,"losses":2,"wins":21},"gpt-4.1":{"draws":10,"losses":7,"wins":3},"gpt-5":{"draws":12,"losses":11,"wins":23},"gpt-5.4":{"draws":30,"losses":43,"wins":19},"gpt-5.4-mini":{"draws":71,"losses":42,"wins":81},"gpt-5.4-nano":{"draws":51,"losses":54,"wins":73},"gpt-5.5":{"draws":28,"losses":26,"wins":16},"gpt-5.6-luna":{"draws":21,"losses":23,"wins":34},"gpt-5.6-sol":{"draws":16,"losses":41,"wins":27},"gpt-5.6-terra":{"draws":12,"losses":6,"wins":6},"inclusionai/ling-3.0-flash":{"draws":11,"losses":4,"wins":13},"meituan/longcat-2.0":{"draws":16,"losses":14,"wins":16},"minimax/minimax-m3":{"draws":13,"losses":9,"wins":18},"mistralai/mistral-medium-3-5":{"draws":2,"losses":1,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":7,"wins":9},"moonshotai/kimi-k3":{"draws":27,"losses":22,"wins":19},"nex-agi/nex-n2-pro":{"draws":10,"losses":6,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":25,"losses":8,"wins":27},"o3":{"draws":5,"losses":16,"wins":27},"openai/gpt-oss-120b":{"draws":10,"losses":5,"wins":27},"poolside/laguna-s-2.1":{"draws":23,"losses":15,"wins":12},"qwen/qwen3.7-max":{"draws":12,"losses":8,"wins":14},"qwen/qwen3.7-plus":{"draws":15,"losses":13,"wins":14},"stepfun/step-3.7-flash":{"draws":11,"losses":4,"wins":15},"tencent/hy3-preview":{"draws":14,"losses":8,"wins":12},"thinkingmachines/inkling":{"draws":21,"losses":12,"wins":13},"x-ai/grok-4.5":{"draws":26,"losses":66,"wins":28},"x-ai/grok-build-0.1":{"draws":12,"losses":2,"wins":10},"xiaomi/mimo-v2.5":{"draws":45,"losses":16,"wins":35},"xiaomi/mimo-v2.5-pro":{"draws":13,"losses":8,"wins":13},"z-ai/glm-5.2":{"draws":54,"losses":54,"wins":58}},"inclusionai/ling-3.0-flash":{"claude-opus-4-5":{"draws":18,"losses":13,"wins":7},"claude-opus-4-8":{"draws":18,"losses":4,"wins":0},"claude-opus-5":{"draws":12,"losses":22,"wins":2},"claude-sonnet-5":{"draws":23,"losses":22,"wins":3},"cohere/north-mini-code":{"draws":18,"losses":6,"wins":10},"deepseek/deepseek-v4-flash":{"draws":44,"losses":37,"wins":17},"deepseek/deepseek-v4-pro":{"draws":14,"losses":12,"wins":4},"google/gemini-3.1-flash-lite":{"draws":9,"losses":13,"wins":8},"google/gemini-3.5-flash":{"draws":6,"losses":2,"wins":2},"google/gemini-3.5-flash-lite":{"draws":50,"losses":39,"wins":15},"google/gemini-3.6-flash":{"draws":67,"losses":46,"wins":19},"google/gemma-4-31b-it":{"draws":12,"losses":19,"wins":5},"gpt-4.1":{"draws":10,"losses":10,"wins":0},"gpt-4.1-nano":{"draws":1,"losses":4,"wins":1},"gpt-5":{"draws":6,"losses":6,"wins":8},"gpt-5.4":{"draws":17,"losses":9,"wins":2},"gpt-5.4-mini":{"draws":59,"losses":44,"wins":21},"gpt-5.4-nano":{"draws":78,"losses":32,"wins":30},"gpt-5.5":{"draws":27,"losses":7,"wins":4},"gpt-5.6-luna":{"draws":30,"losses":5,"wins":11},"gpt-5.6-sol":{"draws":7,"losses":11,"wins":2},"gpt-5.6-terra":{"draws":11,"losses":13,"wins":4},"inclusionai/ling-3.0-flash":{"draws":20,"losses":18,"wins":18},"meituan/longcat-2.0":{"draws":42,"losses":37,"wins":27},"minimax/minimax-m3":{"draws":18,"losses":15,"wins":7},"mistralai/mistral-medium-3-5":{"draws":8,"losses":10,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":7,"wins":3},"moonshotai/kimi-k3":{"draws":27,"losses":24,"wins":11},"nex-agi/nex-n2-pro":{"draws":20,"losses":12,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":17,"losses":6,"wins":5},"o3":{"draws":7,"losses":27,"wins":8},"openai/gpt-oss-120b":{"draws":25,"losses":15,"wins":10},"poolside/laguna-s-2.1":{"draws":47,"losses":31,"wins":14},"qwen/qwen3.7-max":{"draws":21,"losses":10,"wins":5},"qwen/qwen3.7-plus":{"draws":13,"losses":9,"wins":8},"stepfun/step-3.7-flash":{"draws":4,"losses":14,"wins":6},"tencent/hy3-preview":{"draws":11,"losses":11,"wins":2},"thinkingmachines/inkling":{"draws":33,"losses":32,"wins":27},"x-ai/grok-4.5":{"draws":30,"losses":53,"wins":9},"x-ai/grok-build-0.1":{"draws":7,"losses":11,"wins":0},"xiaomi/mimo-v2.5":{"draws":30,"losses":24,"wins":16},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":13,"wins":8},"z-ai/glm-5.2":{"draws":48,"losses":10,"wins":10}},"meituan/longcat-2.0":{"claude-fable-5":{"draws":1,"losses":6,"wins":1},"claude-opus-4-5":{"draws":28,"losses":30,"wins":17},"claude-opus-4-8":{"draws":8,"losses":17,"wins":7},"claude-opus-5":{"draws":10,"losses":48,"wins":10},"claude-sonnet-5":{"draws":21,"losses":37,"wins":10},"cohere/north-mini-code":{"draws":22,"losses":8,"wins":18},"deepseek/deepseek-v4-flash":{"draws":32,"losses":33,"wins":27},"deepseek/deepseek-v4-pro":{"draws":5,"losses":16,"wins":7},"google/gemini-3.1-flash-lite":{"draws":10,"losses":16,"wins":24},"google/gemini-3.5-flash":{"draws":7,"losses":2,"wins":3},"google/gemini-3.5-flash-lite":{"draws":38,"losses":54,"wins":47},"google/gemini-3.6-flash":{"draws":45,"losses":59,"wins":28},"google/gemma-4-31b-it":{"draws":6,"losses":11,"wins":13},"gpt-4.1":{"draws":4,"losses":12,"wins":4},"gpt-4.1-nano":{"draws":1,"losses":3,"wins":0},"gpt-5":{"draws":8,"losses":16,"wins":6},"gpt-5.4":{"draws":13,"losses":11,"wins":10},"gpt-5.4-mini":{"draws":53,"losses":58,"wins":39},"gpt-5.4-nano":{"draws":47,"losses":61,"wins":54},"gpt-5.5":{"draws":16,"losses":12,"wins":12},"gpt-5.6-luna":{"draws":26,"losses":15,"wins":11},"gpt-5.6-sol":{"draws":5,"losses":8,"wins":9},"gpt-5.6-terra":{"draws":16,"losses":16,"wins":14},"inclusionai/ling-3.0-flash":{"draws":42,"losses":27,"wins":37},"meituan/longcat-2.0":{"draws":18,"losses":17,"wins":17},"minimax/minimax-m3":{"draws":6,"losses":18,"wins":16},"mistralai/mistral-medium-3-5":{"draws":4,"losses":6,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":6,"wins":2},"moonshotai/kimi-k3":{"draws":36,"losses":56,"wins":18},"nex-agi/nex-n2-pro":{"draws":11,"losses":13,"wins":14},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":17,"losses":18,"wins":9},"o3":{"draws":12,"losses":45,"wins":25},"openai/gpt-oss-120b":{"draws":23,"losses":14,"wins":21},"poolside/laguna-s-2.1":{"draws":46,"losses":32,"wins":26},"qwen/qwen3.7-max":{"draws":18,"losses":16,"wins":4},"qwen/qwen3.7-plus":{"draws":9,"losses":8,"wins":7},"stepfun/step-3.7-flash":{"draws":5,"losses":22,"wins":15},"tencent/hy3-preview":{"draws":11,"losses":7,"wins":6},"thinkingmachines/inkling":{"draws":24,"losses":43,"wins":33},"x-ai/grok-4.5":{"draws":36,"losses":93,"wins":27},"x-ai/grok-build-0.1":{"draws":9,"losses":13,"wins":8},"xiaomi/mimo-v2.5":{"draws":23,"losses":29,"wins":32},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":18,"wins":14},"z-ai/glm-5.2":{"draws":46,"losses":44,"wins":20}},"minimax/minimax-m3":{"claude-fable-5":{"draws":2,"losses":16,"wins":0},"claude-opus-4-5":{"draws":11,"losses":28,"wins":7},"claude-opus-4-8":{"draws":11,"losses":19,"wins":4},"claude-opus-5":{"draws":3,"losses":33,"wins":4},"claude-sonnet-5":{"draws":11,"losses":16,"wins":7},"cohere/north-mini-code":{"draws":3,"losses":10,"wins":15},"deepseek/deepseek-v4-flash":{"draws":19,"losses":26,"wins":33},"deepseek/deepseek-v4-pro":{"draws":3,"losses":4,"wins":9},"google/gemini-3.1-flash-lite":{"draws":5,"losses":13,"wins":10},"google/gemini-3.5-flash":{"draws":5,"losses":12,"wins":1},"google/gemini-3.5-flash-lite":{"draws":9,"losses":11,"wins":6},"google/gemini-3.6-flash":{"draws":11,"losses":17,"wins":6},"google/gemma-4-31b-it":{"draws":6,"losses":8,"wins":12},"gpt-4.1":{"draws":4,"losses":7,"wins":5},"gpt-4.1-nano":{"draws":0,"losses":1,"wins":1},"gpt-5":{"draws":7,"losses":11,"wins":6},"gpt-5.4":{"draws":10,"losses":19,"wins":7},"gpt-5.4-mini":{"draws":41,"losses":40,"wins":41},"gpt-5.4-nano":{"draws":48,"losses":50,"wins":48},"gpt-5.5":{"draws":9,"losses":21,"wins":10},"gpt-5.6-luna":{"draws":16,"losses":14,"wins":10},"gpt-5.6-sol":{"draws":11,"losses":23,"wins":2},"gpt-5.6-terra":{"draws":13,"losses":18,"wins":9},"inclusionai/ling-3.0-flash":{"draws":18,"losses":7,"wins":15},"meituan/longcat-2.0":{"draws":6,"losses":16,"wins":18},"mistralai/mistral-medium-3-5":{"draws":0,"losses":4,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":10,"wins":1},"moonshotai/kimi-k3":{"draws":10,"losses":19,"wins":7},"nex-agi/nex-n2-pro":{"draws":7,"losses":6,"wins":15},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":11,"wins":9},"o3":{"draws":5,"losses":12,"wins":3},"openai/gpt-oss-120b":{"draws":9,"losses":6,"wins":13},"poolside/laguna-s-2.1":{"draws":13,"losses":14,"wins":9},"qwen/qwen3.7-max":{"draws":13,"losses":12,"wins":7},"qwen/qwen3.7-plus":{"draws":6,"losses":11,"wins":11},"stepfun/step-3.7-flash":{"draws":5,"losses":3,"wins":10},"tencent/hy3-preview":{"draws":8,"losses":9,"wins":5},"thinkingmachines/inkling":{"draws":6,"losses":12,"wins":14},"x-ai/grok-4.5":{"draws":6,"losses":31,"wins":3},"x-ai/grok-build-0.1":{"draws":8,"losses":8,"wins":6},"xiaomi/mimo-v2.5":{"draws":28,"losses":26,"wins":30},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":14,"wins":9},"z-ai/glm-5.2":{"draws":28,"losses":19,"wins":17}},"mistralai/mistral-medium-3-5":{"claude-fable-5":{"draws":0,"losses":8,"wins":0},"claude-opus-4-5":{"draws":4,"losses":20,"wins":0},"claude-opus-4-8":{"draws":2,"losses":18,"wins":2},"claude-opus-5":{"draws":0,"losses":2,"wins":0},"claude-sonnet-5":{"draws":2,"losses":10,"wins":6},"cohere/north-mini-code":{"draws":7,"losses":4,"wins":7},"deepseek/deepseek-v4-flash":{"draws":13,"losses":35,"wins":28},"deepseek/deepseek-v4-pro":{"draws":4,"losses":13,"wins":3},"google/gemini-3.1-flash-lite":{"draws":6,"losses":15,"wins":11},"google/gemini-3.5-flash":{"draws":4,"losses":6,"wins":0},"google/gemini-3.5-flash-lite":{"draws":4,"losses":11,"wins":7},"google/gemini-3.6-flash":{"draws":3,"losses":14,"wins":3},"google/gemma-4-31b-it":{"draws":3,"losses":9,"wins":8},"gpt-4.1":{"draws":0,"losses":0,"wins":4},"gpt-5":{"draws":0,"losses":14,"wins":4},"gpt-5.4":{"draws":1,"losses":15,"wins":0},"gpt-5.4-mini":{"draws":12,"losses":37,"wins":17},"gpt-5.4-nano":{"draws":13,"losses":43,"wins":32},"gpt-5.5":{"draws":2,"losses":12,"wins":0},"gpt-5.6-luna":{"draws":4,"losses":10,"wins":9},"gpt-5.6-sol":{"draws":0,"losses":19,"wins":1},"gpt-5.6-terra":{"draws":2,"losses":17,"wins":1},"inclusionai/ling-3.0-flash":{"draws":8,"losses":2,"wins":10},"meituan/longcat-2.0":{"draws":4,"losses":6,"wins":6},"minimax/minimax-m3":{"draws":0,"losses":10,"wins":4},"mistralai/mistral-medium-3-5":{"draws":0,"losses":6,"wins":6},"moonshotai/kimi-k3":{"draws":2,"losses":18,"wins":0},"nex-agi/nex-n2-pro":{"draws":2,"losses":5,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":16,"wins":8},"o3":{"draws":3,"losses":20,"wins":5},"openai/gpt-oss-120b":{"draws":8,"losses":8,"wins":2},"poolside/laguna-s-2.1":{"draws":0,"losses":4,"wins":2},"qwen/qwen3.7-max":{"draws":4,"losses":5,"wins":5},"qwen/qwen3.7-plus":{"draws":3,"losses":5,"wins":6},"stepfun/step-3.7-flash":{"draws":4,"losses":9,"wins":7},"tencent/hy3-preview":{"draws":2,"losses":11,"wins":7},"thinkingmachines/inkling":{"draws":5,"losses":7,"wins":14},"x-ai/grok-4.5":{"draws":0,"losses":26,"wins":0},"x-ai/grok-build-0.1":{"draws":2,"losses":4,"wins":0},"xiaomi/mimo-v2.5":{"draws":10,"losses":22,"wins":14},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":5,"wins":1},"z-ai/glm-5.2":{"draws":8,"losses":28,"wins":14}},"moonshotai/kimi-k2.7-code":{"claude-fable-5":{"draws":0,"losses":16,"wins":2},"claude-opus-4-5":{"draws":10,"losses":13,"wins":11},"claude-opus-4-8":{"draws":4,"losses":8,"wins":4},"claude-opus-5":{"draws":6,"losses":29,"wins":1},"claude-sonnet-5":{"draws":6,"losses":8,"wins":6},"cohere/north-mini-code":{"draws":3,"losses":4,"wins":3},"deepseek/deepseek-v4-flash":{"draws":5,"losses":4,"wins":7},"deepseek/deepseek-v4-pro":{"draws":4,"losses":3,"wins":1},"google/gemini-3.1-flash-lite":{"draws":6,"losses":0,"wins":8},"google/gemini-3.5-flash":{"draws":4,"losses":4,"wins":6},"google/gemini-3.5-flash-lite":{"draws":4,"losses":4,"wins":0},"google/gemini-3.6-flash":{"draws":5,"losses":9,"wins":2},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":10},"gpt-4.1":{"draws":4,"losses":1,"wins":1},"gpt-5":{"draws":4,"losses":9,"wins":5},"gpt-5.4":{"draws":8,"losses":6,"wins":6},"gpt-5.4-mini":{"draws":17,"losses":10,"wins":29},"gpt-5.4-nano":{"draws":13,"losses":14,"wins":29},"gpt-5.5":{"draws":9,"losses":5,"wins":6},"gpt-5.6-luna":{"draws":5,"losses":5,"wins":10},"gpt-5.6-sol":{"draws":2,"losses":11,"wins":3},"gpt-5.6-terra":{"draws":8,"losses":9,"wins":7},"inclusionai/ling-3.0-flash":{"draws":2,"losses":3,"wins":7},"meituan/longcat-2.0":{"draws":6,"losses":2,"wins":6},"minimax/minimax-m3":{"draws":5,"losses":1,"wins":10},"moonshotai/kimi-k3":{"draws":2,"losses":4,"wins":12},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":2,"wins":8},"o3":{"draws":1,"losses":4,"wins":7},"openai/gpt-oss-120b":{"draws":4,"losses":0,"wins":6},"poolside/laguna-s-2.1":{"draws":8,"losses":9,"wins":1},"qwen/qwen3.7-max":{"draws":4,"losses":4,"wins":4},"qwen/qwen3.7-plus":{"draws":8,"losses":2,"wins":6},"stepfun/step-3.7-flash":{"draws":6,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":2,"losses":2,"wins":2},"thinkingmachines/inkling":{"draws":2,"losses":5,"wins":7},"x-ai/grok-4.5":{"draws":5,"losses":26,"wins":1},"x-ai/grok-build-0.1":{"draws":3,"losses":1,"wins":8},"xiaomi/mimo-v2.5":{"draws":14,"losses":6,"wins":22},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":0,"wins":6},"z-ai/glm-5.2":{"draws":6,"losses":19,"wins":13}},"moonshotai/kimi-k3":{"claude-fable-5":{"draws":2,"losses":18,"wins":0},"claude-opus-4-5":{"draws":45,"losses":36,"wins":75},"claude-opus-4-8":{"draws":16,"losses":15,"wins":23},"claude-opus-5":{"draws":21,"losses":115,"wins":18},"claude-sonnet-5":{"draws":23,"losses":18,"wins":23},"cohere/north-mini-code":{"draws":8,"losses":8,"wins":18},"deepseek/deepseek-v4-flash":{"draws":27,"losses":6,"wins":55},"deepseek/deepseek-v4-pro":{"draws":6,"losses":7,"wins":21},"google/gemini-3.1-flash-lite":{"draws":5,"losses":1,"wins":8},"google/gemini-3.5-flash":{"draws":15,"losses":7,"wins":8},"google/gemini-3.5-flash-lite":{"draws":99,"losses":52,"wins":133},"google/gemini-3.6-flash":{"draws":70,"losses":136,"wins":120},"google/gemma-4-31b-it":{"draws":7,"losses":7,"wins":20},"gpt-4.1":{"draws":7,"losses":5,"wins":2},"gpt-4.1-nano":{"draws":5,"losses":0,"wins":3},"gpt-5":{"draws":7,"losses":5,"wins":8},"gpt-5.4":{"draws":18,"losses":23,"wins":17},"gpt-5.4-mini":{"draws":71,"losses":29,"wins":68},"gpt-5.4-nano":{"draws":45,"losses":21,"wins":88},"gpt-5.5":{"draws":27,"losses":14,"wins":15},"gpt-5.6-luna":{"draws":17,"losses":18,"wins":23},"gpt-5.6-sol":{"draws":13,"losses":32,"wins":15},"gpt-5.6-terra":{"draws":27,"losses":19,"wins":22},"inclusionai/ling-3.0-flash":{"draws":27,"losses":11,"wins":24},"meituan/longcat-2.0":{"draws":36,"losses":18,"wins":56},"minimax/minimax-m3":{"draws":10,"losses":7,"wins":19},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":12,"wins":4},"moonshotai/kimi-k3":{"draws":130,"losses":139,"wins":139},"nex-agi/nex-n2-pro":{"draws":10,"losses":5,"wins":21},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":7,"wins":7},"o3":{"draws":22,"losses":63,"wins":93},"openai/gpt-oss-120b":{"draws":20,"losses":5,"wins":37},"poolside/laguna-s-2.1":{"draws":49,"losses":14,"wins":47},"qwen/qwen3.7-max":{"draws":13,"losses":7,"wins":24},"qwen/qwen3.7-plus":{"draws":18,"losses":9,"wins":19},"stepfun/step-3.7-flash":{"draws":9,"losses":7,"wins":26},"tencent/hy3-preview":{"draws":9,"losses":6,"wins":17},"thinkingmachines/inkling":{"draws":44,"losses":17,"wins":67},"x-ai/grok-4.5":{"draws":126,"losses":166,"wins":131},"x-ai/grok-build-0.1":{"draws":7,"losses":3,"wins":12},"xiaomi/mimo-v2.5":{"draws":27,"losses":15,"wins":42},"xiaomi/mimo-v2.5-pro":{"draws":15,"losses":21,"wins":16},"z-ai/glm-5.2":{"draws":12,"losses":4,"wins":18}},"nex-agi/nex-n2-pro":{"claude-fable-5":{"draws":0,"losses":14,"wins":0},"claude-opus-4-5":{"draws":9,"losses":20,"wins":7},"claude-opus-4-8":{"draws":14,"losses":21,"wins":3},"claude-opus-5":{"draws":0,"losses":15,"wins":1},"claude-sonnet-5":{"draws":8,"losses":19,"wins":7},"cohere/north-mini-code":{"draws":9,"losses":10,"wins":13},"deepseek/deepseek-v4-flash":{"draws":30,"losses":25,"wins":37},"deepseek/deepseek-v4-pro":{"draws":6,"losses":8,"wins":8},"google/gemini-3.1-flash-lite":{"draws":4,"losses":11,"wins":15},"google/gemini-3.5-flash":{"draws":4,"losses":6,"wins":4},"google/gemini-3.5-flash-lite":{"draws":13,"losses":7,"wins":8},"google/gemini-3.6-flash":{"draws":15,"losses":11,"wins":4},"google/gemma-4-31b-it":{"draws":4,"losses":11,"wins":9},"gpt-4.1":{"draws":3,"losses":2,"wins":3},"gpt-5":{"draws":4,"losses":10,"wins":2},"gpt-5.4":{"draws":10,"losses":21,"wins":5},"gpt-5.4-mini":{"draws":34,"losses":42,"wins":28},"gpt-5.4-nano":{"draws":33,"losses":38,"wins":39},"gpt-5.5":{"draws":8,"losses":15,"wins":3},"gpt-5.6-luna":{"draws":18,"losses":14,"wins":14},"gpt-5.6-sol":{"draws":5,"losses":19,"wins":4},"gpt-5.6-terra":{"draws":10,"losses":16,"wins":6},"inclusionai/ling-3.0-flash":{"draws":20,"losses":8,"wins":12},"meituan/longcat-2.0":{"draws":11,"losses":14,"wins":13},"minimax/minimax-m3":{"draws":7,"losses":15,"wins":6},"mistralai/mistral-medium-3-5":{"draws":2,"losses":7,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":6,"wins":0},"moonshotai/kimi-k3":{"draws":10,"losses":21,"wins":5},"nex-agi/nex-n2-pro":{"draws":4,"losses":0,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":16,"wins":9},"o3":{"draws":2,"losses":11,"wins":3},"openai/gpt-oss-120b":{"draws":14,"losses":13,"wins":5},"poolside/laguna-s-2.1":{"draws":7,"losses":7,"wins":4},"qwen/qwen3.7-max":{"draws":7,"losses":14,"wins":3},"qwen/qwen3.7-plus":{"draws":6,"losses":8,"wins":8},"stepfun/step-3.7-flash":{"draws":5,"losses":6,"wins":7},"tencent/hy3-preview":{"draws":11,"losses":2,"wins":5},"thinkingmachines/inkling":{"draws":4,"losses":5,"wins":9},"x-ai/grok-4.5":{"draws":10,"losses":26,"wins":4},"x-ai/grok-build-0.1":{"draws":7,"losses":7,"wins":2},"xiaomi/mimo-v2.5":{"draws":18,"losses":29,"wins":19},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":10,"wins":6},"z-ai/glm-5.2":{"draws":26,"losses":23,"wins":11}},"nvidia/nemotron-3-ultra-550b-a55b":{"claude-fable-5":{"draws":4,"losses":27,"wins":1},"claude-opus-4-5":{"draws":35,"losses":29,"wins":16},"claude-opus-4-8":{"draws":14,"losses":31,"wins":11},"claude-opus-5":{"draws":11,"losses":43,"wins":0},"claude-sonnet-5":{"draws":38,"losses":25,"wins":15},"cohere/north-mini-code":{"draws":7,"losses":13,"wins":10},"deepseek/deepseek-v4-flash":{"draws":60,"losses":38,"wins":32},"deepseek/deepseek-v4-pro":{"draws":15,"losses":14,"wins":7},"google/gemini-3.1-flash-lite":{"draws":16,"losses":13,"wins":24},"google/gemini-3.5-flash":{"draws":11,"losses":20,"wins":3},"google/gemini-3.5-flash-lite":{"draws":13,"losses":8,"wins":11},"google/gemini-3.6-flash":{"draws":9,"losses":21,"wins":4},"google/gemma-4-31b-it":{"draws":6,"losses":13,"wins":7},"gpt-4.1":{"draws":6,"losses":7,"wins":5},"gpt-5":{"draws":17,"losses":15,"wins":6},"gpt-5.4":{"draws":16,"losses":27,"wins":3},"gpt-5.4-mini":{"draws":68,"losses":49,"wins":25},"gpt-5.4-nano":{"draws":73,"losses":51,"wins":32},"gpt-5.5":{"draws":22,"losses":23,"wins":5},"gpt-5.6-luna":{"draws":32,"losses":23,"wins":9},"gpt-5.6-sol":{"draws":6,"losses":38,"wins":8},"gpt-5.6-terra":{"draws":25,"losses":27,"wins":8},"inclusionai/ling-3.0-flash":{"draws":17,"losses":5,"wins":6},"meituan/longcat-2.0":{"draws":17,"losses":9,"wins":18},"minimax/minimax-m3":{"draws":16,"losses":9,"wins":11},"mistralai/mistral-medium-3-5":{"draws":6,"losses":8,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":8,"wins":2},"moonshotai/kimi-k3":{"draws":8,"losses":7,"wins":7},"nex-agi/nex-n2-pro":{"draws":15,"losses":9,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":7,"wins":7},"o3":{"draws":18,"losses":30,"wins":10},"openai/gpt-oss-120b":{"draws":21,"losses":11,"wins":8},"poolside/laguna-s-2.1":{"draws":15,"losses":9,"wins":6},"qwen/qwen3.7-max":{"draws":18,"losses":10,"wins":8},"qwen/qwen3.7-plus":{"draws":12,"losses":13,"wins":11},"stepfun/step-3.7-flash":{"draws":11,"losses":10,"wins":11},"tencent/hy3-preview":{"draws":20,"losses":14,"wins":6},"thinkingmachines/inkling":{"draws":19,"losses":15,"wins":24},"x-ai/grok-4.5":{"draws":15,"losses":44,"wins":7},"x-ai/grok-build-0.1":{"draws":18,"losses":8,"wins":8},"xiaomi/mimo-v2.5":{"draws":46,"losses":23,"wins":31},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":12,"wins":5},"z-ai/glm-5.2":{"draws":66,"losses":48,"wins":44}},"o3":{"claude-fable-5":{"draws":1,"losses":31,"wins":2},"claude-opus-4-5":{"draws":18,"losses":58,"wins":30},"claude-opus-4-8":{"draws":4,"losses":34,"wins":6},"claude-opus-5":{"draws":2,"losses":68,"wins":6},"claude-sonnet-5":{"draws":12,"losses":28,"wins":30},"cohere/north-mini-code":{"draws":12,"losses":4,"wins":6},"deepseek/deepseek-v4-flash":{"draws":14,"losses":28,"wins":36},"deepseek/deepseek-v4-pro":{"draws":11,"losses":16,"wins":15},"google/gemini-3.1-flash-lite":{"draws":10,"losses":2,"wins":24},"google/gemini-3.5-flash":{"draws":8,"losses":10,"wins":18},"google/gemini-3.5-flash-lite":{"draws":27,"losses":50,"wins":105},"google/gemini-3.6-flash":{"draws":30,"losses":76,"wins":56},"google/gemma-4-31b-it":{"draws":8,"losses":3,"wins":7},"gpt-4.1":{"draws":4,"losses":4,"wins":2},"gpt-4.1-nano":{"draws":0,"losses":4,"wins":2},"gpt-5":{"draws":6,"losses":20,"wins":16},"gpt-5.4":{"draws":7,"losses":28,"wins":7},"gpt-5.4-mini":{"draws":19,"losses":55,"wins":52},"gpt-5.4-nano":{"draws":26,"losses":42,"wins":62},"gpt-5.5":{"draws":12,"losses":34,"wins":6},"gpt-5.6-luna":{"draws":7,"losses":23,"wins":16},"gpt-5.6-sol":{"draws":4,"losses":28,"wins":10},"gpt-5.6-terra":{"draws":5,"losses":27,"wins":16},"inclusionai/ling-3.0-flash":{"draws":7,"losses":8,"wins":27},"meituan/longcat-2.0":{"draws":12,"losses":25,"wins":45},"minimax/minimax-m3":{"draws":5,"losses":3,"wins":12},"mistralai/mistral-medium-3-5":{"draws":3,"losses":5,"wins":20},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":7,"wins":4},"moonshotai/kimi-k3":{"draws":22,"losses":93,"wins":63},"nex-agi/nex-n2-pro":{"draws":2,"losses":3,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":10,"wins":30},"o3":{"draws":10,"losses":61,"wins":61},"openai/gpt-oss-120b":{"draws":14,"losses":11,"wins":29},"poolside/laguna-s-2.1":{"draws":20,"losses":18,"wins":26},"qwen/qwen3.7-max":{"draws":10,"losses":6,"wins":6},"qwen/qwen3.7-plus":{"draws":3,"losses":5,"wins":6},"stepfun/step-3.7-flash":{"draws":9,"losses":19,"wins":36},"tencent/hy3-preview":{"draws":10,"losses":14,"wins":12},"thinkingmachines/inkling":{"draws":19,"losses":21,"wins":43},"x-ai/grok-4.5":{"draws":19,"losses":126,"wins":47},"x-ai/grok-build-0.1":{"draws":3,"losses":0,"wins":9},"xiaomi/mimo-v2.5":{"draws":12,"losses":4,"wins":24},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":12,"wins":8},"z-ai/glm-5.2":{"draws":23,"losses":68,"wins":41}},"openai/gpt-oss-120b":{"claude-fable-5":{"draws":4,"losses":19,"wins":1},"claude-opus-4-5":{"draws":27,"losses":44,"wins":9},"claude-opus-4-8":{"draws":13,"losses":23,"wins":6},"claude-opus-5":{"draws":4,"losses":21,"wins":3},"claude-sonnet-5":{"draws":20,"losses":17,"wins":7},"cohere/north-mini-code":{"draws":16,"losses":8,"wins":6},"deepseek/deepseek-v4-flash":{"draws":36,"losses":24,"wins":36},"deepseek/deepseek-v4-pro":{"draws":8,"losses":8,"wins":8},"google/gemini-3.1-flash-lite":{"draws":11,"losses":7,"wins":14},"google/gemini-3.5-flash":{"draws":13,"losses":12,"wins":5},"google/gemini-3.5-flash-lite":{"draws":22,"losses":38,"wins":18},"google/gemini-3.6-flash":{"draws":16,"losses":33,"wins":4},"google/gemma-4-31b-it":{"draws":9,"losses":13,"wins":4},"gpt-4.1":{"draws":5,"losses":2,"wins":7},"gpt-4.1-nano":{"draws":0,"losses":1,"wins":1},"gpt-5":{"draws":14,"losses":6,"wins":2},"gpt-5.4":{"draws":12,"losses":29,"wins":3},"gpt-5.4-mini":{"draws":45,"losses":52,"wins":33},"gpt-5.4-nano":{"draws":63,"losses":43,"wins":36},"gpt-5.5":{"draws":21,"losses":18,"wins":3},"gpt-5.6-luna":{"draws":20,"losses":19,"wins":15},"gpt-5.6-sol":{"draws":14,"losses":28,"wins":4},"gpt-5.6-terra":{"draws":10,"losses":27,"wins":5},"inclusionai/ling-3.0-flash":{"draws":25,"losses":10,"wins":15},"meituan/longcat-2.0":{"draws":23,"losses":21,"wins":14},"minimax/minimax-m3":{"draws":9,"losses":13,"wins":6},"mistralai/mistral-medium-3-5":{"draws":8,"losses":2,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":6,"wins":0},"moonshotai/kimi-k3":{"draws":20,"losses":37,"wins":5},"nex-agi/nex-n2-pro":{"draws":14,"losses":5,"wins":13},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":21,"losses":8,"wins":11},"o3":{"draws":14,"losses":29,"wins":11},"openai/gpt-oss-120b":{"draws":10,"losses":1,"wins":1},"poolside/laguna-s-2.1":{"draws":17,"losses":13,"wins":14},"qwen/qwen3.7-max":{"draws":17,"losses":12,"wins":5},"qwen/qwen3.7-plus":{"draws":11,"losses":9,"wins":13},"stepfun/step-3.7-flash":{"draws":11,"losses":10,"wins":5},"tencent/hy3-preview":{"draws":13,"losses":10,"wins":3},"thinkingmachines/inkling":{"draws":17,"losses":22,"wins":21},"x-ai/grok-4.5":{"draws":15,"losses":44,"wins":11},"x-ai/grok-build-0.1":{"draws":9,"losses":11,"wins":2},"xiaomi/mimo-v2.5":{"draws":36,"losses":26,"wins":26},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":16,"wins":1},"z-ai/glm-5.2":{"draws":49,"losses":26,"wins":23}},"poolside/laguna-s-2.1":{"claude-fable-5":{"draws":0,"losses":4,"wins":6},"claude-opus-4-5":{"draws":29,"losses":24,"wins":5},"claude-opus-4-8":{"draws":12,"losses":23,"wins":5},"claude-opus-5":{"draws":8,"losses":66,"wins":8},"claude-sonnet-5":{"draws":24,"losses":26,"wins":10},"cohere/north-mini-code":{"draws":21,"losses":15,"wins":2},"deepseek/deepseek-v4-flash":{"draws":33,"losses":15,"wins":30},"deepseek/deepseek-v4-pro":{"draws":6,"losses":8,"wins":10},"google/gemini-3.1-flash-lite":{"draws":8,"losses":12,"wins":8},"google/gemini-3.5-flash":{"draws":10,"losses":7,"wins":7},"google/gemini-3.5-flash-lite":{"draws":60,"losses":38,"wins":44},"google/gemini-3.6-flash":{"draws":63,"losses":49,"wins":26},"google/gemma-4-31b-it":{"draws":4,"losses":11,"wins":9},"gpt-4.1":{"draws":6,"losses":10,"wins":6},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":4},"gpt-5":{"draws":11,"losses":6,"wins":9},"gpt-5.4":{"draws":12,"losses":17,"wins":3},"gpt-5.4-mini":{"draws":53,"losses":43,"wins":28},"gpt-5.4-nano":{"draws":48,"losses":21,"wins":37},"gpt-5.5":{"draws":15,"losses":13,"wins":14},"gpt-5.6-luna":{"draws":23,"losses":7,"wins":12},"gpt-5.6-sol":{"draws":0,"losses":16,"wins":12},"gpt-5.6-terra":{"draws":23,"losses":12,"wins":15},"inclusionai/ling-3.0-flash":{"draws":47,"losses":14,"wins":31},"meituan/longcat-2.0":{"draws":46,"losses":26,"wins":32},"minimax/minimax-m3":{"draws":13,"losses":9,"wins":14},"mistralai/mistral-medium-3-5":{"draws":0,"losses":2,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":1,"wins":9},"moonshotai/kimi-k3":{"draws":49,"losses":47,"wins":14},"nex-agi/nex-n2-pro":{"draws":7,"losses":4,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":6,"wins":9},"o3":{"draws":20,"losses":26,"wins":18},"openai/gpt-oss-120b":{"draws":17,"losses":14,"wins":13},"poolside/laguna-s-2.1":{"draws":42,"losses":23,"wins":23},"qwen/qwen3.7-max":{"draws":9,"losses":10,"wins":5},"qwen/qwen3.7-plus":{"draws":15,"losses":3,"wins":8},"stepfun/step-3.7-flash":{"draws":2,"losses":16,"wins":6},"tencent/hy3-preview":{"draws":6,"losses":9,"wins":7},"thinkingmachines/inkling":{"draws":34,"losses":25,"wins":41},"x-ai/grok-4.5":{"draws":38,"losses":95,"wins":21},"x-ai/grok-build-0.1":{"draws":12,"losses":10,"wins":6},"xiaomi/mimo-v2.5":{"draws":23,"losses":19,"wins":24},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":12,"wins":9},"z-ai/glm-5.2":{"draws":40,"losses":34,"wins":35}},"qwen/qwen3.7-max":{"claude-fable-5":{"draws":3,"losses":17,"wins":4},"claude-opus-4-5":{"draws":22,"losses":28,"wins":14},"claude-opus-4-8":{"draws":12,"losses":17,"wins":11},"claude-opus-5":{"draws":12,"losses":55,"wins":7},"claude-sonnet-5":{"draws":23,"losses":10,"wins":11},"cohere/north-mini-code":{"draws":9,"losses":4,"wins":17},"deepseek/deepseek-v4-flash":{"draws":26,"losses":12,"wins":24},"deepseek/deepseek-v4-pro":{"draws":11,"losses":11,"wins":6},"google/gemini-3.1-flash-lite":{"draws":9,"losses":5,"wins":10},"google/gemini-3.5-flash":{"draws":8,"losses":9,"wins":9},"google/gemini-3.5-flash-lite":{"draws":7,"losses":7,"wins":4},"google/gemini-3.6-flash":{"draws":6,"losses":21,"wins":3},"google/gemma-4-31b-it":{"draws":3,"losses":5,"wins":14},"gpt-4.1":{"draws":7,"losses":0,"wins":3},"gpt-5":{"draws":10,"losses":10,"wins":4},"gpt-5.4":{"draws":9,"losses":26,"wins":7},"gpt-5.4-mini":{"draws":44,"losses":33,"wins":51},"gpt-5.4-nano":{"draws":52,"losses":21,"wins":49},"gpt-5.5":{"draws":17,"losses":16,"wins":11},"gpt-5.6-luna":{"draws":22,"losses":15,"wins":11},"gpt-5.6-sol":{"draws":6,"losses":23,"wins":9},"gpt-5.6-terra":{"draws":12,"losses":14,"wins":8},"inclusionai/ling-3.0-flash":{"draws":21,"losses":5,"wins":10},"meituan/longcat-2.0":{"draws":18,"losses":4,"wins":16},"minimax/minimax-m3":{"draws":13,"losses":7,"wins":12},"mistralai/mistral-medium-3-5":{"draws":4,"losses":5,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":4,"wins":4},"moonshotai/kimi-k3":{"draws":13,"losses":24,"wins":7},"nex-agi/nex-n2-pro":{"draws":7,"losses":3,"wins":14},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":8,"wins":10},"o3":{"draws":10,"losses":6,"wins":6},"openai/gpt-oss-120b":{"draws":17,"losses":5,"wins":12},"poolside/laguna-s-2.1":{"draws":9,"losses":5,"wins":10},"qwen/qwen3.7-max":{"draws":4,"losses":4,"wins":4},"qwen/qwen3.7-plus":{"draws":11,"losses":9,"wins":14},"stepfun/step-3.7-flash":{"draws":9,"losses":5,"wins":12},"tencent/hy3-preview":{"draws":9,"losses":3,"wins":8},"thinkingmachines/inkling":{"draws":11,"losses":3,"wins":10},"x-ai/grok-4.5":{"draws":19,"losses":32,"wins":15},"x-ai/grok-build-0.1":{"draws":6,"losses":8,"wins":4},"xiaomi/mimo-v2.5":{"draws":28,"losses":19,"wins":31},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":4,"wins":17},"z-ai/glm-5.2":{"draws":35,"losses":41,"wins":22}},"qwen/qwen3.7-plus":{"claude-fable-5":{"draws":1,"losses":14,"wins":1},"claude-opus-4-5":{"draws":23,"losses":18,"wins":11},"claude-opus-4-8":{"draws":12,"losses":20,"wins":6},"claude-opus-5":{"draws":4,"losses":20,"wins":2},"claude-sonnet-5":{"draws":11,"losses":8,"wins":5},"cohere/north-mini-code":{"draws":7,"losses":9,"wins":14},"deepseek/deepseek-v4-flash":{"draws":22,"losses":30,"wins":28},"deepseek/deepseek-v4-pro":{"draws":6,"losses":8,"wins":0},"google/gemini-3.1-flash-lite":{"draws":9,"losses":6,"wins":17},"google/gemini-3.5-flash":{"draws":4,"losses":13,"wins":1},"google/gemini-3.5-flash-lite":{"draws":12,"losses":3,"wins":9},"google/gemini-3.6-flash":{"draws":12,"losses":21,"wins":3},"google/gemma-4-31b-it":{"draws":1,"losses":12,"wins":7},"gpt-4.1":{"draws":2,"losses":2,"wins":2},"gpt-5":{"draws":2,"losses":5,"wins":5},"gpt-5.4":{"draws":10,"losses":19,"wins":3},"gpt-5.4-mini":{"draws":41,"losses":21,"wins":40},"gpt-5.4-nano":{"draws":35,"losses":30,"wins":57},"gpt-5.5":{"draws":13,"losses":13,"wins":4},"gpt-5.6-luna":{"draws":11,"losses":10,"wins":11},"gpt-5.6-sol":{"draws":10,"losses":13,"wins":7},"gpt-5.6-terra":{"draws":15,"losses":14,"wins":13},"inclusionai/ling-3.0-flash":{"draws":13,"losses":8,"wins":9},"meituan/longcat-2.0":{"draws":9,"losses":7,"wins":8},"minimax/minimax-m3":{"draws":6,"losses":11,"wins":11},"mistralai/mistral-medium-3-5":{"draws":3,"losses":6,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":6,"wins":2},"moonshotai/kimi-k3":{"draws":18,"losses":19,"wins":9},"nex-agi/nex-n2-pro":{"draws":6,"losses":8,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":11,"wins":13},"o3":{"draws":3,"losses":6,"wins":5},"openai/gpt-oss-120b":{"draws":11,"losses":13,"wins":9},"poolside/laguna-s-2.1":{"draws":15,"losses":8,"wins":3},"qwen/qwen3.7-max":{"draws":11,"losses":14,"wins":9},"qwen/qwen3.7-plus":{"draws":4,"losses":4,"wins":4},"stepfun/step-3.7-flash":{"draws":4,"losses":8,"wins":10},"tencent/hy3-preview":{"draws":5,"losses":11,"wins":4},"thinkingmachines/inkling":{"draws":7,"losses":8,"wins":13},"x-ai/grok-4.5":{"draws":6,"losses":33,"wins":3},"x-ai/grok-build-0.1":{"draws":6,"losses":2,"wins":10},"xiaomi/mimo-v2.5":{"draws":23,"losses":25,"wins":20},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":13,"wins":3},"z-ai/glm-5.2":{"draws":36,"losses":28,"wins":16}},"stepfun/step-3.7-flash":{"claude-fable-5":{"draws":3,"losses":19,"wins":0},"claude-opus-4-5":{"draws":14,"losses":36,"wins":10},"claude-opus-4-8":{"draws":7,"losses":21,"wins":8},"claude-opus-5":{"draws":5,"losses":26,"wins":1},"claude-sonnet-5":{"draws":13,"losses":22,"wins":5},"cohere/north-mini-code":{"draws":4,"losses":3,"wins":11},"deepseek/deepseek-v4-flash":{"draws":18,"losses":31,"wins":39},"deepseek/deepseek-v4-pro":{"draws":6,"losses":13,"wins":3},"google/gemini-3.1-flash-lite":{"draws":6,"losses":5,"wins":19},"google/gemini-3.5-flash":{"draws":5,"losses":10,"wins":3},"google/gemini-3.5-flash-lite":{"draws":11,"losses":18,"wins":25},"google/gemini-3.6-flash":{"draws":5,"losses":22,"wins":4},"google/gemma-4-31b-it":{"draws":3,"losses":2,"wins":13},"gpt-4.1":{"draws":0,"losses":3,"wins":3},"gpt-5":{"draws":8,"losses":14,"wins":0},"gpt-5.4":{"draws":5,"losses":15,"wins":4},"gpt-5.4-mini":{"draws":29,"losses":38,"wins":29},"gpt-5.4-nano":{"draws":33,"losses":39,"wins":24},"gpt-5.5":{"draws":6,"losses":18,"wins":2},"gpt-5.6-luna":{"draws":7,"losses":17,"wins":10},"gpt-5.6-sol":{"draws":3,"losses":23,"wins":4},"gpt-5.6-terra":{"draws":11,"losses":15,"wins":4},"inclusionai/ling-3.0-flash":{"draws":4,"losses":6,"wins":14},"meituan/longcat-2.0":{"draws":5,"losses":15,"wins":22},"minimax/minimax-m3":{"draws":5,"losses":10,"wins":3},"mistralai/mistral-medium-3-5":{"draws":4,"losses":7,"wins":9},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":9,"losses":26,"wins":7},"nex-agi/nex-n2-pro":{"draws":5,"losses":7,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":11,"wins":10},"o3":{"draws":9,"losses":36,"wins":19},"openai/gpt-oss-120b":{"draws":11,"losses":5,"wins":10},"poolside/laguna-s-2.1":{"draws":2,"losses":6,"wins":16},"qwen/qwen3.7-max":{"draws":9,"losses":12,"wins":5},"qwen/qwen3.7-plus":{"draws":4,"losses":10,"wins":8},"tencent/hy3-preview":{"draws":6,"losses":5,"wins":9},"thinkingmachines/inkling":{"draws":10,"losses":16,"wins":28},"x-ai/grok-4.5":{"draws":6,"losses":41,"wins":5},"x-ai/grok-build-0.1":{"draws":6,"losses":4,"wins":0},"xiaomi/mimo-v2.5":{"draws":28,"losses":15,"wins":15},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":9,"wins":6},"z-ai/glm-5.2":{"draws":6,"losses":35,"wins":17}},"tencent/hy3-preview":{"claude-fable-5":{"draws":1,"losses":20,"wins":5},"claude-opus-4-5":{"draws":17,"losses":19,"wins":8},"claude-opus-4-8":{"draws":11,"losses":17,"wins":10},"claude-opus-5":{"draws":11,"losses":48,"wins":7},"claude-sonnet-5":{"draws":16,"losses":12,"wins":10},"cohere/north-mini-code":{"draws":3,"losses":2,"wins":9},"deepseek/deepseek-v4-flash":{"draws":35,"losses":23,"wins":34},"deepseek/deepseek-v4-pro":{"draws":7,"losses":11,"wins":8},"google/gemini-3.1-flash-lite":{"draws":4,"losses":6,"wins":10},"google/gemini-3.5-flash":{"draws":4,"losses":10,"wins":2},"google/gemini-3.5-flash-lite":{"draws":9,"losses":3,"wins":8},"google/gemini-3.6-flash":{"draws":11,"losses":18,"wins":11},"google/gemma-4-31b-it":{"draws":7,"losses":4,"wins":7},"gpt-4.1":{"draws":11,"losses":6,"wins":3},"gpt-5":{"draws":5,"losses":9,"wins":8},"gpt-5.4":{"draws":17,"losses":23,"wins":4},"gpt-5.4-mini":{"draws":32,"losses":35,"wins":25},"gpt-5.4-nano":{"draws":43,"losses":20,"wins":39},"gpt-5.5":{"draws":24,"losses":17,"wins":5},"gpt-5.6-luna":{"draws":13,"losses":16,"wins":15},"gpt-5.6-sol":{"draws":13,"losses":25,"wins":10},"gpt-5.6-terra":{"draws":14,"losses":12,"wins":8},"inclusionai/ling-3.0-flash":{"draws":11,"losses":2,"wins":11},"meituan/longcat-2.0":{"draws":11,"losses":6,"wins":7},"minimax/minimax-m3":{"draws":8,"losses":5,"wins":9},"mistralai/mistral-medium-3-5":{"draws":2,"losses":7,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":2},"moonshotai/kimi-k3":{"draws":9,"losses":17,"wins":6},"nex-agi/nex-n2-pro":{"draws":11,"losses":5,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":20,"losses":6,"wins":14},"o3":{"draws":10,"losses":12,"wins":14},"openai/gpt-oss-120b":{"draws":13,"losses":3,"wins":10},"poolside/laguna-s-2.1":{"draws":6,"losses":7,"wins":9},"qwen/qwen3.7-max":{"draws":9,"losses":8,"wins":3},"qwen/qwen3.7-plus":{"draws":5,"losses":4,"wins":11},"stepfun/step-3.7-flash":{"draws":6,"losses":9,"wins":5},"tencent/hy3-preview":{"draws":2,"losses":1,"wins":1},"thinkingmachines/inkling":{"draws":4,"losses":11,"wins":9},"x-ai/grok-4.5":{"draws":12,"losses":36,"wins":10},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":4},"xiaomi/mimo-v2.5":{"draws":16,"losses":17,"wins":17},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":3,"wins":10},"z-ai/glm-5.2":{"draws":46,"losses":34,"wins":28}},"thinkingmachines/inkling":{"claude-fable-5":{"draws":4,"losses":10,"wins":0},"claude-opus-4-5":{"draws":28,"losses":43,"wins":11},"claude-opus-4-8":{"draws":8,"losses":24,"wins":6},"claude-opus-5":{"draws":9,"losses":52,"wins":11},"claude-sonnet-5":{"draws":27,"losses":28,"wins":9},"cohere/north-mini-code":{"draws":9,"losses":16,"wins":11},"deepseek/deepseek-v4-flash":{"draws":34,"losses":35,"wins":35},"deepseek/deepseek-v4-pro":{"draws":12,"losses":14,"wins":4},"google/gemini-3.1-flash-lite":{"draws":11,"losses":11,"wins":24},"google/gemini-3.5-flash":{"draws":10,"losses":18,"wins":4},"google/gemini-3.5-flash-lite":{"draws":48,"losses":63,"wins":43},"google/gemini-3.6-flash":{"draws":64,"losses":67,"wins":23},"google/gemma-4-31b-it":{"draws":4,"losses":14,"wins":10},"gpt-4.1":{"draws":4,"losses":5,"wins":9},"gpt-4.1-nano":{"draws":0,"losses":8,"wins":0},"gpt-5":{"draws":12,"losses":13,"wins":5},"gpt-5.4":{"draws":16,"losses":15,"wins":9},"gpt-5.4-mini":{"draws":55,"losses":59,"wins":44},"gpt-5.4-nano":{"draws":42,"losses":43,"wins":48},"gpt-5.5":{"draws":15,"losses":22,"wins":11},"gpt-5.6-luna":{"draws":18,"losses":14,"wins":10},"gpt-5.6-sol":{"draws":10,"losses":16,"wins":8},"gpt-5.6-terra":{"draws":21,"losses":13,"wins":12},"inclusionai/ling-3.0-flash":{"draws":33,"losses":27,"wins":32},"meituan/longcat-2.0":{"draws":24,"losses":33,"wins":43},"minimax/minimax-m3":{"draws":6,"losses":14,"wins":12},"mistralai/mistral-medium-3-5":{"draws":5,"losses":14,"wins":7},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":7,"wins":5},"moonshotai/kimi-k3":{"draws":44,"losses":67,"wins":17},"nex-agi/nex-n2-pro":{"draws":4,"losses":9,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":19,"losses":24,"wins":15},"o3":{"draws":19,"losses":43,"wins":21},"openai/gpt-oss-120b":{"draws":17,"losses":21,"wins":22},"poolside/laguna-s-2.1":{"draws":34,"losses":41,"wins":25},"qwen/qwen3.7-max":{"draws":11,"losses":10,"wins":3},"qwen/qwen3.7-plus":{"draws":7,"losses":13,"wins":8},"stepfun/step-3.7-flash":{"draws":10,"losses":28,"wins":16},"tencent/hy3-preview":{"draws":4,"losses":9,"wins":11},"thinkingmachines/inkling":{"draws":14,"losses":21,"wins":21},"x-ai/grok-4.5":{"draws":37,"losses":64,"wins":23},"x-ai/grok-build-0.1":{"draws":4,"losses":6,"wins":4},"xiaomi/mimo-v2.5":{"draws":20,"losses":42,"wins":16},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":12,"wins":4},"z-ai/glm-5.2":{"draws":36,"losses":48,"wins":32}},"x-ai/grok-4.5":{"claude-fable-5":{"draws":15,"losses":58,"wins":23},"claude-opus-4-5":{"draws":65,"losses":55,"wins":106},"claude-opus-4-8":{"draws":21,"losses":38,"wins":59},"claude-opus-5":{"draws":31,"losses":165,"wins":60},"claude-sonnet-5":{"draws":33,"losses":22,"wins":51},"cohere/north-mini-code":{"draws":11,"losses":2,"wins":27},"deepseek/deepseek-v4-flash":{"draws":21,"losses":15,"wins":68},"deepseek/deepseek-v4-pro":{"draws":10,"losses":9,"wins":39},"google/gemini-3.1-flash-lite":{"draws":12,"losses":1,"wins":29},"google/gemini-3.5-flash":{"draws":11,"losses":29,"wins":24},"google/gemini-3.5-flash-lite":{"draws":57,"losses":59,"wins":132},"google/gemini-3.6-flash":{"draws":62,"losses":132,"wins":142},"google/gemma-4-31b-it":{"draws":8,"losses":2,"wins":20},"gpt-4.1":{"draws":9,"losses":7,"wins":24},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":15,"losses":11,"wins":40},"gpt-5.4":{"draws":25,"losses":54,"wins":31},"gpt-5.4-mini":{"draws":63,"losses":33,"wins":132},"gpt-5.4-nano":{"draws":44,"losses":57,"wins":169},"gpt-5.5":{"draws":38,"losses":34,"wins":48},"gpt-5.6-luna":{"draws":22,"losses":25,"wins":57},"gpt-5.6-sol":{"draws":20,"losses":56,"wins":56},"gpt-5.6-terra":{"draws":26,"losses":28,"wins":66},"inclusionai/ling-3.0-flash":{"draws":30,"losses":9,"wins":53},"meituan/longcat-2.0":{"draws":36,"losses":27,"wins":93},"minimax/minimax-m3":{"draws":6,"losses":3,"wins":31},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":26},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":1,"wins":26},"moonshotai/kimi-k3":{"draws":126,"losses":131,"wins":166},"nex-agi/nex-n2-pro":{"draws":10,"losses":4,"wins":26},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":7,"wins":44},"o3":{"draws":19,"losses":47,"wins":126},"openai/gpt-oss-120b":{"draws":15,"losses":11,"wins":44},"poolside/laguna-s-2.1":{"draws":38,"losses":21,"wins":95},"qwen/qwen3.7-max":{"draws":19,"losses":15,"wins":32},"qwen/qwen3.7-plus":{"draws":6,"losses":3,"wins":33},"stepfun/step-3.7-flash":{"draws":6,"losses":5,"wins":41},"tencent/hy3-preview":{"draws":12,"losses":10,"wins":36},"thinkingmachines/inkling":{"draws":37,"losses":23,"wins":64},"x-ai/grok-4.5":{"draws":102,"losses":159,"wins":159},"x-ai/grok-build-0.1":{"draws":9,"losses":1,"wins":26},"xiaomi/mimo-v2.5":{"draws":25,"losses":9,"wins":64},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":24,"wins":28},"z-ai/glm-5.2":{"draws":26,"losses":40,"wins":90}},"x-ai/grok-build-0.1":{"claude-fable-5":{"draws":2,"losses":11,"wins":3},"claude-opus-4-5":{"draws":13,"losses":11,"wins":6},"claude-opus-4-8":{"draws":9,"losses":9,"wins":6},"claude-opus-5":{"draws":6,"losses":10,"wins":2},"claude-sonnet-5":{"draws":9,"losses":14,"wins":1},"cohere/north-mini-code":{"draws":4,"losses":3,"wins":7},"deepseek/deepseek-v4-flash":{"draws":16,"losses":9,"wins":11},"deepseek/deepseek-v4-pro":{"draws":8,"losses":3,"wins":1},"google/gemini-3.1-flash-lite":{"draws":9,"losses":2,"wins":13},"google/gemini-3.5-flash":{"draws":8,"losses":9,"wins":1},"google/gemini-3.5-flash-lite":{"draws":10,"losses":2,"wins":10},"google/gemini-3.6-flash":{"draws":6,"losses":6,"wins":0},"google/gemma-4-31b-it":{"draws":7,"losses":5,"wins":8},"gpt-4.1":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":7,"losses":11,"wins":4},"gpt-5.4":{"draws":8,"losses":13,"wins":5},"gpt-5.4-mini":{"draws":20,"losses":21,"wins":23},"gpt-5.4-nano":{"draws":21,"losses":25,"wins":24},"gpt-5.5":{"draws":15,"losses":5,"wins":6},"gpt-5.6-luna":{"draws":19,"losses":12,"wins":1},"gpt-5.6-sol":{"draws":6,"losses":14,"wins":6},"gpt-5.6-terra":{"draws":12,"losses":10,"wins":2},"inclusionai/ling-3.0-flash":{"draws":7,"losses":0,"wins":11},"meituan/longcat-2.0":{"draws":9,"losses":8,"wins":13},"minimax/minimax-m3":{"draws":8,"losses":6,"wins":8},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":8,"wins":1},"moonshotai/kimi-k3":{"draws":7,"losses":12,"wins":3},"nex-agi/nex-n2-pro":{"draws":7,"losses":2,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":8,"wins":8},"o3":{"draws":3,"losses":9,"wins":0},"openai/gpt-oss-120b":{"draws":9,"losses":2,"wins":11},"poolside/laguna-s-2.1":{"draws":12,"losses":6,"wins":10},"qwen/qwen3.7-max":{"draws":6,"losses":4,"wins":8},"qwen/qwen3.7-plus":{"draws":6,"losses":10,"wins":2},"stepfun/step-3.7-flash":{"draws":6,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":0,"losses":4,"wins":0},"thinkingmachines/inkling":{"draws":4,"losses":4,"wins":6},"x-ai/grok-4.5":{"draws":9,"losses":26,"wins":1},"xiaomi/mimo-v2.5":{"draws":24,"losses":10,"wins":18},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":8,"wins":0},"z-ai/glm-5.2":{"draws":10,"losses":11,"wins":11}},"xiaomi/mimo-v2.5":{"claude-fable-5":{"draws":5,"losses":41,"wins":2},"claude-opus-4-5":{"draws":62,"losses":55,"wins":33},"claude-opus-4-8":{"draws":38,"losses":46,"wins":12},"claude-opus-5":{"draws":9,"losses":50,"wins":3},"claude-sonnet-5":{"draws":61,"losses":41,"wins":14},"cohere/north-mini-code":{"draws":27,"losses":15,"wins":24},"deepseek/deepseek-v4-flash":{"draws":82,"losses":58,"wins":80},"deepseek/deepseek-v4-pro":{"draws":16,"losses":25,"wins":11},"google/gemini-3.1-flash-lite":{"draws":35,"losses":25,"wins":42},"google/gemini-3.5-flash":{"draws":28,"losses":25,"wins":9},"google/gemini-3.5-flash-lite":{"draws":11,"losses":12,"wins":17},"google/gemini-3.6-flash":{"draws":20,"losses":17,"wins":11},"google/gemma-4-31b-it":{"draws":17,"losses":27,"wins":26},"gpt-4.1":{"draws":13,"losses":13,"wins":10},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":31,"losses":23,"wins":18},"gpt-5.4":{"draws":36,"losses":45,"wins":9},"gpt-5.4-mini":{"draws":139,"losses":88,"wins":103},"gpt-5.4-nano":{"draws":141,"losses":113,"wins":110},"gpt-5.5":{"draws":37,"losses":33,"wins":10},"gpt-5.6-luna":{"draws":37,"losses":30,"wins":37},"gpt-5.6-sol":{"draws":27,"losses":53,"wins":14},"gpt-5.6-terra":{"draws":45,"losses":35,"wins":16},"inclusionai/ling-3.0-flash":{"draws":30,"losses":16,"wins":24},"meituan/longcat-2.0":{"draws":23,"losses":32,"wins":29},"minimax/minimax-m3":{"draws":28,"losses":30,"wins":26},"mistralai/mistral-medium-3-5":{"draws":10,"losses":14,"wins":22},"moonshotai/kimi-k2.7-code":{"draws":14,"losses":22,"wins":6},"moonshotai/kimi-k3":{"draws":27,"losses":42,"wins":15},"nex-agi/nex-n2-pro":{"draws":18,"losses":19,"wins":29},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":46,"losses":31,"wins":23},"o3":{"draws":12,"losses":24,"wins":4},"openai/gpt-oss-120b":{"draws":36,"losses":26,"wins":26},"poolside/laguna-s-2.1":{"draws":23,"losses":24,"wins":19},"qwen/qwen3.7-max":{"draws":28,"losses":31,"wins":19},"qwen/qwen3.7-plus":{"draws":23,"losses":20,"wins":25},"stepfun/step-3.7-flash":{"draws":28,"losses":15,"wins":15},"tencent/hy3-preview":{"draws":16,"losses":17,"wins":17},"thinkingmachines/inkling":{"draws":20,"losses":16,"wins":42},"x-ai/grok-4.5":{"draws":25,"losses":64,"wins":9},"x-ai/grok-build-0.1":{"draws":24,"losses":18,"wins":10},"xiaomi/mimo-v2.5":{"draws":76,"losses":56,"wins":56},"xiaomi/mimo-v2.5-pro":{"draws":22,"losses":32,"wins":22},"z-ai/glm-5.2":{"draws":93,"losses":90,"wins":55}},"xiaomi/mimo-v2.5-pro":{"claude-fable-5":{"draws":0,"losses":20,"wins":0},"claude-opus-4-5":{"draws":8,"losses":21,"wins":21},"claude-opus-4-8":{"draws":9,"losses":18,"wins":11},"claude-opus-5":{"draws":11,"losses":40,"wins":1},"claude-sonnet-5":{"draws":13,"losses":13,"wins":16},"cohere/north-mini-code":{"draws":5,"losses":6,"wins":11},"deepseek/deepseek-v4-flash":{"draws":22,"losses":23,"wins":29},"deepseek/deepseek-v4-pro":{"draws":3,"losses":7,"wins":6},"google/gemini-3.1-flash-lite":{"draws":5,"losses":2,"wins":19},"google/gemini-3.5-flash":{"draws":5,"losses":9,"wins":4},"google/gemini-3.5-flash-lite":{"draws":2,"losses":11,"wins":9},"google/gemini-3.6-flash":{"draws":5,"losses":16,"wins":5},"google/gemma-4-31b-it":{"draws":2,"losses":5,"wins":13},"gpt-4.1":{"draws":2,"losses":12,"wins":6},"gpt-5":{"draws":5,"losses":8,"wins":5},"gpt-5.4":{"draws":8,"losses":27,"wins":9},"gpt-5.4-mini":{"draws":26,"losses":32,"wins":32},"gpt-5.4-nano":{"draws":30,"losses":29,"wins":55},"gpt-5.5":{"draws":12,"losses":12,"wins":8},"gpt-5.6-luna":{"draws":9,"losses":7,"wins":16},"gpt-5.6-sol":{"draws":8,"losses":21,"wins":5},"gpt-5.6-terra":{"draws":13,"losses":13,"wins":8},"inclusionai/ling-3.0-flash":{"draws":5,"losses":8,"wins":13},"meituan/longcat-2.0":{"draws":10,"losses":14,"wins":18},"minimax/minimax-m3":{"draws":7,"losses":9,"wins":14},"mistralai/mistral-medium-3-5":{"draws":2,"losses":1,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":6,"wins":0},"moonshotai/kimi-k3":{"draws":15,"losses":16,"wins":21},"nex-agi/nex-n2-pro":{"draws":4,"losses":6,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":5,"wins":12},"o3":{"draws":4,"losses":8,"wins":12},"openai/gpt-oss-120b":{"draws":9,"losses":1,"wins":16},"poolside/laguna-s-2.1":{"draws":5,"losses":9,"wins":12},"qwen/qwen3.7-max":{"draws":9,"losses":17,"wins":4},"qwen/qwen3.7-plus":{"draws":8,"losses":3,"wins":13},"stepfun/step-3.7-flash":{"draws":3,"losses":6,"wins":9},"tencent/hy3-preview":{"draws":3,"losses":10,"wins":3},"thinkingmachines/inkling":{"draws":2,"losses":4,"wins":12},"x-ai/grok-4.5":{"draws":8,"losses":28,"wins":24},"x-ai/grok-build-0.1":{"draws":4,"losses":0,"wins":8},"xiaomi/mimo-v2.5":{"draws":22,"losses":22,"wins":32},"z-ai/glm-5.2":{"draws":18,"losses":37,"wins":19}},"z-ai/glm-5.2":{"claude-fable-5":{"draws":10,"losses":71,"wins":19},"claude-opus-4-5":{"draws":67,"losses":90,"wins":91},"claude-opus-4-8":{"draws":46,"losses":81,"wins":49},"claude-opus-5":{"draws":40,"losses":207,"wins":27},"claude-sonnet-5":{"draws":74,"losses":72,"wins":78},"cohere/north-mini-code":{"draws":26,"losses":13,"wins":17},"deepseek/deepseek-v4-flash":{"draws":129,"losses":78,"wins":101},"deepseek/deepseek-v4-pro":{"draws":29,"losses":50,"wins":33},"google/gemini-3.1-flash-lite":{"draws":37,"losses":17,"wins":54},"google/gemini-3.5-flash":{"draws":22,"losses":42,"wins":38},"google/gemini-3.5-flash-lite":{"draws":33,"losses":17,"wins":30},"google/gemini-3.6-flash":{"draws":27,"losses":35,"wins":22},"google/gemma-4-31b-it":{"draws":21,"losses":13,"wins":16},"gpt-4.1":{"draws":20,"losses":22,"wins":26},"gpt-5":{"draws":48,"losses":47,"wins":49},"gpt-5.4":{"draws":74,"losses":68,"wins":36},"gpt-5.4-mini":{"draws":162,"losses":117,"wins":145},"gpt-5.4-nano":{"draws":165,"losses":125,"wins":159},"gpt-5.5":{"draws":54,"losses":68,"wins":38},"gpt-5.6-luna":{"draws":56,"losses":49,"wins":57},"gpt-5.6-sol":{"draws":34,"losses":87,"wins":51},"gpt-5.6-terra":{"draws":54,"losses":58,"wins":54},"inclusionai/ling-3.0-flash":{"draws":48,"losses":10,"wins":10},"meituan/longcat-2.0":{"draws":46,"losses":20,"wins":44},"minimax/minimax-m3":{"draws":28,"losses":17,"wins":19},"mistralai/mistral-medium-3-5":{"draws":8,"losses":14,"wins":28},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":13,"wins":19},"moonshotai/kimi-k3":{"draws":12,"losses":18,"wins":4},"nex-agi/nex-n2-pro":{"draws":26,"losses":11,"wins":23},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":66,"losses":44,"wins":48},"o3":{"draws":23,"losses":41,"wins":68},"openai/gpt-oss-120b":{"draws":49,"losses":23,"wins":26},"poolside/laguna-s-2.1":{"draws":40,"losses":35,"wins":34},"qwen/qwen3.7-max":{"draws":35,"losses":22,"wins":41},"qwen/qwen3.7-plus":{"draws":36,"losses":16,"wins":28},"stepfun/step-3.7-flash":{"draws":6,"losses":17,"wins":35},"tencent/hy3-preview":{"draws":46,"losses":28,"wins":34},"thinkingmachines/inkling":{"draws":36,"losses":32,"wins":48},"x-ai/grok-4.5":{"draws":26,"losses":90,"wins":40},"x-ai/grok-build-0.1":{"draws":10,"losses":11,"wins":11},"xiaomi/mimo-v2.5":{"draws":93,"losses":55,"wins":90},"xiaomi/mimo-v2.5-pro":{"draws":18,"losses":19,"wins":37},"z-ai/glm-5.2":{"draws":168,"losses":184,"wins":184}}},"versus_totals_tracks":{"highest":{"claude-fable-5":{"claude-fable-5":{"draws":2,"losses":2,"wins":10},"claude-opus-4-5":{"draws":4,"losses":4,"wins":24},"claude-opus-4-8":{"draws":3,"losses":10,"wins":17},"claude-opus-5":{"draws":17,"losses":30,"wins":43},"claude-sonnet-5":{"draws":8,"losses":0,"wins":20},"deepseek/deepseek-v4-flash":{"draws":4,"losses":2,"wins":28},"deepseek/deepseek-v4-pro":{"draws":1,"losses":0,"wins":19},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":11},"google/gemini-3.5-flash":{"draws":7,"losses":2,"wins":21},"google/gemini-3.5-flash-lite":{"draws":1,"losses":0,"wins":7},"google/gemini-3.6-flash":{"draws":2,"losses":7,"wins":15},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":2},"gpt-4.1":{"draws":2,"losses":2,"wins":0},"gpt-5":{"draws":1,"losses":0,"wins":21},"gpt-5.4":{"draws":3,"losses":14,"wins":19},"gpt-5.4-mini":{"draws":9,"losses":6,"wins":29},"gpt-5.4-nano":{"draws":8,"losses":8,"wins":50},"gpt-5.5":{"draws":5,"losses":11,"wins":14},"gpt-5.6-luna":{"draws":4,"losses":3,"wins":17},"gpt-5.6-sol":{"draws":11,"losses":8,"wins":25},"gpt-5.6-terra":{"draws":4,"losses":1,"wins":27},"meituan/longcat-2.0":{"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":1,"wins":5},"moonshotai/kimi-k3":{"draws":2,"losses":0,"wins":8},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":1,"wins":16},"o3":{"draws":0,"losses":2,"wins":20},"openai/gpt-oss-120b":{"draws":1,"losses":1,"wins":10},"poolside/laguna-s-2.1":{"draws":0,"losses":2,"wins":4},"qwen/qwen3.7-max":{"draws":1,"losses":2,"wins":5},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":4},"stepfun/step-3.7-flash":{"draws":1,"losses":0,"wins":11},"tencent/hy3-preview":{"draws":0,"losses":3,"wins":15},"thinkingmachines/inkling":{"draws":4,"losses":0,"wins":8},"x-ai/grok-4.5":{"draws":6,"losses":9,"wins":37},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":2,"losses":0,"wins":10},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":6},"z-ai/glm-5.2":{"draws":9,"losses":12,"wins":49}},"claude-opus-4-5":{"claude-fable-5":{"draws":0,"losses":23,"wins":3},"claude-opus-4-5":{"draws":11,"losses":10,"wins":13},"claude-opus-4-8":{"draws":8,"losses":23,"wins":7},"claude-opus-5":{"draws":7,"losses":81,"wins":8},"claude-sonnet-5":{"draws":14,"losses":17,"wins":9},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":3},"deepseek/deepseek-v4-flash":{"draws":23,"losses":8,"wins":19},"deepseek/deepseek-v4-pro":{"draws":9,"losses":4,"wins":11},"google/gemini-3.1-flash-lite":{"draws":6,"losses":1,"wins":17},"google/gemini-3.5-flash":{"draws":4,"losses":11,"wins":7},"google/gemini-3.5-flash-lite":{"draws":24,"losses":11,"wins":17},"google/gemini-3.6-flash":{"draws":13,"losses":22,"wins":15},"google/gemma-4-31b-it":{"draws":4,"losses":4,"wins":0},"gpt-4.1":{"draws":5,"losses":1,"wins":0},"gpt-5":{"draws":13,"losses":9,"wins":6},"gpt-5.4":{"draws":6,"losses":16,"wins":8},"gpt-5.4-mini":{"draws":24,"losses":20,"wins":32},"gpt-5.4-nano":{"draws":30,"losses":24,"wins":30},"gpt-5.5":{"draws":2,"losses":16,"wins":10},"gpt-5.6-luna":{"draws":11,"losses":16,"wins":5},"gpt-5.6-sol":{"draws":7,"losses":20,"wins":9},"gpt-5.6-terra":{"draws":8,"losses":19,"wins":9},"inclusionai/ling-3.0-flash":{"draws":5,"losses":5,"wins":4},"meituan/longcat-2.0":{"draws":7,"losses":7,"wins":8},"minimax/minimax-m3":{"draws":3,"losses":1,"wins":4},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":4},"moonshotai/kimi-k3":{"draws":12,"losses":28,"wins":20},"nex-agi/nex-n2-pro":{"draws":2,"losses":2,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":19,"losses":6,"wins":11},"o3":{"draws":8,"losses":9,"wins":33},"openai/gpt-oss-120b":{"draws":13,"losses":4,"wins":13},"poolside/laguna-s-2.1":{"draws":13,"losses":0,"wins":9},"qwen/qwen3.7-max":{"draws":7,"losses":2,"wins":9},"qwen/qwen3.7-plus":{"draws":6,"losses":2,"wins":2},"stepfun/step-3.7-flash":{"draws":5,"losses":4,"wins":19},"tencent/hy3-preview":{"draws":9,"losses":4,"wins":7},"thinkingmachines/inkling":{"draws":10,"losses":2,"wins":18},"x-ai/grok-4.5":{"draws":24,"losses":46,"wins":20},"x-ai/grok-build-0.1":{"draws":4,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":18,"losses":12,"wins":8},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":5,"wins":5},"z-ai/glm-5.2":{"draws":25,"losses":46,"wins":37}},"claude-opus-4-8":{"claude-fable-5":{"draws":4,"losses":12,"wins":18},"claude-opus-4-5":{"draws":3,"losses":8,"wins":25},"claude-opus-4-8":{"draws":0,"losses":3,"wins":5},"claude-opus-5":{"draws":14,"losses":33,"wins":23},"claude-sonnet-5":{"draws":6,"losses":6,"wins":22},"deepseek/deepseek-v4-flash":{"draws":0,"losses":4,"wins":22},"deepseek/deepseek-v4-pro":{"draws":2,"losses":2,"wins":12},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":11},"google/gemini-3.5-flash":{"draws":4,"losses":8,"wins":8},"google/gemini-3.5-flash-lite":{"draws":0,"losses":2,"wins":12},"google/gemini-3.6-flash":{"draws":2,"losses":12,"wins":10},"google/gemma-4-31b-it":{"draws":0,"losses":2,"wins":0},"gpt-4.1":{"draws":0,"losses":0,"wins":4},"gpt-5":{"draws":3,"losses":5,"wins":16},"gpt-5.4":{"draws":6,"losses":13,"wins":11},"gpt-5.4-mini":{"draws":10,"losses":10,"wins":26},"gpt-5.4-nano":{"draws":5,"losses":7,"wins":40},"gpt-5.5":{"draws":4,"losses":14,"wins":10},"gpt-5.6-luna":{"draws":2,"losses":4,"wins":12},"gpt-5.6-sol":{"draws":4,"losses":16,"wins":16},"gpt-5.6-terra":{"draws":3,"losses":6,"wins":15},"meituan/longcat-2.0":{"draws":2,"losses":0,"wins":2},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":6},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":4},"moonshotai/kimi-k3":{"draws":2,"losses":2,"wins":4},"nex-agi/nex-n2-pro":{"draws":0,"losses":1,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":2,"wins":18},"o3":{"draws":0,"losses":5,"wins":25},"openai/gpt-oss-120b":{"draws":2,"losses":0,"wins":8},"poolside/laguna-s-2.1":{"draws":0,"losses":2,"wins":8},"qwen/qwen3.7-max":{"draws":3,"losses":2,"wins":3},"qwen/qwen3.7-plus":{"draws":0,"losses":2,"wins":6},"stepfun/step-3.7-flash":{"draws":0,"losses":1,"wins":11},"tencent/hy3-preview":{"draws":4,"losses":4,"wins":10},"thinkingmachines/inkling":{"draws":3,"losses":0,"wins":15},"x-ai/grok-4.5":{"draws":9,"losses":11,"wins":24},"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":2,"wins":4},"z-ai/glm-5.2":{"draws":8,"losses":20,"wins":48}},"claude-opus-5":{"claude-fable-5":{"draws":7,"losses":19,"wins":26},"claude-opus-4-5":{"draws":3,"losses":6,"wins":53},"claude-opus-4-8":{"draws":2,"losses":12,"wins":16},"claude-opus-5":{"draws":14,"losses":51,"wins":81},"claude-sonnet-5":{"draws":3,"losses":1,"wins":38},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":3},"deepseek/deepseek-v4-flash":{"draws":2,"losses":2,"wins":14},"deepseek/deepseek-v4-pro":{"draws":0,"losses":2,"wins":18},"google/gemini-3.1-flash-lite":{"draws":0,"losses":1,"wins":13},"google/gemini-3.5-flash":{"draws":0,"losses":1,"wins":23},"google/gemini-3.5-flash-lite":{"draws":3,"losses":1,"wins":34},"google/gemini-3.6-flash":{"draws":4,"losses":8,"wins":34},"gpt-4.1":{"draws":1,"losses":0,"wins":7},"gpt-5":{"draws":0,"losses":2,"wins":16},"gpt-5.4":{"draws":0,"losses":9,"wins":29},"gpt-5.4-mini":{"draws":1,"losses":1,"wins":32},"gpt-5.4-nano":{"draws":3,"losses":7,"wins":36},"gpt-5.5":{"draws":0,"losses":7,"wins":23},"gpt-5.6-luna":{"draws":3,"losses":0,"wins":17},"gpt-5.6-sol":{"draws":8,"losses":8,"wins":28},"gpt-5.6-terra":{"draws":3,"losses":2,"wins":27},"meituan/longcat-2.0":{"draws":0,"losses":3,"wins":3},"minimax/minimax-m3":{"draws":0,"losses":1,"wins":5},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":1,"wins":4},"moonshotai/kimi-k3":{"draws":4,"losses":3,"wins":33},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":1,"losses":0,"wins":15},"o3":{"draws":0,"losses":3,"wins":41},"openai/gpt-oss-120b":{"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},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":6},"tencent/hy3-preview":{"draws":0,"losses":1,"wins":19},"thinkingmachines/inkling":{"draws":1,"losses":2,"wins":23},"x-ai/grok-4.5":{"draws":3,"losses":10,"wins":53},"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":7,"losses":3,"wins":42}},"claude-sonnet-5":{"claude-fable-5":{"draws":7,"losses":16,"wins":1},"claude-opus-4-5":{"draws":23,"losses":10,"wins":19},"claude-opus-4-8":{"draws":5,"losses":21,"wins":6},"claude-opus-5":{"draws":18,"losses":65,"wins":9},"claude-sonnet-5":{"draws":5,"losses":9,"wins":12},"cohere/north-mini-code":{"draws":1,"losses":1,"wins":4},"deepseek/deepseek-v4-flash":{"draws":11,"losses":6,"wins":29},"deepseek/deepseek-v4-pro":{"draws":7,"losses":5,"wins":8},"google/gemini-3.1-flash-lite":{"draws":5,"losses":1,"wins":10},"google/gemini-3.5-flash":{"draws":11,"losses":6,"wins":9},"google/gemini-3.5-flash-lite":{"draws":9,"losses":8,"wins":7},"google/gemini-3.6-flash":{"draws":8,"losses":18,"wins":10},"google/gemma-4-31b-it":{"draws":0,"losses":1,"wins":3},"gpt-4.1":{"draws":2,"losses":3,"wins":5},"gpt-5":{"draws":12,"losses":10,"wins":10},"gpt-5.4":{"draws":12,"losses":21,"wins":3},"gpt-5.4-mini":{"draws":25,"losses":12,"wins":21},"gpt-5.4-nano":{"draws":21,"losses":19,"wins":12},"gpt-5.5":{"draws":10,"losses":10,"wins":8},"gpt-5.6-luna":{"draws":8,"losses":15,"wins":3},"gpt-5.6-sol":{"draws":7,"losses":25,"wins":10},"gpt-5.6-terra":{"draws":9,"losses":14,"wins":13},"inclusionai/ling-3.0-flash":{"draws":5,"losses":1,"wins":2},"meituan/longcat-2.0":{"draws":6,"losses":1,"wins":7},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":4},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":0,"wins":1},"moonshotai/kimi-k3":{"draws":6,"losses":8,"wins":4},"nex-agi/nex-n2-pro":{"draws":1,"losses":4,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":2,"wins":12},"o3":{"draws":5,"losses":21,"wins":16},"openai/gpt-oss-120b":{"draws":5,"losses":4,"wins":5},"poolside/laguna-s-2.1":{"draws":3,"losses":4,"wins":5},"qwen/qwen3.7-max":{"draws":6,"losses":0,"wins":2},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":0},"stepfun/step-3.7-flash":{"draws":4,"losses":1,"wins":9},"tencent/hy3-preview":{"draws":8,"losses":4,"wins":8},"thinkingmachines/inkling":{"draws":11,"losses":6,"wins":13},"x-ai/grok-4.5":{"draws":15,"losses":20,"wins":9},"x-ai/grok-build-0.1":{"draws":1,"losses":1,"wins":2},"xiaomi/mimo-v2.5":{"draws":10,"losses":1,"wins":5},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":2,"wins":3},"z-ai/glm-5.2":{"draws":32,"losses":35,"wins":31}},"deepseek/deepseek-v4-flash":{"claude-fable-5":{"draws":1,"losses":21,"wins":2},"claude-opus-4-5":{"draws":18,"losses":18,"wins":10},"claude-opus-4-8":{"draws":0,"losses":20,"wins":8},"claude-opus-5":{"draws":5,"losses":26,"wins":3},"claude-sonnet-5":{"draws":10,"losses":21,"wins":7},"cohere/north-mini-code":{"draws":4,"losses":4,"wins":2},"deepseek/deepseek-v4-flash":{"draws":16,"losses":25,"wins":31},"deepseek/deepseek-v4-pro":{"draws":6,"losses":16,"wins":4},"google/gemini-3.1-flash-lite":{"draws":6,"losses":9,"wins":15},"google/gemini-3.5-flash":{"draws":2,"losses":14,"wins":4},"google/gemini-3.5-flash-lite":{"draws":6,"losses":13,"wins":11},"google/gemini-3.6-flash":{"draws":8,"losses":12,"wins":4},"google/gemma-4-31b-it":{"draws":3,"losses":10,"wins":3},"gpt-4.1":{"draws":2,"losses":2,"wins":2},"gpt-5":{"draws":5,"losses":21,"wins":4},"gpt-5.4":{"draws":9,"losses":19,"wins":4},"gpt-5.4-mini":{"draws":21,"losses":34,"wins":15},"gpt-5.4-nano":{"draws":34,"losses":27,"wins":27},"gpt-5.5":{"draws":3,"losses":21,"wins":0},"gpt-5.6-luna":{"draws":8,"losses":15,"wins":11},"gpt-5.6-sol":{"draws":2,"losses":25,"wins":7},"gpt-5.6-terra":{"draws":9,"losses":17,"wins":6},"inclusionai/ling-3.0-flash":{"draws":6,"losses":3,"wins":7},"meituan/longcat-2.0":{"draws":4,"losses":5,"wins":7},"minimax/minimax-m3":{"draws":0,"losses":5,"wins":5},"mistralai/mistral-medium-3-5":{"draws":0,"losses":10,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":1,"wins":1},"moonshotai/kimi-k3":{"draws":4,"losses":6,"wins":2},"nex-agi/nex-n2-pro":{"draws":4,"losses":3,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":9,"wins":15},"o3":{"draws":5,"losses":29,"wins":24},"openai/gpt-oss-120b":{"draws":6,"losses":8,"wins":2},"poolside/laguna-s-2.1":{"draws":4,"losses":8,"wins":4},"qwen/qwen3.7-max":{"draws":0,"losses":3,"wins":5},"qwen/qwen3.7-plus":{"draws":0,"losses":5,"wins":7},"stepfun/step-3.7-flash":{"draws":4,"losses":11,"wins":13},"tencent/hy3-preview":{"draws":8,"losses":11,"wins":7},"thinkingmachines/inkling":{"draws":13,"losses":4,"wins":19},"x-ai/grok-4.5":{"draws":4,"losses":32,"wins":6},"x-ai/grok-build-0.1":{"draws":2,"losses":2,"wins":2},"xiaomi/mimo-v2.5":{"draws":10,"losses":5,"wins":13},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":2,"wins":6},"z-ai/glm-5.2":{"draws":42,"losses":46,"wins":38}},"deepseek/deepseek-v4-pro":{"claude-fable-5":{"draws":0,"losses":14,"wins":2},"claude-opus-4-5":{"draws":9,"losses":12,"wins":3},"claude-opus-4-8":{"draws":5,"losses":13,"wins":6},"claude-opus-5":{"draws":3,"losses":32,"wins":1},"claude-sonnet-5":{"draws":8,"losses":11,"wins":5},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":1},"deepseek/deepseek-v4-flash":{"draws":9,"losses":6,"wins":27},"deepseek/deepseek-v4-pro":{"draws":0,"losses":0,"wins":4},"google/gemini-3.1-flash-lite":{"draws":4,"losses":2,"wins":6},"google/gemini-3.5-flash":{"draws":2,"losses":6,"wins":4},"google/gemini-3.5-flash-lite":{"draws":5,"losses":2,"wins":9},"google/gemini-3.6-flash":{"draws":4,"losses":10,"wins":6},"google/gemma-4-31b-it":{"draws":3,"losses":2,"wins":5},"gpt-4.1":{"draws":2,"losses":5,"wins":1},"gpt-5":{"draws":3,"losses":4,"wins":11},"gpt-5.4":{"draws":1,"losses":19,"wins":2},"gpt-5.4-mini":{"draws":11,"losses":16,"wins":17},"gpt-5.4-nano":{"draws":14,"losses":14,"wins":18},"gpt-5.5":{"draws":8,"losses":10,"wins":2},"gpt-5.6-luna":{"draws":6,"losses":10,"wins":6},"gpt-5.6-sol":{"draws":0,"losses":11,"wins":5},"gpt-5.6-terra":{"draws":10,"losses":8,"wins":4},"inclusionai/ling-3.0-flash":{"draws":0,"losses":0,"wins":6},"meituan/longcat-2.0":{"draws":0,"losses":4,"wins":4},"minimax/minimax-m3":{"draws":0,"losses":3,"wins":1},"mistralai/mistral-medium-3-5":{"draws":2,"losses":2,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":0,"losses":6,"wins":0},"nex-agi/nex-n2-pro":{"draws":2,"losses":2,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":3,"wins":12},"o3":{"draws":7,"losses":13,"wins":16},"openai/gpt-oss-120b":{"draws":4,"losses":3,"wins":1},"poolside/laguna-s-2.1":{"draws":0,"losses":3,"wins":7},"qwen/qwen3.7-max":{"draws":0,"losses":3,"wins":3},"stepfun/step-3.7-flash":{"draws":2,"losses":1,"wins":7},"tencent/hy3-preview":{"draws":2,"losses":4,"wins":8},"thinkingmachines/inkling":{"draws":7,"losses":2,"wins":5},"x-ai/grok-4.5":{"draws":3,"losses":24,"wins":3},"x-ai/grok-build-0.1":{"draws":4,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":7,"losses":3,"wins":4},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":2},"z-ai/glm-5.2":{"draws":15,"losses":20,"wins":29}},"google/gemini-3.1-flash-lite":{"claude-fable-5":{"draws":1,"losses":9,"wins":0},"claude-opus-4-5":{"draws":6,"losses":14,"wins":2},"claude-opus-4-8":{"draws":3,"losses":13,"wins":2},"claude-opus-5":{"draws":2,"losses":18,"wins":0},"claude-sonnet-5":{"draws":8,"losses":6,"wins":2},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":6},"deepseek/deepseek-v4-flash":{"draws":10,"losses":12,"wins":16},"deepseek/deepseek-v4-pro":{"draws":4,"losses":5,"wins":3},"google/gemini-3.1-flash-lite":{"draws":0,"losses":2,"wins":2},"google/gemini-3.5-flash":{"draws":2,"losses":7,"wins":1},"google/gemini-3.5-flash-lite":{"draws":6,"losses":6,"wins":4},"google/gemini-3.6-flash":{"draws":4,"losses":11,"wins":1},"google/gemma-4-31b-it":{"draws":2,"losses":3,"wins":1},"gpt-4.1":{"draws":2,"losses":2,"wins":2},"gpt-5":{"draws":6,"losses":8,"wins":0},"gpt-5.4":{"draws":1,"losses":9,"wins":0},"gpt-5.4-mini":{"draws":7,"losses":21,"wins":4},"gpt-5.4-nano":{"draws":11,"losses":25,"wins":6},"gpt-5.5":{"draws":4,"losses":12,"wins":0},"gpt-5.6-luna":{"draws":6,"losses":10,"wins":4},"gpt-5.6-sol":{"draws":1,"losses":9,"wins":2},"gpt-5.6-terra":{"draws":3,"losses":9,"wins":2},"inclusionai/ling-3.0-flash":{"draws":6,"losses":1,"wins":3},"meituan/longcat-2.0":{"draws":4,"losses":5,"wins":3},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":2},"mistralai/mistral-medium-3-5":{"draws":2,"losses":3,"wins":5},"moonshotai/kimi-k3":{"draws":1,"losses":3,"wins":0},"nex-agi/nex-n2-pro":{"draws":0,"losses":6,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":8,"wins":3},"o3":{"draws":4,"losses":16,"wins":2},"openai/gpt-oss-120b":{"draws":5,"losses":4,"wins":3},"poolside/laguna-s-2.1":{"draws":4,"losses":1,"wins":3},"qwen/qwen3.7-max":{"draws":0,"losses":2,"wins":0},"qwen/qwen3.7-plus":{"draws":0,"losses":2,"wins":2},"stepfun/step-3.7-flash":{"draws":2,"losses":5,"wins":3},"tencent/hy3-preview":{"draws":3,"losses":5,"wins":4},"thinkingmachines/inkling":{"draws":4,"losses":8,"wins":2},"x-ai/grok-4.5":{"draws":6,"losses":14,"wins":0},"x-ai/grok-build-0.1":{"draws":3,"losses":0,"wins":1},"xiaomi/mimo-v2.5":{"draws":11,"losses":4,"wins":3},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":6,"wins":0},"z-ai/glm-5.2":{"draws":11,"losses":17,"wins":8}},"google/gemini-3.5-flash":{"claude-fable-5":{"draws":2,"losses":16,"wins":4},"claude-opus-4-5":{"draws":8,"losses":5,"wins":11},"claude-opus-4-8":{"draws":1,"losses":6,"wins":7},"claude-opus-5":{"draws":4,"losses":32,"wins":0},"claude-sonnet-5":{"draws":9,"losses":5,"wins":6},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":2},"deepseek/deepseek-v4-flash":{"draws":13,"losses":4,"wins":17},"deepseek/deepseek-v4-pro":{"draws":2,"losses":4,"wins":6},"google/gemini-3.1-flash-lite":{"draws":2,"losses":1,"wins":7},"google/gemini-3.5-flash":{"draws":2,"losses":2,"wins":2},"google/gemini-3.5-flash-lite":{"draws":6,"losses":3,"wins":9},"google/gemini-3.6-flash":{"draws":3,"losses":7,"wins":4},"google/gemma-4-31b-it":{"draws":0,"losses":3,"wins":3},"gpt-4.1":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":2,"losses":5,"wins":7},"gpt-5.4":{"draws":3,"losses":7,"wins":6},"gpt-5.4-mini":{"draws":12,"losses":17,"wins":13},"gpt-5.4-nano":{"draws":13,"losses":16,"wins":11},"gpt-5.5":{"draws":8,"losses":12,"wins":2},"gpt-5.6-luna":{"draws":5,"losses":9,"wins":4},"gpt-5.6-sol":{"draws":3,"losses":9,"wins":4},"gpt-5.6-terra":{"draws":5,"losses":12,"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":2,"losses":0,"wins":2},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":0,"wins":1},"moonshotai/kimi-k3":{"draws":3,"losses":3,"wins":0},"nex-agi/nex-n2-pro":{"draws":0,"losses":4,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":3,"wins":12},"o3":{"draws":7,"losses":12,"wins":5},"openai/gpt-oss-120b":{"draws":4,"losses":4,"wins":4},"poolside/laguna-s-2.1":{"draws":5,"losses":4,"wins":1},"qwen/qwen3.7-max":{"draws":0,"losses":2,"wins":0},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":4},"stepfun/step-3.7-flash":{"draws":2,"losses":2,"wins":6},"tencent/hy3-preview":{"draws":4,"losses":2,"wins":6},"thinkingmachines/inkling":{"draws":7,"losses":2,"wins":11},"x-ai/grok-4.5":{"draws":3,"losses":9,"wins":12},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":11,"losses":6,"wins":5},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":0,"wins":2},"z-ai/glm-5.2":{"draws":12,"losses":21,"wins":25}},"google/gemini-3.5-flash-lite":{"claude-fable-5":{"draws":1,"losses":7,"wins":0},"claude-opus-4-5":{"draws":11,"losses":14,"wins":9},"claude-opus-4-8":{"draws":0,"losses":12,"wins":2},"claude-opus-5":{"draws":3,"losses":30,"wins":1},"claude-sonnet-5":{"draws":11,"losses":7,"wins":6},"deepseek/deepseek-v4-flash":{"draws":6,"losses":10,"wins":12},"deepseek/deepseek-v4-pro":{"draws":5,"losses":7,"wins":2},"google/gemini-3.1-flash-lite":{"draws":5,"losses":4,"wins":5},"google/gemini-3.5-flash":{"draws":6,"losses":9,"wins":3},"google/gemini-3.5-flash-lite":{"draws":18,"losses":26,"wins":30},"google/gemini-3.6-flash":{"draws":20,"losses":30,"wins":14},"gpt-4.1-nano":{"draws":1,"losses":1,"wins":0},"gpt-5":{"draws":10,"losses":6,"wins":2},"gpt-5.4":{"draws":2,"losses":8,"wins":0},"gpt-5.4-mini":{"draws":7,"losses":19,"wins":4},"gpt-5.4-nano":{"draws":13,"losses":9,"wins":12},"gpt-5.5":{"draws":6,"losses":8,"wins":2},"gpt-5.6-luna":{"draws":5,"losses":8,"wins":3},"gpt-5.6-sol":{"draws":0,"losses":9,"wins":1},"gpt-5.6-terra":{"draws":5,"losses":9,"wins":0},"inclusionai/ling-3.0-flash":{"draws":3,"losses":4,"wins":9},"meituan/longcat-2.0":{"draws":7,"losses":8,"wins":11},"mistralai/mistral-medium-3-5":{"draws":0,"losses":3,"wins":9},"moonshotai/kimi-k3":{"draws":24,"losses":38,"wins":26},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":9,"wins":6},"o3":{"draws":4,"losses":42,"wins":26},"openai/gpt-oss-120b":{"draws":7,"losses":5,"wins":20},"poolside/laguna-s-2.1":{"draws":11,"losses":7,"wins":12},"stepfun/step-3.7-flash":{"draws":4,"losses":9,"wins":9},"tencent/hy3-preview":{"draws":3,"losses":4,"wins":3},"thinkingmachines/inkling":{"draws":12,"losses":10,"wins":16},"x-ai/grok-4.5":{"draws":14,"losses":36,"wins":18},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":2,"wins":0},"z-ai/glm-5.2":{"draws":17,"losses":23,"wins":10}},"google/gemini-3.6-flash":{"claude-fable-5":{"draws":2,"losses":15,"wins":5},"claude-opus-4-5":{"draws":4,"losses":10,"wins":18},"claude-opus-4-8":{"draws":2,"losses":10,"wins":10},"claude-opus-5":{"draws":8,"losses":35,"wins":11},"claude-sonnet-5":{"draws":6,"losses":6,"wins":14},"deepseek/deepseek-v4-flash":{"draws":5,"losses":2,"wins":11},"deepseek/deepseek-v4-pro":{"draws":4,"losses":6,"wins":10},"google/gemini-3.1-flash-lite":{"draws":3,"losses":1,"wins":8},"google/gemini-3.5-flash":{"draws":3,"losses":4,"wins":7},"google/gemini-3.5-flash-lite":{"draws":13,"losses":7,"wins":30},"google/gemini-3.6-flash":{"draws":13,"losses":22,"wins":31},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":3,"losses":7,"wins":12},"gpt-5.4":{"draws":4,"losses":12,"wins":4},"gpt-5.4-mini":{"draws":7,"losses":8,"wins":15},"gpt-5.4-nano":{"draws":8,"losses":11,"wins":23},"gpt-5.5":{"draws":4,"losses":12,"wins":6},"gpt-5.6-luna":{"draws":3,"losses":11,"wins":10},"gpt-5.6-sol":{"draws":3,"losses":16,"wins":5},"gpt-5.6-terra":{"draws":4,"losses":8,"wins":12},"inclusionai/ling-3.0-flash":{"draws":8,"losses":1,"wins":7},"meituan/longcat-2.0":{"draws":8,"losses":3,"wins":15},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":8},"moonshotai/kimi-k3":{"draws":9,"losses":22,"wins":65},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":3,"wins":11},"o3":{"draws":7,"losses":13,"wins":34},"openai/gpt-oss-120b":{"draws":3,"losses":2,"wins":17},"poolside/laguna-s-2.1":{"draws":9,"losses":1,"wins":10},"stepfun/step-3.7-flash":{"draws":3,"losses":1,"wins":11},"tencent/hy3-preview":{"draws":1,"losses":7,"wins":12},"thinkingmachines/inkling":{"draws":12,"losses":5,"wins":19},"x-ai/grok-4.5":{"draws":9,"losses":45,"wins":52},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":1,"wins":1},"z-ai/glm-5.2":{"draws":8,"losses":14,"wins":26}},"gpt-5":{"claude-fable-5":{"draws":1,"losses":20,"wins":1},"claude-opus-4-5":{"draws":19,"losses":9,"wins":10},"claude-opus-4-8":{"draws":4,"losses":15,"wins":5},"claude-opus-5":{"draws":3,"losses":37,"wins":2},"claude-sonnet-5":{"draws":17,"losses":8,"wins":9},"cohere/north-mini-code":{"draws":3,"losses":3,"wins":4},"deepseek/deepseek-v4-flash":{"draws":18,"losses":2,"wins":24},"deepseek/deepseek-v4-pro":{"draws":4,"losses":9,"wins":5},"google/gemini-3.1-flash-lite":{"draws":8,"losses":2,"wins":8},"google/gemini-3.5-flash":{"draws":4,"losses":8,"wins":6},"google/gemini-3.5-flash-lite":{"draws":12,"losses":4,"wins":6},"google/gemini-3.6-flash":{"draws":5,"losses":12,"wins":7},"google/gemma-4-31b-it":{"draws":2,"losses":1,"wins":3},"gpt-4.1":{"draws":3,"losses":3,"wins":2},"gpt-5":{"draws":0,"losses":0,"wins":4},"gpt-5.4":{"draws":7,"losses":14,"wins":3},"gpt-5.4-mini":{"draws":18,"losses":19,"wins":13},"gpt-5.4-nano":{"draws":14,"losses":9,"wins":27},"gpt-5.5":{"draws":8,"losses":12,"wins":4},"gpt-5.6-luna":{"draws":11,"losses":6,"wins":13},"gpt-5.6-sol":{"draws":8,"losses":14,"wins":8},"gpt-5.6-terra":{"draws":6,"losses":13,"wins":7},"inclusionai/ling-3.0-flash":{"draws":3,"losses":3,"wins":2},"meituan/longcat-2.0":{"draws":2,"losses":5,"wins":3},"minimax/minimax-m3":{"draws":3,"losses":1,"wins":4},"mistralai/mistral-medium-3-5":{"draws":0,"losses":2,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":4},"moonshotai/kimi-k3":{"draws":2,"losses":5,"wins":1},"nex-agi/nex-n2-pro":{"draws":4,"losses":0,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":0,"wins":10},"o3":{"draws":3,"losses":12,"wins":15},"openai/gpt-oss-120b":{"draws":7,"losses":1,"wins":2},"poolside/laguna-s-2.1":{"draws":5,"losses":6,"wins":3},"qwen/qwen3.7-max":{"draws":4,"losses":1,"wins":5},"qwen/qwen3.7-plus":{"draws":0,"losses":1,"wins":1},"stepfun/step-3.7-flash":{"draws":4,"losses":0,"wins":8},"tencent/hy3-preview":{"draws":5,"losses":6,"wins":7},"thinkingmachines/inkling":{"draws":7,"losses":4,"wins":9},"x-ai/grok-4.5":{"draws":6,"losses":17,"wins":9},"x-ai/grok-build-0.1":{"draws":2,"losses":1,"wins":1},"xiaomi/mimo-v2.5":{"draws":15,"losses":4,"wins":11},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":3,"wins":3},"z-ai/glm-5.2":{"draws":38,"losses":32,"wins":28}},"gpt-5.4":{"claude-fable-5":{"draws":4,"losses":11,"wins":19},"claude-opus-4-5":{"draws":11,"losses":7,"wins":16},"claude-opus-4-8":{"draws":5,"losses":8,"wins":15},"claude-opus-5":{"draws":7,"losses":39,"wins":34},"claude-sonnet-5":{"draws":7,"losses":2,"wins":15},"cohere/north-mini-code":{"draws":1,"losses":1,"wins":4},"deepseek/deepseek-v4-flash":{"draws":5,"losses":2,"wins":23},"deepseek/deepseek-v4-pro":{"draws":2,"losses":0,"wins":18},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":9},"google/gemini-3.5-flash":{"draws":7,"losses":2,"wins":11},"google/gemini-3.5-flash-lite":{"draws":2,"losses":0,"wins":8},"google/gemini-3.6-flash":{"draws":4,"losses":4,"wins":14},"gpt-5":{"draws":4,"losses":3,"wins":15},"gpt-5.4":{"draws":4,"losses":2,"wins":12},"gpt-5.4-mini":{"draws":12,"losses":7,"wins":33},"gpt-5.4-nano":{"draws":12,"losses":7,"wins":33},"gpt-5.5":{"draws":12,"losses":6,"wins":14},"gpt-5.6-luna":{"draws":9,"losses":2,"wins":23},"gpt-5.6-sol":{"draws":7,"losses":5,"wins":24},"gpt-5.6-terra":{"draws":9,"losses":8,"wins":21},"inclusionai/ling-3.0-flash":{"draws":1,"losses":0,"wins":1},"meituan/longcat-2.0":{"draws":3,"losses":0,"wins":3},"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":5,"losses":0,"wins":1},"moonshotai/kimi-k3":{"draws":2,"losses":2,"wins":4},"nex-agi/nex-n2-pro":{"draws":1,"losses":0,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":0,"wins":17},"o3":{"draws":2,"losses":2,"wins":22},"openai/gpt-oss-120b":{"draws":1,"losses":0,"wins":9},"poolside/laguna-s-2.1":{"draws":0,"losses":0,"wins":4},"qwen/qwen3.7-max":{"draws":0,"losses":0,"wins":8},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":2},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":10},"tencent/hy3-preview":{"draws":3,"losses":0,"wins":15},"thinkingmachines/inkling":{"draws":3,"losses":3,"wins":6},"x-ai/grok-4.5":{"draws":6,"losses":8,"wins":28},"x-ai/grok-build-0.1":{"draws":0,"losses":1,"wins":1},"xiaomi/mimo-v2.5":{"draws":3,"losses":0,"wins":7},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":8},"z-ai/glm-5.2":{"draws":12,"losses":11,"wins":43}},"gpt-5.4-mini":{"claude-fable-5":{"draws":8,"losses":22,"wins":8},"claude-opus-4-5":{"draws":14,"losses":23,"wins":21},"claude-opus-4-8":{"draws":6,"losses":23,"wins":13},"claude-opus-5":{"draws":4,"losses":75,"wins":5},"claude-sonnet-5":{"draws":10,"losses":15,"wins":17},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":2},"deepseek/deepseek-v4-flash":{"draws":20,"losses":8,"wins":38},"deepseek/deepseek-v4-pro":{"draws":6,"losses":9,"wins":13},"google/gemini-3.1-flash-lite":{"draws":7,"losses":2,"wins":17},"google/gemini-3.5-flash":{"draws":1,"losses":7,"wins":14},"google/gemini-3.5-flash-lite":{"draws":9,"losses":4,"wins":21},"google/gemini-3.6-flash":{"draws":12,"losses":18,"wins":8},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":2},"gpt-4.1":{"draws":6,"losses":4,"wins":4},"gpt-5":{"draws":11,"losses":7,"wins":14},"gpt-5.4":{"draws":5,"losses":26,"wins":11},"gpt-5.4-mini":{"draws":23,"losses":15,"wins":26},"gpt-5.4-nano":{"draws":25,"losses":22,"wins":33},"gpt-5.5":{"draws":5,"losses":17,"wins":10},"gpt-5.6-luna":{"draws":13,"losses":17,"wins":6},"gpt-5.6-sol":{"draws":3,"losses":20,"wins":15},"gpt-5.6-terra":{"draws":9,"losses":14,"wins":13},"inclusionai/ling-3.0-flash":{"draws":9,"losses":0,"wins":7},"meituan/longcat-2.0":{"draws":7,"losses":4,"wins":3},"minimax/minimax-m3":{"draws":2,"losses":4,"wins":0},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":2},"moonshotai/kimi-k3":{"draws":4,"losses":5,"wins":3},"nex-agi/nex-n2-pro":{"draws":2,"losses":1,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":8,"wins":21},"o3":{"draws":4,"losses":29,"wins":35},"openai/gpt-oss-120b":{"draws":11,"losses":4,"wins":13},"poolside/laguna-s-2.1":{"draws":8,"losses":2,"wins":8},"qwen/qwen3.7-max":{"draws":6,"losses":3,"wins":11},"qwen/qwen3.7-plus":{"draws":6,"losses":2,"wins":2},"stepfun/step-3.7-flash":{"draws":3,"losses":2,"wins":17},"tencent/hy3-preview":{"draws":5,"losses":2,"wins":21},"thinkingmachines/inkling":{"draws":12,"losses":8,"wins":18},"x-ai/grok-4.5":{"draws":3,"losses":33,"wins":12},"xiaomi/mimo-v2.5":{"draws":16,"losses":4,"wins":16},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":2,"wins":6},"z-ai/glm-5.2":{"draws":50,"losses":48,"wins":54}},"gpt-5.4-nano":{"claude-fable-5":{"draws":8,"losses":32,"wins":12},"claude-opus-4-5":{"draws":19,"losses":25,"wins":20},"claude-opus-4-8":{"draws":3,"losses":28,"wins":13},"claude-opus-5":{"draws":8,"losses":64,"wins":12},"claude-sonnet-5":{"draws":29,"losses":11,"wins":16},"cohere/north-mini-code":{"draws":4,"losses":2,"wins":8},"deepseek/deepseek-v4-flash":{"draws":38,"losses":20,"wins":30},"deepseek/deepseek-v4-pro":{"draws":9,"losses":19,"wins":10},"google/gemini-3.1-flash-lite":{"draws":9,"losses":2,"wins":19},"google/gemini-3.5-flash":{"draws":8,"losses":8,"wins":14},"google/gemini-3.5-flash-lite":{"draws":15,"losses":12,"wins":9},"google/gemini-3.6-flash":{"draws":10,"losses":25,"wins":11},"google/gemma-4-31b-it":{"draws":5,"losses":1,"wins":4},"gpt-4.1":{"draws":8,"losses":1,"wins":1},"gpt-5":{"draws":12,"losses":22,"wins":12},"gpt-5.4":{"draws":16,"losses":27,"wins":13},"gpt-5.4-mini":{"draws":35,"losses":26,"wins":31},"gpt-5.4-nano":{"draws":25,"losses":15,"wins":38},"gpt-5.5":{"draws":8,"losses":30,"wins":6},"gpt-5.6-luna":{"draws":15,"losses":15,"wins":22},"gpt-5.6-sol":{"draws":9,"losses":28,"wins":13},"gpt-5.6-terra":{"draws":10,"losses":20,"wins":18},"inclusionai/ling-3.0-flash":{"draws":8,"losses":4,"wins":2},"meituan/longcat-2.0":{"draws":5,"losses":9,"wins":2},"minimax/minimax-m3":{"draws":9,"losses":3,"wins":6},"mistralai/mistral-medium-3-5":{"draws":1,"losses":8,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":2},"moonshotai/kimi-k3":{"draws":3,"losses":11,"wins":2},"nex-agi/nex-n2-pro":{"draws":3,"losses":1,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":31,"losses":3,"wins":20},"o3":{"draws":7,"losses":30,"wins":25},"openai/gpt-oss-120b":{"draws":11,"losses":9,"wins":8},"poolside/laguna-s-2.1":{"draws":6,"losses":4,"wins":4},"qwen/qwen3.7-max":{"draws":2,"losses":4,"wins":2},"qwen/qwen3.7-plus":{"draws":0,"losses":2,"wins":2},"stepfun/step-3.7-flash":{"draws":7,"losses":3,"wins":14},"tencent/hy3-preview":{"draws":7,"losses":11,"wins":16},"thinkingmachines/inkling":{"draws":16,"losses":11,"wins":14},"x-ai/grok-4.5":{"draws":8,"losses":45,"wins":23},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":4},"xiaomi/mimo-v2.5":{"draws":22,"losses":5,"wins":13},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":2,"wins":2},"z-ai/glm-5.2":{"draws":57,"losses":49,"wins":56}},"gpt-5.5":{"claude-fable-5":{"draws":3,"losses":11,"wins":16},"claude-opus-4-5":{"draws":6,"losses":5,"wins":17},"claude-opus-4-8":{"draws":2,"losses":3,"wins":19},"claude-opus-5":{"draws":1,"losses":38,"wins":27},"claude-sonnet-5":{"draws":5,"losses":4,"wins":11},"cohere/north-mini-code":{"draws":1,"losses":1,"wins":0},"deepseek/deepseek-v4-flash":{"draws":7,"losses":0,"wins":21},"deepseek/deepseek-v4-pro":{"draws":6,"losses":0,"wins":8},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":10},"google/gemini-3.5-flash":{"draws":7,"losses":6,"wins":11},"google/gemini-3.5-flash-lite":{"draws":6,"losses":2,"wins":8},"google/gemini-3.6-flash":{"draws":6,"losses":8,"wins":12},"gpt-4.1":{"draws":1,"losses":1,"wins":4},"gpt-5":{"draws":5,"losses":3,"wins":14},"gpt-5.4":{"draws":11,"losses":10,"wins":13},"gpt-5.4-mini":{"draws":10,"losses":5,"wins":17},"gpt-5.4-nano":{"draws":3,"losses":6,"wins":37},"gpt-5.5":{"draws":6,"losses":5,"wins":7},"gpt-5.6-luna":{"draws":3,"losses":8,"wins":13},"gpt-5.6-sol":{"draws":0,"losses":10,"wins":20},"gpt-5.6-terra":{"draws":5,"losses":6,"wins":11},"minimax/minimax-m3":{"draws":1,"losses":1,"wins":4},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":1,"wins":0},"moonshotai/kimi-k3":{"draws":3,"losses":3,"wins":2},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":0,"wins":11},"o3":{"draws":1,"losses":2,"wins":27},"openai/gpt-oss-120b":{"draws":3,"losses":0,"wins":7},"poolside/laguna-s-2.1":{"draws":1,"losses":1,"wins":4},"qwen/qwen3.7-max":{"draws":1,"losses":1,"wins":6},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":2},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":10},"tencent/hy3-preview":{"draws":7,"losses":0,"wins":9},"thinkingmachines/inkling":{"draws":2,"losses":3,"wins":11},"x-ai/grok-4.5":{"draws":11,"losses":15,"wins":18},"x-ai/grok-build-0.1":{"draws":0,"losses":1,"wins":1},"xiaomi/mimo-v2.5":{"draws":3,"losses":2,"wins":3},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":0,"wins":2},"z-ai/glm-5.2":{"draws":12,"losses":9,"wins":43}},"gpt-5.6-luna":{"claude-fable-5":{"draws":4,"losses":19,"wins":5},"claude-opus-4-5":{"draws":7,"losses":7,"wins":18},"claude-opus-4-8":{"draws":3,"losses":10,"wins":13},"claude-opus-5":{"draws":10,"losses":45,"wins":9},"claude-sonnet-5":{"draws":10,"losses":4,"wins":16},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":1},"deepseek/deepseek-v4-flash":{"draws":11,"losses":8,"wins":21},"deepseek/deepseek-v4-pro":{"draws":3,"losses":4,"wins":13},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":10},"google/gemini-3.5-flash":{"draws":7,"losses":5,"wins":10},"google/gemini-3.5-flash-lite":{"draws":5,"losses":3,"wins":8},"google/gemini-3.6-flash":{"draws":5,"losses":12,"wins":11},"gpt-4.1":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":9,"losses":9,"wins":8},"gpt-5.4":{"draws":10,"losses":16,"wins":6},"gpt-5.4-mini":{"draws":14,"losses":4,"wins":22},"gpt-5.4-nano":{"draws":12,"losses":23,"wins":25},"gpt-5.5":{"draws":2,"losses":10,"wins":12},"gpt-5.6-luna":{"draws":2,"losses":2,"wins":8},"gpt-5.6-sol":{"draws":0,"losses":14,"wins":14},"gpt-5.6-terra":{"draws":5,"losses":15,"wins":16},"inclusionai/ling-3.0-flash":{"draws":5,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":4,"losses":2,"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":1,"losses":2,"wins":3},"moonshotai/kimi-k3":{"draws":2,"losses":1,"wins":5},"nex-agi/nex-n2-pro":{"draws":3,"losses":2,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":1,"wins":16},"o3":{"draws":1,"losses":10,"wins":17},"openai/gpt-oss-120b":{"draws":4,"losses":1,"wins":7},"poolside/laguna-s-2.1":{"draws":2,"losses":2,"wins":2},"qwen/qwen3.7-max":{"draws":1,"losses":2,"wins":5},"qwen/qwen3.7-plus":{"draws":2,"losses":1,"wins":1},"stepfun/step-3.7-flash":{"draws":1,"losses":2,"wins":9},"tencent/hy3-preview":{"draws":6,"losses":2,"wins":10},"thinkingmachines/inkling":{"draws":6,"losses":2,"wins":10},"x-ai/grok-4.5":{"draws":5,"losses":23,"wins":16},"x-ai/grok-build-0.1":{"draws":4,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":2,"losses":0,"wins":8},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":3,"wins":2},"z-ai/glm-5.2":{"draws":20,"losses":24,"wins":36}},"gpt-5.6-sol":{"claude-fable-5":{"draws":9,"losses":15,"wins":14},"claude-opus-4-5":{"draws":5,"losses":5,"wins":22},"claude-opus-4-8":{"draws":3,"losses":7,"wins":16},"claude-opus-5":{"draws":14,"losses":48,"wins":24},"claude-sonnet-5":{"draws":3,"losses":6,"wins":29},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":3},"deepseek/deepseek-v4-flash":{"draws":0,"losses":5,"wins":33},"deepseek/deepseek-v4-pro":{"draws":0,"losses":2,"wins":12},"google/gemini-3.1-flash-lite":{"draws":1,"losses":2,"wins":11},"google/gemini-3.5-flash":{"draws":7,"losses":4,"wins":13},"google/gemini-3.5-flash-lite":{"draws":0,"losses":1,"wins":9},"google/gemini-3.6-flash":{"draws":3,"losses":7,"wins":16},"gpt-4.1":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":1,"losses":5,"wins":18},"gpt-5.4":{"draws":5,"losses":19,"wins":10},"gpt-5.4-mini":{"draws":5,"losses":13,"wins":26},"gpt-5.4-nano":{"draws":9,"losses":10,"wins":35},"gpt-5.5":{"draws":3,"losses":16,"wins":15},"gpt-5.6-luna":{"draws":0,"losses":7,"wins":15},"gpt-5.6-sol":{"draws":3,"losses":7,"wins":8},"gpt-5.6-terra":{"draws":3,"losses":11,"wins":16},"meituan/longcat-2.0":{"draws":0,"losses":2,"wins":2},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":4},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":4},"moonshotai/kimi-k3":{"draws":0,"losses":2,"wins":8},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":1,"losses":4,"wins":17},"o3":{"draws":1,"losses":6,"wins":17},"openai/gpt-oss-120b":{"draws":3,"losses":3,"wins":6},"poolside/laguna-s-2.1":{"draws":0,"losses":2,"wins":6},"qwen/qwen3.7-max":{"draws":0,"losses":0,"wins":6},"qwen/qwen3.7-plus":{"draws":0,"losses":1,"wins":1},"stepfun/step-3.7-flash":{"draws":0,"losses":1,"wins":11},"tencent/hy3-preview":{"draws":3,"losses":2,"wins":13},"thinkingmachines/inkling":{"draws":2,"losses":3,"wins":5},"x-ai/grok-4.5":{"draws":4,"losses":16,"wins":26},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":0,"losses":3,"wins":9},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":0,"wins":5},"z-ai/glm-5.2":{"draws":9,"losses":12,"wins":47}},"gpt-5.6-terra":{"claude-fable-5":{"draws":4,"losses":30,"wins":4},"claude-opus-4-5":{"draws":11,"losses":8,"wins":17},"claude-opus-4-8":{"draws":1,"losses":16,"wins":5},"claude-opus-5":{"draws":12,"losses":52,"wins":10},"claude-sonnet-5":{"draws":7,"losses":8,"wins":17},"deepseek/deepseek-v4-flash":{"draws":9,"losses":3,"wins":18},"deepseek/deepseek-v4-pro":{"draws":7,"losses":3,"wins":10},"google/gemini-3.1-flash-lite":{"draws":3,"losses":0,"wins":13},"google/gemini-3.5-flash":{"draws":4,"losses":3,"wins":13},"google/gemini-3.5-flash-lite":{"draws":7,"losses":0,"wins":9},"google/gemini-3.6-flash":{"draws":4,"losses":12,"wins":8},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":2},"gpt-4.1":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":5,"losses":5,"wins":16},"gpt-5.4":{"draws":8,"losses":17,"wins":11},"gpt-5.4-mini":{"draws":11,"losses":15,"wins":32},"gpt-5.4-nano":{"draws":7,"losses":20,"wins":23},"gpt-5.5":{"draws":5,"losses":11,"wins":10},"gpt-5.6-luna":{"draws":2,"losses":10,"wins":14},"gpt-5.6-sol":{"draws":3,"losses":14,"wins":19},"gpt-5.6-terra":{"draws":5,"losses":2,"wins":3},"inclusionai/ling-3.0-flash":{"draws":1,"losses":0,"wins":1},"meituan/longcat-2.0":{"draws":5,"losses":1,"wins":0},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":2},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":0,"wins":3},"moonshotai/kimi-k3":{"draws":2,"losses":3,"wins":3},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":0,"wins":13},"o3":{"draws":1,"losses":9,"wins":20},"openai/gpt-oss-120b":{"draws":1,"losses":1,"wins":8},"poolside/laguna-s-2.1":{"draws":2,"losses":2,"wins":0},"qwen/qwen3.7-max":{"draws":1,"losses":1,"wins":4},"qwen/qwen3.7-plus":{"draws":0,"losses":2,"wins":4},"stepfun/step-3.7-flash":{"draws":1,"losses":0,"wins":9},"tencent/hy3-preview":{"draws":4,"losses":2,"wins":10},"thinkingmachines/inkling":{"draws":6,"losses":2,"wins":8},"x-ai/grok-4.5":{"draws":6,"losses":22,"wins":20},"x-ai/grok-build-0.1":{"draws":1,"losses":0,"wins":3},"xiaomi/mimo-v2.5":{"draws":9,"losses":0,"wins":3},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":1,"wins":3},"z-ai/glm-5.2":{"draws":18,"losses":24,"wins":36}},"mistralai/mistral-medium-3-5":{"claude-fable-5":{"draws":0,"losses":8,"wins":0},"claude-opus-4-5":{"draws":4,"losses":8,"wins":0},"claude-opus-4-8":{"draws":0,"losses":10,"wins":0},"claude-opus-5":{"draws":0,"losses":2,"wins":0},"claude-sonnet-5":{"draws":0,"losses":10,"wins":2},"cohere/north-mini-code":{"draws":1,"losses":2,"wins":5},"deepseek/deepseek-v4-flash":{"draws":2,"losses":21,"wins":11},"deepseek/deepseek-v4-pro":{"draws":0,"losses":7,"wins":1},"google/gemini-3.1-flash-lite":{"draws":2,"losses":11,"wins":7},"google/gemini-3.5-flash":{"draws":0,"losses":6,"wins":0},"google/gemini-3.5-flash-lite":{"draws":0,"losses":9,"wins":3},"google/gemini-3.6-flash":{"draws":0,"losses":8,"wins":0},"google/gemma-4-31b-it":{"draws":0,"losses":5,"wins":5},"gpt-4.1":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":0,"losses":12,"wins":0},"gpt-5.4":{"draws":0,"losses":10,"wins":0},"gpt-5.4-mini":{"draws":4,"losses":21,"wins":7},"gpt-5.4-nano":{"draws":2,"losses":25,"wins":21},"gpt-5.5":{"draws":0,"losses":8,"wins":0},"gpt-5.6-luna":{"draws":2,"losses":9,"wins":5},"gpt-5.6-sol":{"draws":0,"losses":10,"wins":0},"gpt-5.6-terra":{"draws":0,"losses":8,"wins":0},"inclusionai/ling-3.0-flash":{"draws":0,"losses":2,"wins":4},"meituan/longcat-2.0":{"draws":0,"losses":4,"wins":2},"minimax/minimax-m3":{"draws":0,"losses":2,"wins":2},"mistralai/mistral-medium-3-5":{"draws":0,"losses":5,"wins":1},"moonshotai/kimi-k3":{"draws":0,"losses":4,"wins":0},"nex-agi/nex-n2-pro":{"draws":0,"losses":4,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":9,"wins":5},"o3":{"draws":0,"losses":20,"wins":2},"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":2,"losses":2,"wins":2},"qwen/qwen3.7-plus":{"draws":1,"losses":2,"wins":3},"stepfun/step-3.7-flash":{"draws":0,"losses":6,"wins":2},"tencent/hy3-preview":{"draws":0,"losses":11,"wins":3},"thinkingmachines/inkling":{"draws":4,"losses":4,"wins":6},"x-ai/grok-4.5":{"draws":0,"losses":14,"wins":0},"x-ai/grok-build-0.1":{"draws":0,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":1,"losses":8,"wins":3},"z-ai/glm-5.2":{"draws":4,"losses":18,"wins":2}},"moonshotai/kimi-k3":{"claude-fable-5":{"draws":2,"losses":8,"wins":0},"claude-opus-4-5":{"draws":12,"losses":3,"wins":31},"claude-opus-4-8":{"draws":2,"losses":4,"wins":2},"claude-opus-5":{"draws":5,"losses":21,"wins":2},"claude-sonnet-5":{"draws":6,"losses":3,"wins":9},"deepseek/deepseek-v4-flash":{"draws":4,"losses":2,"wins":6},"deepseek/deepseek-v4-pro":{"draws":0,"losses":0,"wins":6},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":3},"google/gemini-3.5-flash":{"draws":3,"losses":0,"wins":3},"google/gemini-3.5-flash-lite":{"draws":31,"losses":8,"wins":53},"google/gemini-3.6-flash":{"draws":16,"losses":40,"wins":62},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":1},"gpt-5":{"draws":2,"losses":1,"wins":5},"gpt-5.4":{"draws":2,"losses":4,"wins":2},"gpt-5.4-mini":{"draws":4,"losses":3,"wins":5},"gpt-5.4-nano":{"draws":3,"losses":2,"wins":11},"gpt-5.5":{"draws":3,"losses":2,"wins":3},"gpt-5.6-luna":{"draws":2,"losses":5,"wins":1},"gpt-5.6-sol":{"draws":0,"losses":8,"wins":2},"gpt-5.6-terra":{"draws":2,"losses":3,"wins":3},"inclusionai/ling-3.0-flash":{"draws":2,"losses":1,"wins":5},"meituan/longcat-2.0":{"draws":11,"losses":6,"wins":19},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":4},"moonshotai/kimi-k3":{"draws":49,"losses":31,"wins":76},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":0,"wins":3},"o3":{"draws":3,"losses":16,"wins":49},"openai/gpt-oss-120b":{"draws":5,"losses":1,"wins":4},"poolside/laguna-s-2.1":{"draws":12,"losses":4,"wins":14},"stepfun/step-3.7-flash":{"draws":0,"losses":2,"wins":8},"tencent/hy3-preview":{"draws":2,"losses":2,"wins":4},"thinkingmachines/inkling":{"draws":14,"losses":2,"wins":18},"x-ai/grok-4.5":{"draws":49,"losses":64,"wins":59},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":2,"wins":2},"z-ai/glm-5.2":{"draws":9,"losses":1,"wins":16}},"nvidia/nemotron-3-ultra-550b-a55b":{"claude-fable-5":{"draws":3,"losses":15,"wins":0},"claude-opus-4-5":{"draws":25,"losses":18,"wins":5},"claude-opus-4-8":{"draws":8,"losses":18,"wins":4},"claude-opus-5":{"draws":1,"losses":13,"wins":0},"claude-sonnet-5":{"draws":21,"losses":17,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":2},"deepseek/deepseek-v4-flash":{"draws":34,"losses":14,"wins":22},"deepseek/deepseek-v4-pro":{"draws":9,"losses":8,"wins":5},"google/gemini-3.1-flash-lite":{"draws":9,"losses":4,"wins":12},"google/gemini-3.5-flash":{"draws":3,"losses":8,"wins":3},"google/gemini-3.5-flash-lite":{"draws":9,"losses":6,"wins":9},"google/gemini-3.6-flash":{"draws":4,"losses":11,"wins":3},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":2},"gpt-4.1":{"draws":4,"losses":2,"wins":4},"gpt-5":{"draws":10,"losses":9,"wins":1},"gpt-5.4":{"draws":4,"losses":14,"wins":0},"gpt-5.4-mini":{"draws":34,"losses":19,"wins":7},"gpt-5.4-nano":{"draws":38,"losses":24,"wins":8},"gpt-5.5":{"draws":7,"losses":13,"wins":0},"gpt-5.6-luna":{"draws":11,"losses":12,"wins":1},"gpt-5.6-sol":{"draws":3,"losses":17,"wins":4},"gpt-5.6-terra":{"draws":12,"losses":17,"wins":1},"inclusionai/ling-3.0-flash":{"draws":6,"losses":1,"wins":1},"meituan/longcat-2.0":{"draws":5,"losses":2,"wins":9},"minimax/minimax-m3":{"draws":6,"losses":2,"wins":2},"mistralai/mistral-medium-3-5":{"draws":4,"losses":2,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":5,"losses":3,"wins":0},"nex-agi/nex-n2-pro":{"draws":4,"losses":3,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":5,"wins":3},"o3":{"draws":12,"losses":25,"wins":7},"openai/gpt-oss-120b":{"draws":10,"losses":5,"wins":1},"poolside/laguna-s-2.1":{"draws":4,"losses":3,"wins":1},"qwen/qwen3.7-max":{"draws":8,"losses":0,"wins":0},"qwen/qwen3.7-plus":{"draws":5,"losses":3,"wins":0},"stepfun/step-3.7-flash":{"draws":8,"losses":5,"wins":5},"tencent/hy3-preview":{"draws":11,"losses":9,"wins":4},"thinkingmachines/inkling":{"draws":13,"losses":8,"wins":21},"x-ai/grok-4.5":{"draws":9,"losses":25,"wins":0},"x-ai/grok-build-0.1":{"draws":6,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":21,"losses":6,"wins":9},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":3,"wins":1},"z-ai/glm-5.2":{"draws":33,"losses":30,"wins":23}},"o3":{"claude-fable-5":{"draws":0,"losses":16,"wins":2},"claude-opus-4-5":{"draws":8,"losses":38,"wins":18},"claude-opus-4-8":{"draws":0,"losses":25,"wins":3},"claude-opus-5":{"draws":0,"losses":43,"wins":3},"claude-sonnet-5":{"draws":4,"losses":16,"wins":22},"deepseek/deepseek-v4-flash":{"draws":4,"losses":21,"wins":23},"deepseek/deepseek-v4-pro":{"draws":5,"losses":14,"wins":13},"google/gemini-3.1-flash-lite":{"draws":4,"losses":2,"wins":16},"google/gemini-3.5-flash":{"draws":5,"losses":4,"wins":11},"google/gemini-3.5-flash-lite":{"draws":16,"losses":31,"wins":85},"google/gemini-3.6-flash":{"draws":16,"losses":54,"wins":46},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":2},"gpt-5":{"draws":3,"losses":13,"wins":12},"gpt-5.4":{"draws":1,"losses":19,"wins":2},"gpt-5.4-mini":{"draws":4,"losses":32,"wins":24},"gpt-5.4-nano":{"draws":7,"losses":21,"wins":26},"gpt-5.5":{"draws":1,"losses":23,"wins":2},"gpt-5.6-luna":{"draws":1,"losses":16,"wins":9},"gpt-5.6-sol":{"draws":0,"losses":14,"wins":6},"gpt-5.6-terra":{"draws":0,"losses":19,"wins":9},"inclusionai/ling-3.0-flash":{"draws":0,"losses":3,"wins":11},"meituan/longcat-2.0":{"draws":2,"losses":9,"wins":27},"mistralai/mistral-medium-3-5":{"draws":0,"losses":2,"wins":20},"moonshotai/kimi-k3":{"draws":13,"losses":67,"wins":56},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":7,"wins":25},"o3":{"draws":7,"losses":49,"wins":58},"openai/gpt-oss-120b":{"draws":8,"losses":9,"wins":21},"poolside/laguna-s-2.1":{"draws":6,"losses":8,"wins":10},"stepfun/step-3.7-flash":{"draws":7,"losses":14,"wins":33},"tencent/hy3-preview":{"draws":3,"losses":13,"wins":10},"thinkingmachines/inkling":{"draws":7,"losses":11,"wins":35},"x-ai/grok-4.5":{"draws":9,"losses":90,"wins":41},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":4,"wins":2},"z-ai/glm-5.2":{"draws":7,"losses":42,"wins":31}},"openai/gpt-oss-120b":{"claude-fable-5":{"draws":1,"losses":10,"wins":1},"claude-opus-4-5":{"draws":9,"losses":4,"wins":5},"claude-opus-4-8":{"draws":6,"losses":8,"wins":0},"claude-opus-5":{"draws":3,"losses":13,"wins":2},"claude-sonnet-5":{"draws":9,"losses":7,"wins":2},"cohere/north-mini-code":{"draws":2,"losses":3,"wins":1},"deepseek/deepseek-v4-flash":{"draws":13,"losses":3,"wins":14},"deepseek/deepseek-v4-pro":{"draws":4,"losses":2,"wins":4},"google/gemini-3.1-flash-lite":{"draws":5,"losses":3,"wins":6},"google/gemini-3.5-flash":{"draws":4,"losses":5,"wins":5},"google/gemini-3.5-flash-lite":{"draws":5,"losses":6,"wins":3},"google/gemini-3.6-flash":{"draws":2,"losses":13,"wins":3},"gpt-4.1":{"draws":2,"losses":2,"wins":2},"gpt-5":{"draws":7,"losses":2,"wins":1},"gpt-5.4":{"draws":3,"losses":9,"wins":2},"gpt-5.4-mini":{"draws":12,"losses":8,"wins":8},"gpt-5.4-nano":{"draws":17,"losses":11,"wins":12},"gpt-5.5":{"draws":5,"losses":5,"wins":2},"gpt-5.6-luna":{"draws":7,"losses":8,"wins":3},"gpt-5.6-sol":{"draws":5,"losses":6,"wins":3},"gpt-5.6-terra":{"draws":1,"losses":9,"wins":2},"meituan/longcat-2.0":{"draws":2,"losses":2,"wins":2},"minimax/minimax-m3":{"draws":3,"losses":1,"wins":0},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":4},"moonshotai/kimi-k3":{"draws":3,"losses":2,"wins":1},"nex-agi/nex-n2-pro":{"draws":4,"losses":0,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":1,"wins":5},"o3":{"draws":4,"losses":5,"wins":7},"openai/gpt-oss-120b":{"draws":5,"losses":0,"wins":1},"poolside/laguna-s-2.1":{"draws":0,"losses":1,"wins":1},"qwen/qwen3.7-max":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.7-plus":{"draws":4,"losses":1,"wins":1},"stepfun/step-3.7-flash":{"draws":4,"losses":1,"wins":3},"tencent/hy3-preview":{"draws":6,"losses":3,"wins":3},"thinkingmachines/inkling":{"draws":5,"losses":4,"wins":5},"x-ai/grok-4.5":{"draws":5,"losses":12,"wins":5},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":7,"losses":1,"wins":4},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":4,"wins":1},"z-ai/glm-5.2":{"draws":21,"losses":19,"wins":10}},"stepfun/step-3.7-flash":{"claude-fable-5":{"draws":0,"losses":12,"wins":0},"claude-opus-4-5":{"draws":3,"losses":15,"wins":4},"claude-opus-4-8":{"draws":2,"losses":10,"wins":4},"claude-opus-5":{"draws":0,"losses":6,"wins":0},"claude-sonnet-5":{"draws":4,"losses":11,"wins":3},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":5},"deepseek/deepseek-v4-flash":{"draws":6,"losses":21,"wins":23},"deepseek/deepseek-v4-pro":{"draws":2,"losses":10,"wins":2},"google/gemini-3.1-flash-lite":{"draws":2,"losses":3,"wins":15},"google/gemini-3.5-flash":{"draws":2,"losses":6,"wins":0},"google/gemini-3.5-flash-lite":{"draws":2,"losses":7,"wins":3},"google/gemini-3.6-flash":{"draws":2,"losses":11,"wins":0},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":2},"gpt-4.1":{"draws":0,"losses":2,"wins":2},"gpt-5":{"draws":4,"losses":10,"wins":0},"gpt-5.4":{"draws":0,"losses":12,"wins":0},"gpt-5.4-mini":{"draws":8,"losses":23,"wins":11},"gpt-5.4-nano":{"draws":12,"losses":21,"wins":13},"gpt-5.5":{"draws":0,"losses":10,"wins":0},"gpt-5.6-luna":{"draws":3,"losses":8,"wins":7},"gpt-5.6-sol":{"draws":0,"losses":12,"wins":2},"gpt-5.6-terra":{"draws":3,"losses":10,"wins":1},"inclusionai/ling-3.0-flash":{"draws":0,"losses":2,"wins":4},"meituan/longcat-2.0":{"draws":2,"losses":4,"wins":6},"minimax/minimax-m3":{"draws":1,"losses":5,"wins":0},"mistralai/mistral-medium-3-5":{"draws":2,"losses":4,"wins":8},"moonshotai/kimi-k3":{"draws":0,"losses":3,"wins":1},"nex-agi/nex-n2-pro":{"draws":3,"losses":2,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":5,"wins":9},"o3":{"draws":5,"losses":19,"wins":10},"openai/gpt-oss-120b":{"draws":6,"losses":3,"wins":1},"poolside/laguna-s-2.1":{"draws":0,"losses":1,"wins":3},"qwen/qwen3.7-max":{"draws":2,"losses":5,"wins":1},"qwen/qwen3.7-plus":{"draws":0,"losses":6,"wins":2},"tencent/hy3-preview":{"draws":2,"losses":5,"wins":5},"thinkingmachines/inkling":{"draws":4,"losses":5,"wins":17},"x-ai/grok-4.5":{"draws":0,"losses":22,"wins":0},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":6,"losses":7,"wins":3},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":3,"wins":1},"z-ai/glm-5.2":{"draws":3,"losses":25,"wins":12}},"tencent/hy3-preview":{"claude-fable-5":{"draws":0,"losses":17,"wins":1},"claude-opus-4-5":{"draws":11,"losses":12,"wins":5},"claude-opus-4-8":{"draws":3,"losses":10,"wins":7},"claude-opus-5":{"draws":3,"losses":35,"wins":2},"claude-sonnet-5":{"draws":6,"losses":10,"wins":4},"cohere/north-mini-code":{"draws":1,"losses":2,"wins":3},"deepseek/deepseek-v4-flash":{"draws":12,"losses":16,"wins":22},"deepseek/deepseek-v4-pro":{"draws":2,"losses":10,"wins":4},"google/gemini-3.1-flash-lite":{"draws":4,"losses":6,"wins":8},"google/gemini-3.5-flash":{"draws":4,"losses":8,"wins":2},"google/gemini-3.5-flash-lite":{"draws":3,"losses":3,"wins":4},"google/gemini-3.6-flash":{"draws":3,"losses":13,"wins":8},"google/gemma-4-31b-it":{"draws":3,"losses":4,"wins":3},"gpt-4.1":{"draws":6,"losses":4,"wins":0},"gpt-5":{"draws":3,"losses":9,"wins":8},"gpt-5.4":{"draws":6,"losses":14,"wins":2},"gpt-5.4-mini":{"draws":11,"losses":24,"wins":11},"gpt-5.4-nano":{"draws":19,"losses":16,"wins":15},"gpt-5.5":{"draws":12,"losses":11,"wins":1},"gpt-5.6-luna":{"draws":7,"losses":10,"wins":9},"gpt-5.6-sol":{"draws":4,"losses":17,"wins":7},"gpt-5.6-terra":{"draws":3,"losses":9,"wins":6},"inclusionai/ling-3.0-flash":{"draws":2,"losses":1,"wins":5},"meituan/longcat-2.0":{"draws":3,"losses":2,"wins":3},"minimax/minimax-m3":{"draws":0,"losses":1,"wins":3},"mistralai/mistral-medium-3-5":{"draws":0,"losses":4,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":2,"losses":4,"wins":2},"nex-agi/nex-n2-pro":{"draws":4,"losses":1,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":4,"wins":12},"o3":{"draws":5,"losses":12,"wins":13},"openai/gpt-oss-120b":{"draws":5,"losses":3,"wins":4},"poolside/laguna-s-2.1":{"draws":2,"losses":3,"wins":5},"qwen/qwen3.7-max":{"draws":4,"losses":5,"wins":1},"qwen/qwen3.7-plus":{"draws":0,"losses":3,"wins":7},"stepfun/step-3.7-flash":{"draws":2,"losses":5,"wins":5},"tencent/hy3-preview":{"draws":1,"losses":0,"wins":1},"thinkingmachines/inkling":{"draws":3,"losses":4,"wins":5},"x-ai/grok-4.5":{"draws":5,"losses":29,"wins":2},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":4,"losses":8,"wins":8},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":1,"wins":1},"z-ai/glm-5.2":{"draws":23,"losses":23,"wins":22}},"thinkingmachines/inkling":{"claude-fable-5":{"draws":1,"losses":5,"wins":0},"claude-opus-4-5":{"draws":5,"losses":13,"wins":2},"claude-opus-4-8":{"draws":2,"losses":8,"wins":0},"claude-opus-5":{"draws":1,"losses":15,"wins":2},"claude-sonnet-5":{"draws":7,"losses":10,"wins":3},"deepseek/deepseek-v4-flash":{"draws":9,"losses":12,"wins":1},"deepseek/deepseek-v4-pro":{"draws":6,"losses":2,"wins":2},"google/gemini-3.1-flash-lite":{"draws":2,"losses":2,"wins":6},"google/gemini-3.5-flash":{"draws":5,"losses":6,"wins":1},"google/gemini-3.5-flash-lite":{"draws":20,"losses":30,"wins":22},"google/gemini-3.6-flash":{"draws":18,"losses":29,"wins":7},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":3,"losses":7,"wins":4},"gpt-5.4":{"draws":0,"losses":5,"wins":1},"gpt-5.4-mini":{"draws":8,"losses":13,"wins":1},"gpt-5.4-nano":{"draws":10,"losses":8,"wins":4},"gpt-5.5":{"draws":1,"losses":8,"wins":1},"gpt-5.6-luna":{"draws":3,"losses":9,"wins":0},"gpt-5.6-sol":{"draws":1,"losses":3,"wins":2},"gpt-5.6-terra":{"draws":5,"losses":7,"wins":0},"inclusionai/ling-3.0-flash":{"draws":10,"losses":3,"wins":3},"meituan/longcat-2.0":{"draws":7,"losses":7,"wins":16},"mistralai/mistral-medium-3-5":{"draws":2,"losses":4,"wins":2},"moonshotai/kimi-k3":{"draws":21,"losses":24,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":9,"wins":3},"o3":{"draws":8,"losses":30,"wins":12},"openai/gpt-oss-120b":{"draws":6,"losses":3,"wins":11},"poolside/laguna-s-2.1":{"draws":12,"losses":14,"wins":2},"stepfun/step-3.7-flash":{"draws":5,"losses":8,"wins":7},"tencent/hy3-preview":{"draws":1,"losses":3,"wins":2},"thinkingmachines/inkling":{"draws":4,"losses":10,"wins":6},"x-ai/grok-4.5":{"draws":12,"losses":27,"wins":7},"z-ai/glm-5.2":{"draws":9,"losses":16,"wins":5}},"x-ai/grok-4.5":{"claude-fable-5":{"draws":3,"losses":33,"wins":8},"claude-opus-4-5":{"draws":20,"losses":17,"wins":43},"claude-opus-4-8":{"draws":10,"losses":21,"wins":11},"claude-opus-5":{"draws":11,"losses":62,"wins":27},"claude-sonnet-5":{"draws":12,"losses":7,"wins":23},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":0},"deepseek/deepseek-v4-flash":{"draws":7,"losses":6,"wins":35},"deepseek/deepseek-v4-pro":{"draws":3,"losses":3,"wins":28},"google/gemini-3.1-flash-lite":{"draws":6,"losses":1,"wins":15},"google/gemini-3.5-flash":{"draws":1,"losses":16,"wins":7},"google/gemini-3.5-flash-lite":{"draws":16,"losses":27,"wins":57},"google/gemini-3.6-flash":{"draws":15,"losses":48,"wins":67},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":0},"gpt-4.1":{"draws":2,"losses":1,"wins":7},"gpt-5":{"draws":6,"losses":8,"wins":16},"gpt-5.4":{"draws":8,"losses":21,"wins":11},"gpt-5.4-mini":{"draws":5,"losses":12,"wins":39},"gpt-5.4-nano":{"draws":14,"losses":21,"wins":47},"gpt-5.5":{"draws":11,"losses":15,"wins":12},"gpt-5.6-luna":{"draws":5,"losses":14,"wins":21},"gpt-5.6-sol":{"draws":3,"losses":24,"wins":23},"gpt-5.6-terra":{"draws":3,"losses":16,"wins":23},"inclusionai/ling-3.0-flash":{"draws":2,"losses":2,"wins":18},"meituan/longcat-2.0":{"draws":12,"losses":6,"wins":30},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":4},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":4},"moonshotai/kimi-k3":{"draws":34,"losses":40,"wins":62},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":2,"wins":29},"o3":{"draws":6,"losses":22,"wins":66},"openai/gpt-oss-120b":{"draws":5,"losses":6,"wins":15},"poolside/laguna-s-2.1":{"draws":10,"losses":6,"wins":36},"qwen/qwen3.7-max":{"draws":2,"losses":3,"wins":3},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":4},"stepfun/step-3.7-flash":{"draws":0,"losses":1,"wins":23},"tencent/hy3-preview":{"draws":7,"losses":4,"wins":25},"thinkingmachines/inkling":{"draws":15,"losses":6,"wins":25},"x-ai/grok-4.5":{"draws":39,"losses":69,"wins":66},"xiaomi/mimo-v2.5":{"draws":2,"losses":1,"wins":7},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":6,"wins":5},"z-ai/glm-5.2":{"draws":12,"losses":32,"wins":66}},"xiaomi/mimo-v2.5":{"claude-fable-5":{"draws":1,"losses":3,"wins":0},"claude-opus-4-5":{"draws":12,"losses":5,"wins":3},"claude-opus-4-8":{"draws":7,"losses":2,"wins":1},"claude-opus-5":{"draws":2,"losses":8,"wins":0},"claude-sonnet-5":{"draws":12,"losses":4,"wins":2},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":0},"deepseek/deepseek-v4-flash":{"draws":20,"losses":3,"wins":1},"deepseek/deepseek-v4-pro":{"draws":2,"losses":2,"wins":0},"google/gemini-3.1-flash-lite":{"draws":11,"losses":2,"wins":1},"google/gemini-3.5-flash":{"draws":1,"losses":0,"wins":1},"google/gemini-3.5-flash-lite":{"draws":1,"losses":1,"wins":0},"google/gemini-3.6-flash":{"draws":3,"losses":0,"wins":1},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":0},"gpt-4.1":{"draws":4,"losses":1,"wins":1},"gpt-5":{"draws":9,"losses":3,"wins":2},"gpt-5.4":{"draws":5,"losses":0,"wins":1},"gpt-5.4-mini":{"draws":26,"losses":3,"wins":9},"gpt-5.4-nano":{"draws":35,"losses":10,"wins":5},"gpt-5.5":{"draws":1,"losses":2,"wins":3},"gpt-5.6-luna":{"draws":8,"losses":4,"wins":0},"gpt-5.6-sol":{"draws":3,"losses":3,"wins":0},"gpt-5.6-terra":{"draws":7,"losses":0,"wins":1},"inclusionai/ling-3.0-flash":{"draws":10,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":8,"losses":2,"wins":2},"minimax/minimax-m3":{"draws":1,"losses":5,"wins":0},"mistralai/mistral-medium-3-5":{"draws":3,"losses":3,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":0},"nex-agi/nex-n2-pro":{"draws":5,"losses":0,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":2,"wins":2},"o3":{"draws":1,"losses":1,"wins":0},"openai/gpt-oss-120b":{"draws":4,"losses":2,"wins":2},"poolside/laguna-s-2.1":{"draws":6,"losses":0,"wins":0},"qwen/qwen3.7-max":{"draws":5,"losses":3,"wins":0},"qwen/qwen3.7-plus":{"draws":3,"losses":1,"wins":0},"stepfun/step-3.7-flash":{"draws":4,"losses":0,"wins":4},"thinkingmachines/inkling":{"draws":8,"losses":0,"wins":2},"x-ai/grok-4.5":{"draws":0,"losses":3,"wins":1},"x-ai/grok-build-0.1":{"draws":6,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":13,"losses":9,"wins":0},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":4,"wins":2},"z-ai/glm-5.2":{"draws":29,"losses":9,"wins":6}},"z-ai/glm-5.2":{"claude-fable-5":{"draws":8,"losses":35,"wins":9},"claude-opus-4-5":{"draws":28,"losses":29,"wins":37},"claude-opus-4-8":{"draws":9,"losses":33,"wins":10},"claude-opus-5":{"draws":21,"losses":86,"wins":13},"claude-sonnet-5":{"draws":27,"losses":24,"wins":27},"cohere/north-mini-code":{"draws":10,"losses":1,"wins":3},"deepseek/deepseek-v4-flash":{"draws":47,"losses":20,"wins":31},"deepseek/deepseek-v4-pro":{"draws":10,"losses":19,"wins":7},"google/gemini-3.1-flash-lite":{"draws":10,"losses":3,"wins":23},"google/gemini-3.5-flash":{"draws":11,"losses":15,"wins":16},"google/gemini-3.5-flash-lite":{"draws":23,"losses":14,"wins":27},"google/gemini-3.6-flash":{"draws":17,"losses":31,"wins":18},"google/gemma-4-31b-it":{"draws":3,"losses":2,"wins":5},"gpt-4.1":{"draws":4,"losses":7,"wins":3},"gpt-5":{"draws":27,"losses":17,"wins":12},"gpt-5.4":{"draws":18,"losses":33,"wins":11},"gpt-5.4-mini":{"draws":37,"losses":31,"wins":32},"gpt-5.4-nano":{"draws":66,"losses":30,"wins":39},"gpt-5.5":{"draws":14,"losses":26,"wins":10},"gpt-5.6-luna":{"draws":15,"losses":22,"wins":17},"gpt-5.6-sol":{"draws":11,"losses":31,"wins":20},"gpt-5.6-terra":{"draws":10,"losses":22,"wins":12},"inclusionai/ling-3.0-flash":{"draws":12,"losses":2,"wins":0},"meituan/longcat-2.0":{"draws":13,"losses":4,"wins":9},"minimax/minimax-m3":{"draws":6,"losses":2,"wins":0},"mistralai/mistral-medium-3-5":{"draws":8,"losses":0,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":4},"moonshotai/kimi-k3":{"draws":12,"losses":18,"wins":4},"nex-agi/nex-n2-pro":{"draws":6,"losses":0,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":31,"losses":15,"wins":24},"o3":{"draws":11,"losses":32,"wins":45},"openai/gpt-oss-120b":{"draws":15,"losses":10,"wins":9},"poolside/laguna-s-2.1":{"draws":16,"losses":10,"wins":12},"qwen/qwen3.7-max":{"draws":10,"losses":1,"wins":5},"qwen/qwen3.7-plus":{"draws":10,"losses":3,"wins":5},"stepfun/step-3.7-flash":{"draws":2,"losses":7,"wins":17},"tencent/hy3-preview":{"draws":17,"losses":12,"wins":13},"thinkingmachines/inkling":{"draws":17,"losses":9,"wins":26},"x-ai/grok-4.5":{"draws":11,"losses":59,"wins":18},"x-ai/grok-build-0.1":{"draws":4,"losses":1,"wins":1},"xiaomi/mimo-v2.5":{"draws":29,"losses":7,"wins":18},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":1,"wins":4},"z-ai/glm-5.2":{"draws":48,"losses":66,"wins":62}}},"medium":{"claude-fable-5":{"claude-fable-5":{"draws":2,"losses":10,"wins":2},"claude-opus-4-5":{"draws":3,"losses":4,"wins":21},"claude-opus-4-8":{"draws":3,"losses":16,"wins":11},"claude-opus-5":{"draws":8,"losses":28,"wins":14},"claude-sonnet-5":{"draws":3,"losses":1,"wins":14},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":9},"deepseek/deepseek-v4-flash":{"draws":0,"losses":1,"wins":3},"deepseek/deepseek-v4-pro":{"draws":0,"losses":2,"wins":2},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":11},"google/gemini-3.5-flash":{"draws":3,"losses":8,"wins":7},"google/gemini-3.6-flash":{"draws":0,"losses":7,"wins":7},"google/gemma-4-31b-it":{"draws":1,"losses":1,"wins":6},"gpt-5":{"draws":1,"losses":2,"wins":13},"gpt-5.4":{"draws":5,"losses":14,"wins":11},"gpt-5.4-mini":{"draws":13,"losses":6,"wins":31},"gpt-5.4-nano":{"draws":5,"losses":10,"wins":49},"gpt-5.5":{"draws":3,"losses":11,"wins":10},"gpt-5.6-luna":{"draws":2,"losses":4,"wins":16},"gpt-5.6-sol":{"draws":2,"losses":12,"wins":16},"gpt-5.6-terra":{"draws":3,"losses":4,"wins":21},"meituan/longcat-2.0":{"draws":1,"losses":1,"wins":4},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":11},"moonshotai/kimi-k3":{"draws":0,"losses":0,"wins":10},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":1,"losses":0,"wins":11},"o3":{"draws":1,"losses":0,"wins":11},"openai/gpt-oss-120b":{"draws":3,"losses":0,"wins":9},"poolside/laguna-s-2.1":{"draws":0,"losses":4,"wins":0},"qwen/qwen3.7-max":{"draws":2,"losses":2,"wins":12},"qwen/qwen3.7-plus":{"draws":1,"losses":1,"wins":10},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":8},"tencent/hy3-preview":{"draws":1,"losses":2,"wins":5},"thinkingmachines/inkling":{"draws":0,"losses":0,"wins":2},"x-ai/grok-4.5":{"draws":9,"losses":14,"wins":21},"x-ai/grok-build-0.1":{"draws":2,"losses":3,"wins":9},"xiaomi/mimo-v2.5":{"draws":3,"losses":2,"wins":31},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":14},"z-ai/glm-5.2":{"draws":1,"losses":7,"wins":22}},"claude-opus-4-5":{"claude-fable-5":{"draws":4,"losses":19,"wins":1},"claude-opus-4-5":{"draws":14,"losses":15,"wins":7},"claude-opus-4-8":{"draws":6,"losses":17,"wins":9},"claude-opus-5":{"draws":18,"losses":51,"wins":13},"claude-sonnet-5":{"draws":21,"losses":12,"wins":19},"cohere/north-mini-code":{"draws":5,"losses":2,"wins":11},"deepseek/deepseek-v4-flash":{"draws":13,"losses":5,"wins":8},"deepseek/deepseek-v4-pro":{"draws":6,"losses":3,"wins":3},"google/gemini-3.1-flash-lite":{"draws":10,"losses":0,"wins":18},"google/gemini-3.5-flash":{"draws":10,"losses":11,"wins":9},"google/gemini-3.5-flash-lite":{"draws":12,"losses":7,"wins":25},"google/gemini-3.6-flash":{"draws":9,"losses":19,"wins":12},"google/gemma-4-31b-it":{"draws":4,"losses":7,"wins":3},"gpt-4.1":{"draws":2,"losses":1,"wins":3},"gpt-5":{"draws":8,"losses":11,"wins":15},"gpt-5.4":{"draws":15,"losses":13,"wins":6},"gpt-5.4-mini":{"draws":38,"losses":22,"wins":40},"gpt-5.4-nano":{"draws":31,"losses":24,"wins":47},"gpt-5.5":{"draws":19,"losses":11,"wins":10},"gpt-5.6-luna":{"draws":15,"losses":13,"wins":10},"gpt-5.6-sol":{"draws":11,"losses":22,"wins":3},"gpt-5.6-terra":{"draws":20,"losses":12,"wins":10},"inclusionai/ling-3.0-flash":{"draws":3,"losses":2,"wins":7},"meituan/longcat-2.0":{"draws":10,"losses":7,"wins":16},"minimax/minimax-m3":{"draws":4,"losses":3,"wins":19},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":7,"wins":9},"moonshotai/kimi-k3":{"draws":20,"losses":32,"wins":12},"nex-agi/nex-n2-pro":{"draws":2,"losses":2,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":7,"wins":10},"o3":{"draws":8,"losses":18,"wins":22},"openai/gpt-oss-120b":{"draws":8,"losses":5,"wins":17},"poolside/laguna-s-2.1":{"draws":7,"losses":2,"wins":11},"qwen/qwen3.7-max":{"draws":13,"losses":7,"wins":10},"qwen/qwen3.7-plus":{"draws":11,"losses":6,"wins":9},"stepfun/step-3.7-flash":{"draws":9,"losses":4,"wins":11},"tencent/hy3-preview":{"draws":4,"losses":1,"wins":5},"thinkingmachines/inkling":{"draws":11,"losses":6,"wins":15},"x-ai/grok-4.5":{"draws":29,"losses":42,"wins":25},"x-ai/grok-build-0.1":{"draws":7,"losses":6,"wins":9},"xiaomi/mimo-v2.5":{"draws":28,"losses":12,"wins":24},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":8,"wins":13},"z-ai/glm-5.2":{"draws":34,"losses":28,"wins":28}},"claude-opus-4-8":{"claude-fable-5":{"draws":2,"losses":10,"wins":6},"claude-opus-4-5":{"draws":6,"losses":11,"wins":13},"claude-opus-4-8":{"draws":4,"losses":6,"wins":2},"claude-opus-5":{"draws":3,"losses":14,"wins":1},"claude-sonnet-5":{"draws":8,"losses":4,"wins":10},"cohere/north-mini-code":{"draws":7,"losses":2,"wins":5},"deepseek/deepseek-v4-flash":{"draws":12,"losses":2,"wins":4},"deepseek/deepseek-v4-pro":{"draws":5,"losses":4,"wins":3},"google/gemini-3.1-flash-lite":{"draws":6,"losses":1,"wins":11},"google/gemini-3.5-flash":{"draws":8,"losses":9,"wins":3},"google/gemini-3.5-flash-lite":{"draws":10,"losses":0,"wins":6},"google/gemini-3.6-flash":{"draws":8,"losses":10,"wins":4},"google/gemma-4-31b-it":{"draws":7,"losses":0,"wins":7},"gpt-4.1":{"draws":2,"losses":2,"wins":0},"gpt-5":{"draws":4,"losses":5,"wins":9},"gpt-5.4":{"draws":6,"losses":10,"wins":6},"gpt-5.4-mini":{"draws":31,"losses":16,"wins":21},"gpt-5.4-nano":{"draws":22,"losses":15,"wins":31},"gpt-5.5":{"draws":10,"losses":9,"wins":7},"gpt-5.6-luna":{"draws":12,"losses":9,"wins":5},"gpt-5.6-sol":{"draws":7,"losses":15,"wins":4},"gpt-5.6-terra":{"draws":12,"losses":6,"wins":6},"inclusionai/ling-3.0-flash":{"draws":10,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":5,"losses":6,"wins":5},"minimax/minimax-m3":{"draws":8,"losses":2,"wins":6},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":4,"wins":4},"moonshotai/kimi-k3":{"draws":7,"losses":7,"wins":4},"nex-agi/nex-n2-pro":{"draws":10,"losses":0,"wins":12},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":5,"wins":7},"o3":{"draws":4,"losses":1,"wins":7},"openai/gpt-oss-120b":{"draws":9,"losses":1,"wins":6},"poolside/laguna-s-2.1":{"draws":8,"losses":1,"wins":9},"qwen/qwen3.7-max":{"draws":7,"losses":2,"wins":9},"qwen/qwen3.7-plus":{"draws":6,"losses":2,"wins":8},"stepfun/step-3.7-flash":{"draws":5,"losses":4,"wins":3},"tencent/hy3-preview":{"draws":4,"losses":3,"wins":1},"thinkingmachines/inkling":{"draws":5,"losses":2,"wins":5},"x-ai/grok-4.5":{"draws":6,"losses":26,"wins":6},"x-ai/grok-build-0.1":{"draws":7,"losses":4,"wins":9},"xiaomi/mimo-v2.5":{"draws":21,"losses":3,"wins":16},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":4,"wins":7},"z-ai/glm-5.2":{"draws":20,"losses":10,"wins":22}},"claude-opus-5":{"claude-fable-5":{"draws":10,"losses":21,"wins":17},"claude-opus-4-5":{"draws":15,"losses":6,"wins":73},"claude-opus-4-8":{"draws":8,"losses":9,"wins":25},"claude-opus-5":{"draws":15,"losses":59,"wins":54},"claude-sonnet-5":{"draws":12,"losses":10,"wins":44},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":9},"deepseek/deepseek-v4-flash":{"draws":2,"losses":2,"wins":22},"deepseek/deepseek-v4-pro":{"draws":1,"losses":1,"wins":12},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":9},"google/gemini-3.5-flash":{"draws":6,"losses":5,"wins":21},"google/gemini-3.5-flash-lite":{"draws":7,"losses":4,"wins":19},"google/gemini-3.6-flash":{"draws":3,"losses":11,"wins":36},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":4},"gpt-4.1":{"draws":2,"losses":1,"wins":19},"gpt-5":{"draws":3,"losses":2,"wins":17},"gpt-5.4":{"draws":4,"losses":18,"wins":34},"gpt-5.4-mini":{"draws":9,"losses":8,"wins":79},"gpt-5.4-nano":{"draws":12,"losses":9,"wins":45},"gpt-5.5":{"draws":7,"losses":16,"wins":35},"gpt-5.6-luna":{"draws":4,"losses":7,"wins":21},"gpt-5.6-sol":{"draws":5,"losses":19,"wins":48},"gpt-5.6-terra":{"draws":17,"losses":5,"wins":44},"inclusionai/ling-3.0-flash":{"draws":2,"losses":1,"wins":9},"meituan/longcat-2.0":{"draws":4,"losses":6,"wins":20},"minimax/minimax-m3":{"draws":1,"losses":3,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":16},"moonshotai/kimi-k3":{"draws":9,"losses":4,"wins":43},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":0,"wins":16},"o3":{"draws":0,"losses":0,"wins":14},"openai/gpt-oss-120b":{"draws":2,"losses":1,"wins":7},"poolside/laguna-s-2.1":{"draws":2,"losses":3,"wins":31},"qwen/qwen3.7-max":{"draws":6,"losses":3,"wins":31},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":14},"stepfun/step-3.7-flash":{"draws":3,"losses":1,"wins":8},"tencent/hy3-preview":{"draws":3,"losses":4,"wins":13},"thinkingmachines/inkling":{"draws":6,"losses":2,"wins":20},"x-ai/grok-4.5":{"draws":11,"losses":32,"wins":55},"x-ai/grok-build-0.1":{"draws":3,"losses":1,"wins":6},"xiaomi/mimo-v2.5":{"draws":2,"losses":1,"wins":25},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":0,"wins":16},"z-ai/glm-5.2":{"draws":9,"losses":15,"wins":90}},"claude-sonnet-5":{"claude-fable-5":{"draws":2,"losses":12,"wins":0},"claude-opus-4-5":{"draws":13,"losses":13,"wins":14},"claude-opus-4-8":{"draws":6,"losses":5,"wins":7},"claude-opus-5":{"draws":5,"losses":20,"wins":3},"claude-sonnet-5":{"draws":7,"losses":6,"wins":1},"cohere/north-mini-code":{"draws":4,"losses":2,"wins":6},"deepseek/deepseek-v4-flash":{"draws":14,"losses":5,"wins":9},"deepseek/deepseek-v4-pro":{"draws":4,"losses":1,"wins":1},"google/gemini-3.1-flash-lite":{"draws":5,"losses":2,"wins":7},"google/gemini-3.5-flash":{"draws":5,"losses":5,"wins":4},"google/gemini-3.5-flash-lite":{"draws":8,"losses":0,"wins":14},"google/gemini-3.6-flash":{"draws":4,"losses":12,"wins":4},"google/gemma-4-31b-it":{"draws":3,"losses":3,"wins":4},"gpt-4.1":{"draws":4,"losses":1,"wins":5},"gpt-5":{"draws":5,"losses":6,"wins":3},"gpt-5.4":{"draws":5,"losses":9,"wins":2},"gpt-5.4-mini":{"draws":23,"losses":16,"wins":17},"gpt-5.4-nano":{"draws":20,"losses":10,"wins":28},"gpt-5.5":{"draws":4,"losses":10,"wins":4},"gpt-5.6-luna":{"draws":7,"losses":5,"wins":4},"gpt-5.6-sol":{"draws":2,"losses":14,"wins":2},"gpt-5.6-terra":{"draws":8,"losses":6,"wins":6},"inclusionai/ling-3.0-flash":{"draws":4,"losses":2,"wins":14},"meituan/longcat-2.0":{"draws":3,"losses":6,"wins":17},"minimax/minimax-m3":{"draws":5,"losses":4,"wins":5},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":5,"wins":6},"moonshotai/kimi-k3":{"draws":7,"losses":8,"wins":9},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":9,"wins":4},"o3":{"draws":3,"losses":1,"wins":8},"openai/gpt-oss-120b":{"draws":5,"losses":0,"wins":7},"poolside/laguna-s-2.1":{"draws":7,"losses":4,"wins":11},"qwen/qwen3.7-max":{"draws":7,"losses":7,"wins":6},"qwen/qwen3.7-plus":{"draws":6,"losses":5,"wins":3},"stepfun/step-3.7-flash":{"draws":3,"losses":1,"wins":6},"tencent/hy3-preview":{"draws":2,"losses":2,"wins":2},"thinkingmachines/inkling":{"draws":6,"losses":1,"wins":7},"x-ai/grok-4.5":{"draws":6,"losses":19,"wins":5},"x-ai/grok-build-0.1":{"draws":6,"losses":0,"wins":10},"xiaomi/mimo-v2.5":{"draws":26,"losses":4,"wins":22},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":6,"wins":6},"z-ai/glm-5.2":{"draws":19,"losses":17,"wins":22}},"cohere/north-mini-code":{"claude-fable-5":{"draws":1,"losses":9,"wins":0},"claude-opus-4-5":{"draws":4,"losses":11,"wins":3},"claude-opus-4-8":{"draws":5,"losses":5,"wins":2},"claude-opus-5":{"draws":0,"losses":6,"wins":0},"claude-sonnet-5":{"draws":8,"losses":11,"wins":3},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":4},"deepseek/deepseek-v4-flash":{"draws":11,"losses":5,"wins":20},"deepseek/deepseek-v4-pro":{"draws":1,"losses":2,"wins":1},"google/gemini-3.1-flash-lite":{"draws":6,"losses":7,"wins":7},"google/gemini-3.5-flash":{"draws":5,"losses":12,"wins":1},"google/gemini-3.5-flash-lite":{"draws":10,"losses":0,"wins":10},"google/gemini-3.6-flash":{"draws":5,"losses":9,"wins":2},"google/gemma-4-31b-it":{"draws":2,"losses":3,"wins":3},"gpt-4.1":{"draws":3,"losses":1,"wins":0},"gpt-5":{"draws":5,"losses":13,"wins":2},"gpt-5.4":{"draws":4,"losses":11,"wins":5},"gpt-5.4-mini":{"draws":14,"losses":17,"wins":13},"gpt-5.4-nano":{"draws":24,"losses":22,"wins":16},"gpt-5.5":{"draws":7,"losses":7,"wins":2},"gpt-5.6-luna":{"draws":3,"losses":5,"wins":10},"gpt-5.6-sol":{"draws":5,"losses":11,"wins":0},"gpt-5.6-terra":{"draws":3,"losses":9,"wins":4},"inclusionai/ling-3.0-flash":{"draws":6,"losses":8,"wins":6},"meituan/longcat-2.0":{"draws":6,"losses":10,"wins":6},"minimax/minimax-m3":{"draws":3,"losses":4,"wins":7},"mistralai/mistral-medium-3-5":{"draws":2,"losses":4,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":3,"wins":2},"moonshotai/kimi-k3":{"draws":4,"losses":3,"wins":7},"nex-agi/nex-n2-pro":{"draws":7,"losses":7,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":8,"wins":9},"o3":{"draws":4,"losses":6,"wins":2},"openai/gpt-oss-120b":{"draws":10,"losses":1,"wins":5},"poolside/laguna-s-2.1":{"draws":8,"losses":1,"wins":11},"qwen/qwen3.7-max":{"draws":6,"losses":7,"wins":3},"qwen/qwen3.7-plus":{"draws":2,"losses":8,"wins":6},"stepfun/step-3.7-flash":{"draws":2,"losses":3,"wins":1},"tencent/hy3-preview":{"draws":1,"losses":3,"wins":2},"thinkingmachines/inkling":{"draws":4,"losses":1,"wins":11},"x-ai/grok-4.5":{"draws":7,"losses":20,"wins":1},"x-ai/grok-build-0.1":{"draws":4,"losses":5,"wins":3},"xiaomi/mimo-v2.5":{"draws":13,"losses":9,"wins":10},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":5,"wins":4},"z-ai/glm-5.2":{"draws":13,"losses":8,"wins":11}},"deepseek/deepseek-v4-flash":{"claude-fable-5":{"draws":2,"losses":7,"wins":1},"claude-opus-4-5":{"draws":9,"losses":6,"wins":3},"claude-opus-4-8":{"draws":8,"losses":8,"wins":0},"claude-opus-5":{"draws":3,"losses":21,"wins":0},"claude-sonnet-5":{"draws":14,"losses":20,"wins":2},"cohere/north-mini-code":{"draws":8,"losses":8,"wins":6},"deepseek/deepseek-v4-flash":{"draws":28,"losses":35,"wins":31},"deepseek/deepseek-v4-pro":{"draws":10,"losses":14,"wins":2},"google/gemini-3.1-flash-lite":{"draws":9,"losses":19,"wins":18},"google/gemini-3.5-flash":{"draws":7,"losses":6,"wins":1},"google/gemini-3.5-flash-lite":{"draws":1,"losses":0,"wins":1},"google/gemini-3.6-flash":{"draws":3,"losses":5,"wins":2},"google/gemma-4-31b-it":{"draws":7,"losses":9,"wins":8},"gpt-4.1":{"draws":6,"losses":9,"wins":5},"gpt-5":{"draws":7,"losses":6,"wins":1},"gpt-5.4":{"draws":10,"losses":11,"wins":5},"gpt-5.4-mini":{"draws":42,"losses":46,"wins":26},"gpt-5.4-nano":{"draws":46,"losses":21,"wins":39},"gpt-5.5":{"draws":15,"losses":13,"wins":0},"gpt-5.6-luna":{"draws":14,"losses":5,"wins":13},"gpt-5.6-sol":{"draws":3,"losses":14,"wins":3},"gpt-5.6-terra":{"draws":11,"losses":15,"wins":4},"inclusionai/ling-3.0-flash":{"draws":10,"losses":7,"wins":7},"meituan/longcat-2.0":{"draws":8,"losses":8,"wins":10},"minimax/minimax-m3":{"draws":8,"losses":10,"wins":12},"mistralai/mistral-medium-3-5":{"draws":7,"losses":7,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":3,"wins":2},"nex-agi/nex-n2-pro":{"draws":8,"losses":13,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":20,"losses":10,"wins":12},"o3":{"draws":3,"losses":1,"wins":2},"openai/gpt-oss-120b":{"draws":12,"losses":13,"wins":3},"poolside/laguna-s-2.1":{"draws":12,"losses":8,"wins":4},"qwen/qwen3.7-max":{"draws":10,"losses":2,"wins":4},"qwen/qwen3.7-plus":{"draws":9,"losses":11,"wins":8},"stepfun/step-3.7-flash":{"draws":4,"losses":11,"wins":5},"tencent/hy3-preview":{"draws":10,"losses":9,"wins":7},"thinkingmachines/inkling":{"draws":6,"losses":15,"wins":3},"x-ai/grok-4.5":{"draws":3,"losses":5,"wins":4},"x-ai/grok-build-0.1":{"draws":6,"losses":5,"wins":5},"xiaomi/mimo-v2.5":{"draws":26,"losses":35,"wins":13},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":12,"wins":6},"z-ai/glm-5.2":{"draws":40,"losses":32,"wins":18}},"google/gemini-3.1-flash-lite":{"claude-fable-5":{"draws":1,"losses":13,"wins":0},"claude-opus-4-5":{"draws":6,"losses":20,"wins":0},"claude-opus-4-8":{"draws":6,"losses":10,"wins":2},"claude-opus-5":{"draws":1,"losses":8,"wins":1},"claude-sonnet-5":{"draws":6,"losses":11,"wins":3},"cohere/north-mini-code":{"draws":4,"losses":6,"wins":4},"deepseek/deepseek-v4-flash":{"draws":7,"losses":10,"wins":13},"google/gemini-3.1-flash-lite":{"draws":0,"losses":4,"wins":6},"google/gemini-3.5-flash":{"draws":3,"losses":9,"wins":0},"google/gemini-3.5-flash-lite":{"draws":6,"losses":4,"wins":8},"google/gemini-3.6-flash":{"draws":2,"losses":4,"wins":0},"google/gemma-4-31b-it":{"draws":6,"losses":9,"wins":7},"gpt-4.1":{"draws":2,"losses":2,"wins":2},"gpt-5":{"draws":6,"losses":6,"wins":2},"gpt-5.4":{"draws":5,"losses":13,"wins":0},"gpt-5.4-mini":{"draws":15,"losses":31,"wins":10},"gpt-5.4-nano":{"draws":15,"losses":26,"wins":19},"gpt-5.5":{"draws":3,"losses":7,"wins":2},"gpt-5.6-luna":{"draws":6,"losses":9,"wins":7},"gpt-5.6-sol":{"draws":3,"losses":11,"wins":2},"gpt-5.6-terra":{"draws":5,"losses":8,"wins":3},"inclusionai/ling-3.0-flash":{"draws":3,"losses":4,"wins":7},"meituan/longcat-2.0":{"draws":3,"losses":12,"wins":11},"minimax/minimax-m3":{"draws":5,"losses":5,"wins":6},"mistralai/mistral-medium-3-5":{"draws":0,"losses":4,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":8,"wins":0},"moonshotai/kimi-k3":{"draws":4,"losses":5,"wins":1},"nex-agi/nex-n2-pro":{"draws":4,"losses":4,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":6,"wins":8},"o3":{"draws":6,"losses":6,"wins":0},"openai/gpt-oss-120b":{"draws":4,"losses":4,"wins":2},"poolside/laguna-s-2.1":{"draws":2,"losses":5,"wins":7},"qwen/qwen3.7-max":{"draws":5,"losses":7,"wins":4},"qwen/qwen3.7-plus":{"draws":4,"losses":8,"wins":4},"stepfun/step-3.7-flash":{"draws":2,"losses":5,"wins":1},"tencent/hy3-preview":{"draws":1,"losses":0,"wins":1},"thinkingmachines/inkling":{"draws":1,"losses":10,"wins":5},"x-ai/grok-4.5":{"draws":6,"losses":14,"wins":0},"x-ai/grok-build-0.1":{"draws":4,"losses":9,"wins":1},"xiaomi/mimo-v2.5":{"draws":17,"losses":17,"wins":16},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":6,"wins":2},"z-ai/glm-5.2":{"draws":18,"losses":17,"wins":5}},"google/gemini-3.5-flash":{"claude-fable-5":{"draws":8,"losses":12,"wins":6},"claude-opus-4-5":{"draws":10,"losses":11,"wins":11},"claude-opus-4-8":{"draws":12,"losses":5,"wins":11},"claude-opus-5":{"draws":7,"losses":28,"wins":11},"claude-sonnet-5":{"draws":12,"losses":11,"wins":9},"cohere/north-mini-code":{"draws":3,"losses":1,"wins":12},"deepseek/deepseek-v4-flash":{"draws":9,"losses":2,"wins":7},"deepseek/deepseek-v4-pro":{"draws":0,"losses":0,"wins":2},"google/gemini-3.1-flash-lite":{"draws":4,"losses":0,"wins":10},"google/gemini-3.5-flash":{"draws":2,"losses":2,"wins":2},"google/gemini-3.5-flash-lite":{"draws":2,"losses":1,"wins":5},"google/gemini-3.6-flash":{"draws":4,"losses":6,"wins":8},"google/gemma-4-31b-it":{"draws":3,"losses":3,"wins":4},"gpt-4.1":{"draws":0,"losses":2,"wins":2},"gpt-5":{"draws":6,"losses":3,"wins":11},"gpt-5.4":{"draws":12,"losses":10,"wins":4},"gpt-5.4-mini":{"draws":17,"losses":8,"wins":25},"gpt-5.4-nano":{"draws":16,"losses":8,"wins":34},"gpt-5.5":{"draws":3,"losses":9,"wins":14},"gpt-5.6-luna":{"draws":12,"losses":4,"wins":8},"gpt-5.6-sol":{"draws":9,"losses":12,"wins":7},"gpt-5.6-terra":{"draws":9,"losses":4,"wins":17},"inclusionai/ling-3.0-flash":{"draws":4,"losses":2,"wins":2},"meituan/longcat-2.0":{"draws":6,"losses":2,"wins":2},"minimax/minimax-m3":{"draws":3,"losses":1,"wins":10},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":6,"wins":3},"moonshotai/kimi-k3":{"draws":12,"losses":5,"wins":7},"nex-agi/nex-n2-pro":{"draws":4,"losses":0,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":0,"wins":8},"o3":{"draws":1,"losses":6,"wins":5},"openai/gpt-oss-120b":{"draws":9,"losses":1,"wins":8},"poolside/laguna-s-2.1":{"draws":5,"losses":3,"wins":6},"qwen/qwen3.7-max":{"draws":8,"losses":7,"wins":9},"qwen/qwen3.7-plus":{"draws":4,"losses":1,"wins":9},"stepfun/step-3.7-flash":{"draws":3,"losses":1,"wins":4},"tencent/hy3-preview":{"draws":0,"losses":0,"wins":4},"thinkingmachines/inkling":{"draws":3,"losses":2,"wins":7},"x-ai/grok-4.5":{"draws":8,"losses":15,"wins":17},"x-ai/grok-build-0.1":{"draws":8,"losses":1,"wins":7},"xiaomi/mimo-v2.5":{"draws":17,"losses":3,"wins":20},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":4,"wins":7},"z-ai/glm-5.2":{"draws":10,"losses":17,"wins":17}},"google/gemini-3.5-flash-lite":{"claude-opus-4-5":{"draws":17,"losses":18,"wins":3},"claude-opus-4-8":{"draws":11,"losses":7,"wins":0},"claude-opus-5":{"draws":6,"losses":14,"wins":2},"claude-sonnet-5":{"draws":12,"losses":14,"wins":0},"cohere/north-mini-code":{"draws":12,"losses":10,"wins":0},"deepseek/deepseek-v4-flash":{"draws":3,"losses":3,"wins":2},"deepseek/deepseek-v4-pro":{"draws":1,"losses":2,"wins":1},"google/gemini-3.1-flash-lite":{"draws":7,"losses":8,"wins":5},"google/gemini-3.5-flash":{"draws":2,"losses":5,"wins":1},"google/gemini-3.5-flash-lite":{"draws":29,"losses":23,"wins":30},"google/gemini-3.6-flash":{"draws":34,"losses":27,"wins":12},"google/gemma-4-31b-it":{"draws":2,"losses":11,"wins":1},"gpt-4.1":{"draws":0,"losses":2,"wins":0},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":2},"gpt-5":{"draws":9,"losses":4,"wins":5},"gpt-5.4":{"draws":2,"losses":5,"wins":1},"gpt-5.4-mini":{"draws":30,"losses":27,"wins":9},"gpt-5.4-nano":{"draws":21,"losses":11,"wins":24},"gpt-5.5":{"draws":13,"losses":7,"wins":0},"gpt-5.6-luna":{"draws":8,"losses":5,"wins":1},"gpt-5.6-sol":{"draws":6,"losses":2,"wins":0},"gpt-5.6-terra":{"draws":13,"losses":7,"wins":0},"inclusionai/ling-3.0-flash":{"draws":10,"losses":8,"wins":8},"meituan/longcat-2.0":{"draws":14,"losses":21,"wins":9},"minimax/minimax-m3":{"draws":6,"losses":4,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":0,"wins":4},"moonshotai/kimi-k3":{"draws":34,"losses":37,"wins":7},"nex-agi/nex-n2-pro":{"draws":3,"losses":5,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":2,"wins":2},"o3":{"draws":15,"losses":48,"wins":9},"openai/gpt-oss-120b":{"draws":13,"losses":11,"wins":14},"poolside/laguna-s-2.1":{"draws":19,"losses":15,"wins":8},"qwen/qwen3.7-max":{"draws":5,"losses":4,"wins":3},"qwen/qwen3.7-plus":{"draws":10,"losses":6,"wins":2},"stepfun/step-3.7-flash":{"draws":7,"losses":13,"wins":4},"thinkingmachines/inkling":{"draws":10,"losses":10,"wins":18},"x-ai/grok-4.5":{"draws":22,"losses":44,"wins":8},"x-ai/grok-build-0.1":{"draws":10,"losses":10,"wins":2},"xiaomi/mimo-v2.5":{"draws":11,"losses":15,"wins":8},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":5,"wins":3},"z-ai/glm-5.2":{"draws":15,"losses":6,"wins":5}},"google/gemini-3.6-flash":{"claude-fable-5":{"draws":0,"losses":7,"wins":9},"claude-opus-4-5":{"draws":11,"losses":10,"wins":19},"claude-opus-4-8":{"draws":10,"losses":4,"wins":14},"claude-opus-5":{"draws":3,"losses":27,"wins":14},"claude-sonnet-5":{"draws":8,"losses":6,"wins":18},"cohere/north-mini-code":{"draws":5,"losses":4,"wins":11},"deepseek/deepseek-v4-flash":{"draws":8,"losses":6,"wins":10},"deepseek/deepseek-v4-pro":{"draws":0,"losses":1,"wins":1},"google/gemini-3.1-flash-lite":{"draws":3,"losses":0,"wins":9},"google/gemini-3.5-flash":{"draws":4,"losses":8,"wins":6},"google/gemini-3.5-flash-lite":{"draws":23,"losses":12,"wins":34},"google/gemini-3.6-flash":{"draws":16,"losses":20,"wins":22},"google/gemma-4-31b-it":{"draws":1,"losses":3,"wins":6},"gpt-4.1":{"draws":3,"losses":0,"wins":3},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":2,"losses":5,"wins":9},"gpt-5.4":{"draws":10,"losses":10,"wins":12},"gpt-5.4-mini":{"draws":20,"losses":9,"wins":34},"gpt-5.4-nano":{"draws":20,"losses":5,"wins":27},"gpt-5.5":{"draws":9,"losses":7,"wins":12},"gpt-5.6-luna":{"draws":8,"losses":3,"wins":15},"gpt-5.6-sol":{"draws":7,"losses":7,"wins":12},"gpt-5.6-terra":{"draws":8,"losses":6,"wins":14},"inclusionai/ling-3.0-flash":{"draws":12,"losses":2,"wins":16},"meituan/longcat-2.0":{"draws":15,"losses":6,"wins":19},"minimax/minimax-m3":{"draws":7,"losses":2,"wins":9},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":2,"wins":9},"moonshotai/kimi-k3":{"draws":21,"losses":44,"wins":53},"nex-agi/nex-n2-pro":{"draws":3,"losses":1,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":1,"wins":10},"o3":{"draws":10,"losses":11,"wins":29},"openai/gpt-oss-120b":{"draws":11,"losses":2,"wins":7},"poolside/laguna-s-2.1":{"draws":12,"losses":4,"wins":16},"qwen/qwen3.7-max":{"draws":1,"losses":2,"wins":13},"qwen/qwen3.7-plus":{"draws":5,"losses":2,"wins":15},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":8},"tencent/hy3-preview":{"draws":4,"losses":3,"wins":1},"thinkingmachines/inkling":{"draws":12,"losses":4,"wins":14},"x-ai/grok-4.5":{"draws":24,"losses":44,"wins":52},"x-ai/grok-build-0.1":{"draws":6,"losses":0,"wins":6},"xiaomi/mimo-v2.5":{"draws":18,"losses":4,"wins":10},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":2,"wins":8},"z-ai/glm-5.2":{"draws":17,"losses":7,"wins":8}},"google/gemma-4-31b-it":{"claude-fable-5":{"draws":1,"losses":6,"wins":1},"claude-opus-4-5":{"draws":4,"losses":5,"wins":11},"claude-opus-4-8":{"draws":4,"losses":6,"wins":2},"claude-opus-5":{"draws":0,"losses":8,"wins":0},"claude-sonnet-5":{"draws":3,"losses":7,"wins":4},"cohere/north-mini-code":{"draws":2,"losses":3,"wins":3},"deepseek/deepseek-v4-flash":{"draws":3,"losses":6,"wins":13},"deepseek/deepseek-v4-pro":{"draws":1,"losses":2,"wins":1},"google/gemini-3.1-flash-lite":{"draws":4,"losses":4,"wins":6},"google/gemini-3.5-flash":{"draws":1,"losses":6,"wins":5},"google/gemini-3.5-flash-lite":{"draws":0,"losses":1,"wins":9},"google/gemini-3.6-flash":{"draws":0,"losses":4,"wins":2},"google/gemma-4-31b-it":{"draws":2,"losses":2,"wins":2},"gpt-4.1":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":1,"losses":5,"wins":2},"gpt-5.4":{"draws":1,"losses":6,"wins":3},"gpt-5.4-mini":{"draws":11,"losses":16,"wins":15},"gpt-5.4-nano":{"draws":6,"losses":15,"wins":15},"gpt-5.5":{"draws":2,"losses":7,"wins":1},"gpt-5.6-luna":{"draws":2,"losses":7,"wins":5},"gpt-5.6-sol":{"draws":4,"losses":6,"wins":2},"gpt-5.6-terra":{"draws":1,"losses":9,"wins":2},"inclusionai/ling-3.0-flash":{"draws":0,"losses":3,"wins":5},"meituan/longcat-2.0":{"draws":0,"losses":8,"wins":6},"minimax/minimax-m3":{"draws":2,"losses":3,"wins":5},"mistralai/mistral-medium-3-5":{"draws":1,"losses":2,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":4,"wins":0},"moonshotai/kimi-k3":{"draws":0,"losses":5,"wins":5},"nex-agi/nex-n2-pro":{"draws":0,"losses":2,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":6,"wins":8},"o3":{"draws":4,"losses":6,"wins":0},"openai/gpt-oss-120b":{"draws":4,"losses":1,"wins":5},"poolside/laguna-s-2.1":{"draws":0,"losses":4,"wins":8},"qwen/qwen3.7-max":{"draws":2,"losses":7,"wins":3},"qwen/qwen3.7-plus":{"draws":0,"losses":3,"wins":5},"stepfun/step-3.7-flash":{"draws":1,"losses":7,"wins":0},"tencent/hy3-preview":{"draws":2,"losses":0,"wins":0},"thinkingmachines/inkling":{"draws":2,"losses":2,"wins":10},"x-ai/grok-4.5":{"draws":4,"losses":8,"wins":2},"x-ai/grok-build-0.1":{"draws":2,"losses":4,"wins":4},"xiaomi/mimo-v2.5":{"draws":5,"losses":4,"wins":15},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":5,"wins":3},"z-ai/glm-5.2":{"draws":5,"losses":9,"wins":8}},"gpt-5":{"claude-fable-5":{"draws":1,"losses":14,"wins":1},"claude-opus-4-5":{"draws":6,"losses":12,"wins":10},"claude-opus-4-8":{"draws":7,"losses":11,"wins":8},"claude-opus-5":{"draws":7,"losses":14,"wins":3},"claude-sonnet-5":{"draws":7,"losses":10,"wins":11},"cohere/north-mini-code":{"draws":4,"losses":1,"wins":13},"deepseek/deepseek-v4-flash":{"draws":3,"losses":3,"wins":4},"deepseek/deepseek-v4-pro":{"draws":0,"losses":5,"wins":1},"google/gemini-3.1-flash-lite":{"draws":6,"losses":0,"wins":10},"google/gemini-3.5-flash":{"draws":4,"losses":10,"wins":2},"google/gemini-3.5-flash-lite":{"draws":7,"losses":3,"wins":4},"google/gemini-3.6-flash":{"draws":0,"losses":9,"wins":5},"google/gemma-4-31b-it":{"draws":1,"losses":2,"wins":5},"gpt-4.1":{"draws":2,"losses":1,"wins":1},"gpt-5":{"draws":0,"losses":4,"wins":0},"gpt-5.4":{"draws":4,"losses":14,"wins":4},"gpt-5.4-mini":{"draws":20,"losses":15,"wins":19},"gpt-5.4-nano":{"draws":23,"losses":23,"wins":22},"gpt-5.5":{"draws":3,"losses":9,"wins":6},"gpt-5.6-luna":{"draws":8,"losses":10,"wins":4},"gpt-5.6-sol":{"draws":2,"losses":17,"wins":3},"gpt-5.6-terra":{"draws":6,"losses":10,"wins":4},"inclusionai/ling-3.0-flash":{"draws":3,"losses":5,"wins":4},"meituan/longcat-2.0":{"draws":6,"losses":1,"wins":13},"minimax/minimax-m3":{"draws":4,"losses":5,"wins":7},"mistralai/mistral-medium-3-5":{"draws":0,"losses":2,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":5,"wins":5},"moonshotai/kimi-k3":{"draws":5,"losses":3,"wins":4},"nex-agi/nex-n2-pro":{"draws":0,"losses":2,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":6,"wins":5},"o3":{"draws":3,"losses":4,"wins":5},"openai/gpt-oss-120b":{"draws":7,"losses":1,"wins":4},"poolside/laguna-s-2.1":{"draws":6,"losses":3,"wins":3},"qwen/qwen3.7-max":{"draws":6,"losses":3,"wins":5},"qwen/qwen3.7-plus":{"draws":2,"losses":4,"wins":4},"stepfun/step-3.7-flash":{"draws":4,"losses":0,"wins":6},"tencent/hy3-preview":{"draws":0,"losses":2,"wins":2},"thinkingmachines/inkling":{"draws":5,"losses":1,"wins":4},"x-ai/grok-4.5":{"draws":9,"losses":23,"wins":2},"x-ai/grok-build-0.1":{"draws":5,"losses":3,"wins":10},"xiaomi/mimo-v2.5":{"draws":16,"losses":14,"wins":12},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":2,"wins":5},"z-ai/glm-5.2":{"draws":10,"losses":17,"wins":19}},"gpt-5.4":{"claude-fable-5":{"draws":3,"losses":12,"wins":5},"claude-opus-4-5":{"draws":9,"losses":8,"wins":15},"claude-opus-4-8":{"draws":7,"losses":9,"wins":10},"claude-opus-5":{"draws":6,"losses":24,"wins":6},"claude-sonnet-5":{"draws":11,"losses":6,"wins":13},"cohere/north-mini-code":{"draws":5,"losses":4,"wins":9},"deepseek/deepseek-v4-flash":{"draws":7,"losses":6,"wins":7},"deepseek/deepseek-v4-pro":{"draws":1,"losses":1,"wins":2},"google/gemini-3.1-flash-lite":{"draws":3,"losses":0,"wins":9},"google/gemini-3.5-flash":{"draws":8,"losses":5,"wins":5},"google/gemini-3.5-flash-lite":{"draws":1,"losses":1,"wins":4},"google/gemini-3.6-flash":{"draws":6,"losses":10,"wins":6},"google/gemma-4-31b-it":{"draws":1,"losses":1,"wins":6},"gpt-4.1":{"draws":3,"losses":1,"wins":4},"gpt-5":{"draws":5,"losses":4,"wins":7},"gpt-5.4":{"draws":6,"losses":10,"wins":2},"gpt-5.4-mini":{"draws":16,"losses":11,"wins":31},"gpt-5.4-nano":{"draws":16,"losses":8,"wins":38},"gpt-5.5":{"draws":9,"losses":9,"wins":8},"gpt-5.6-luna":{"draws":14,"losses":6,"wins":4},"gpt-5.6-sol":{"draws":4,"losses":11,"wins":9},"gpt-5.6-terra":{"draws":11,"losses":7,"wins":12},"inclusionai/ling-3.0-flash":{"draws":4,"losses":2,"wins":6},"meituan/longcat-2.0":{"draws":5,"losses":7,"wins":6},"minimax/minimax-m3":{"draws":6,"losses":2,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":6,"wins":5},"moonshotai/kimi-k3":{"draws":7,"losses":5,"wins":6},"nex-agi/nex-n2-pro":{"draws":2,"losses":1,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":2,"wins":6},"o3":{"draws":3,"losses":3,"wins":6},"openai/gpt-oss-120b":{"draws":6,"losses":0,"wins":10},"poolside/laguna-s-2.1":{"draws":6,"losses":1,"wins":11},"qwen/qwen3.7-max":{"draws":5,"losses":5,"wins":8},"qwen/qwen3.7-plus":{"draws":4,"losses":0,"wins":8},"stepfun/step-3.7-flash":{"draws":3,"losses":3,"wins":2},"tencent/hy3-preview":{"draws":6,"losses":1,"wins":1},"thinkingmachines/inkling":{"draws":7,"losses":4,"wins":5},"x-ai/grok-4.5":{"draws":14,"losses":18,"wins":6},"x-ai/grok-build-0.1":{"draws":6,"losses":2,"wins":8},"xiaomi/mimo-v2.5":{"draws":15,"losses":3,"wins":18},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":3,"wins":9},"z-ai/glm-5.2":{"draws":27,"losses":18,"wins":19}},"gpt-5.4-mini":{"claude-fable-5":{"draws":11,"losses":35,"wins":4},"claude-opus-4-5":{"draws":31,"losses":42,"wins":23},"claude-opus-4-8":{"draws":27,"losses":31,"wins":18},"claude-opus-5":{"draws":12,"losses":61,"wins":13},"claude-sonnet-5":{"draws":29,"losses":24,"wins":23},"cohere/north-mini-code":{"draws":17,"losses":10,"wins":17},"deepseek/deepseek-v4-flash":{"draws":30,"losses":21,"wins":35},"deepseek/deepseek-v4-pro":{"draws":8,"losses":9,"wins":3},"google/gemini-3.1-flash-lite":{"draws":14,"losses":6,"wins":26},"google/gemini-3.5-flash":{"draws":16,"losses":27,"wins":9},"google/gemini-3.5-flash-lite":{"draws":22,"losses":7,"wins":25},"google/gemini-3.6-flash":{"draws":12,"losses":24,"wins":9},"google/gemma-4-31b-it":{"draws":10,"losses":11,"wins":17},"gpt-4.1":{"draws":13,"losses":4,"wins":11},"gpt-5":{"draws":16,"losses":16,"wins":20},"gpt-5.4":{"draws":23,"losses":39,"wins":10},"gpt-5.4-mini":{"draws":56,"losses":44,"wins":40},"gpt-5.4-nano":{"draws":53,"losses":50,"wins":94},"gpt-5.5":{"draws":26,"losses":23,"wins":9},"gpt-5.6-luna":{"draws":29,"losses":20,"wins":15},"gpt-5.6-sol":{"draws":20,"losses":34,"wins":8},"gpt-5.6-terra":{"draws":35,"losses":27,"wins":20},"inclusionai/ling-3.0-flash":{"draws":11,"losses":10,"wins":11},"meituan/longcat-2.0":{"draws":23,"losses":18,"wins":43},"minimax/minimax-m3":{"draws":25,"losses":13,"wins":28},"mistralai/mistral-medium-3-5":{"draws":4,"losses":7,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":11,"losses":25,"wins":8},"moonshotai/kimi-k3":{"draws":30,"losses":12,"wins":18},"nex-agi/nex-n2-pro":{"draws":9,"losses":3,"wins":26},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":27,"losses":9,"wins":14},"o3":{"draws":5,"losses":13,"wins":16},"openai/gpt-oss-120b":{"draws":17,"losses":11,"wins":16},"poolside/laguna-s-2.1":{"draws":26,"losses":16,"wins":28},"qwen/qwen3.7-max":{"draws":18,"losses":26,"wins":16},"qwen/qwen3.7-plus":{"draws":19,"losses":18,"wins":7},"stepfun/step-3.7-flash":{"draws":13,"losses":5,"wins":12},"tencent/hy3-preview":{"draws":7,"losses":4,"wins":5},"thinkingmachines/inkling":{"draws":17,"losses":18,"wins":19},"x-ai/grok-4.5":{"draws":25,"losses":66,"wins":17},"x-ai/grok-build-0.1":{"draws":14,"losses":15,"wins":19},"xiaomi/mimo-v2.5":{"draws":58,"losses":37,"wins":39},"xiaomi/mimo-v2.5-pro":{"draws":15,"losses":14,"wins":13},"z-ai/glm-5.2":{"draws":63,"losses":58,"wins":37}},"gpt-5.4-nano":{"claude-fable-5":{"draws":3,"losses":55,"wins":6},"claude-opus-4-5":{"draws":30,"losses":50,"wins":24},"claude-opus-4-8":{"draws":16,"losses":43,"wins":11},"claude-opus-5":{"draws":7,"losses":33,"wins":12},"claude-sonnet-5":{"draws":22,"losses":36,"wins":16},"cohere/north-mini-code":{"draws":17,"losses":18,"wins":25},"deepseek/deepseek-v4-flash":{"draws":22,"losses":39,"wins":9},"deepseek/deepseek-v4-pro":{"draws":5,"losses":1,"wins":8},"google/gemini-3.1-flash-lite":{"draws":10,"losses":20,"wins":40},"google/gemini-3.5-flash":{"draws":15,"losses":32,"wins":7},"google/gemini-3.5-flash-lite":{"draws":12,"losses":24,"wins":10},"google/gemini-3.6-flash":{"draws":11,"losses":20,"wins":5},"google/gemma-4-31b-it":{"draws":3,"losses":22,"wins":15},"gpt-4.1":{"draws":5,"losses":9,"wins":10},"gpt-5":{"draws":12,"losses":22,"wins":16},"gpt-5.4":{"draws":15,"losses":49,"wins":8},"gpt-5.4-mini":{"draws":47,"losses":99,"wins":61},"gpt-5.4-nano":{"draws":44,"losses":84,"wins":86},"gpt-5.5":{"draws":15,"losses":31,"wins":14},"gpt-5.6-luna":{"draws":24,"losses":41,"wins":25},"gpt-5.6-sol":{"draws":10,"losses":43,"wins":7},"gpt-5.6-terra":{"draws":18,"losses":30,"wins":12},"inclusionai/ling-3.0-flash":{"draws":20,"losses":12,"wins":10},"meituan/longcat-2.0":{"draws":17,"losses":26,"wins":41},"minimax/minimax-m3":{"draws":20,"losses":19,"wins":27},"mistralai/mistral-medium-3-5":{"draws":3,"losses":14,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":27,"wins":9},"moonshotai/kimi-k3":{"draws":12,"losses":20,"wins":6},"nex-agi/nex-n2-pro":{"draws":9,"losses":16,"wins":19},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":23,"wins":17},"o3":{"draws":8,"losses":25,"wins":9},"openai/gpt-oss-120b":{"draws":21,"losses":14,"wins":15},"poolside/laguna-s-2.1":{"draws":17,"losses":18,"wins":11},"qwen/qwen3.7-max":{"draws":23,"losses":26,"wins":11},"qwen/qwen3.7-plus":{"draws":19,"losses":42,"wins":11},"stepfun/step-3.7-flash":{"draws":15,"losses":7,"wins":16},"tencent/hy3-preview":{"draws":8,"losses":6,"wins":2},"thinkingmachines/inkling":{"draws":11,"losses":18,"wins":17},"x-ai/grok-4.5":{"draws":15,"losses":66,"wins":19},"x-ai/grok-build-0.1":{"draws":16,"losses":22,"wins":16},"xiaomi/mimo-v2.5":{"draws":56,"losses":52,"wins":52},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":25,"wins":14},"z-ai/glm-5.2":{"draws":42,"losses":51,"wins":42}},"gpt-5.5":{"claude-fable-5":{"draws":5,"losses":13,"wins":6},"claude-opus-4-5":{"draws":11,"losses":9,"wins":10},"claude-opus-4-8":{"draws":8,"losses":10,"wins":12},"claude-opus-5":{"draws":10,"losses":28,"wins":6},"claude-sonnet-5":{"draws":12,"losses":5,"wins":9},"cohere/north-mini-code":{"draws":6,"losses":1,"wins":7},"deepseek/deepseek-v4-flash":{"draws":7,"losses":0,"wins":13},"deepseek/deepseek-v4-pro":{"draws":1,"losses":2,"wins":3},"google/gemini-3.1-flash-lite":{"draws":7,"losses":3,"wins":10},"google/gemini-3.5-flash":{"draws":3,"losses":9,"wins":8},"google/gemini-3.5-flash-lite":{"draws":9,"losses":0,"wins":7},"google/gemini-3.6-flash":{"draws":7,"losses":7,"wins":4},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":6},"gpt-4.1":{"draws":3,"losses":2,"wins":3},"gpt-5":{"draws":3,"losses":6,"wins":7},"gpt-5.4":{"draws":8,"losses":15,"wins":7},"gpt-5.4-mini":{"draws":23,"losses":15,"wins":22},"gpt-5.4-nano":{"draws":19,"losses":22,"wins":27},"gpt-5.5":{"draws":5,"losses":7,"wins":8},"gpt-5.6-luna":{"draws":7,"losses":8,"wins":9},"gpt-5.6-sol":{"draws":10,"losses":9,"wins":11},"gpt-5.6-terra":{"draws":9,"losses":6,"wins":11},"inclusionai/ling-3.0-flash":{"draws":5,"losses":4,"wins":5},"meituan/longcat-2.0":{"draws":3,"losses":7,"wins":10},"minimax/minimax-m3":{"draws":6,"losses":2,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":2,"wins":4},"moonshotai/kimi-k3":{"draws":13,"losses":4,"wins":3},"nex-agi/nex-n2-pro":{"draws":0,"losses":1,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":2,"wins":11},"o3":{"draws":4,"losses":3,"wins":5},"openai/gpt-oss-120b":{"draws":9,"losses":2,"wins":5},"poolside/laguna-s-2.1":{"draws":4,"losses":7,"wins":7},"qwen/qwen3.7-max":{"draws":6,"losses":5,"wins":9},"qwen/qwen3.7-plus":{"draws":8,"losses":2,"wins":6},"stepfun/step-3.7-flash":{"draws":3,"losses":0,"wins":5},"tencent/hy3-preview":{"draws":7,"losses":0,"wins":5},"thinkingmachines/inkling":{"draws":4,"losses":5,"wins":5},"x-ai/grok-4.5":{"draws":16,"losses":18,"wins":16},"x-ai/grok-build-0.1":{"draws":9,"losses":5,"wins":4},"xiaomi/mimo-v2.5":{"draws":15,"losses":4,"wins":17},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":4,"wins":7},"z-ai/glm-5.2":{"draws":15,"losses":13,"wins":10}},"gpt-5.6-luna":{"claude-fable-5":{"draws":2,"losses":14,"wins":2},"claude-opus-4-5":{"draws":13,"losses":11,"wins":12},"claude-opus-4-8":{"draws":7,"losses":7,"wins":4},"claude-opus-5":{"draws":2,"losses":18,"wins":4},"claude-sonnet-5":{"draws":13,"losses":7,"wins":10},"cohere/north-mini-code":{"draws":3,"losses":5,"wins":4},"deepseek/deepseek-v4-flash":{"draws":13,"losses":3,"wins":4},"deepseek/deepseek-v4-pro":{"draws":4,"losses":2,"wins":0},"google/gemini-3.1-flash-lite":{"draws":2,"losses":2,"wins":8},"google/gemini-3.5-flash":{"draws":10,"losses":7,"wins":3},"google/gemini-3.5-flash-lite":{"draws":7,"losses":1,"wins":4},"google/gemini-3.6-flash":{"draws":4,"losses":11,"wins":3},"google/gemma-4-31b-it":{"draws":4,"losses":1,"wins":7},"gpt-4.1":{"draws":4,"losses":1,"wins":5},"gpt-5":{"draws":7,"losses":5,"wins":8},"gpt-5.4":{"draws":15,"losses":12,"wins":3},"gpt-5.4-mini":{"draws":28,"losses":12,"wins":16},"gpt-5.4-nano":{"draws":20,"losses":13,"wins":35},"gpt-5.5":{"draws":7,"losses":13,"wins":4},"gpt-5.6-luna":{"draws":6,"losses":4,"wins":8},"gpt-5.6-sol":{"draws":7,"losses":15,"wins":6},"gpt-5.6-terra":{"draws":11,"losses":6,"wins":7},"inclusionai/ling-3.0-flash":{"draws":8,"losses":2,"wins":2},"meituan/longcat-2.0":{"draws":14,"losses":3,"wins":9},"minimax/minimax-m3":{"draws":6,"losses":2,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":8,"wins":2},"moonshotai/kimi-k3":{"draws":6,"losses":2,"wins":10},"nex-agi/nex-n2-pro":{"draws":6,"losses":1,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":2,"wins":6},"o3":{"draws":4,"losses":2,"wins":6},"openai/gpt-oss-120b":{"draws":8,"losses":4,"wins":8},"poolside/laguna-s-2.1":{"draws":14,"losses":8,"wins":4},"qwen/qwen3.7-max":{"draws":13,"losses":1,"wins":10},"qwen/qwen3.7-plus":{"draws":4,"losses":3,"wins":7},"stepfun/step-3.7-flash":{"draws":3,"losses":1,"wins":6},"tencent/hy3-preview":{"draws":3,"losses":4,"wins":1},"thinkingmachines/inkling":{"draws":4,"losses":2,"wins":2},"x-ai/grok-4.5":{"draws":9,"losses":23,"wins":6},"x-ai/grok-build-0.1":{"draws":9,"losses":0,"wins":11},"xiaomi/mimo-v2.5":{"draws":20,"losses":6,"wins":18},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":4,"wins":5},"z-ai/glm-5.2":{"draws":26,"losses":20,"wins":8}},"gpt-5.6-sol":{"claude-fable-5":{"draws":3,"losses":19,"wins":6},"claude-opus-4-5":{"draws":8,"losses":2,"wins":18},"claude-opus-4-8":{"draws":3,"losses":8,"wins":17},"claude-opus-5":{"draws":8,"losses":36,"wins":10},"claude-sonnet-5":{"draws":6,"losses":4,"wins":16},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":10},"deepseek/deepseek-v4-flash":{"draws":1,"losses":0,"wins":7},"deepseek/deepseek-v4-pro":{"draws":0,"losses":2,"wins":0},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":10},"google/gemini-3.5-flash":{"draws":5,"losses":7,"wins":8},"google/gemini-3.5-flash-lite":{"draws":4,"losses":0,"wins":0},"google/gemini-3.6-flash":{"draws":5,"losses":8,"wins":7},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":8},"gpt-4.1":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":6,"losses":3,"wins":11},"gpt-5.4":{"draws":3,"losses":21,"wins":8},"gpt-5.4-mini":{"draws":16,"losses":7,"wins":31},"gpt-5.4-nano":{"draws":13,"losses":10,"wins":45},"gpt-5.5":{"draws":6,"losses":13,"wins":9},"gpt-5.6-luna":{"draws":5,"losses":7,"wins":12},"gpt-5.6-sol":{"draws":2,"losses":6,"wins":8},"gpt-5.6-terra":{"draws":4,"losses":5,"wins":17},"inclusionai/ling-3.0-flash":{"draws":3,"losses":0,"wins":3},"meituan/longcat-2.0":{"draws":2,"losses":2,"wins":2},"minimax/minimax-m3":{"draws":6,"losses":0,"wins":10},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":3,"wins":7},"moonshotai/kimi-k3":{"draws":6,"losses":2,"wins":10},"nex-agi/nex-n2-pro":{"draws":0,"losses":1,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":0,"wins":17},"o3":{"draws":2,"losses":2,"wins":8},"openai/gpt-oss-120b":{"draws":7,"losses":0,"wins":11},"poolside/laguna-s-2.1":{"draws":0,"losses":1,"wins":5},"qwen/qwen3.7-max":{"draws":3,"losses":2,"wins":11},"qwen/qwen3.7-plus":{"draws":6,"losses":3,"wins":5},"stepfun/step-3.7-flash":{"draws":3,"losses":0,"wins":7},"tencent/hy3-preview":{"draws":1,"losses":3,"wins":4},"thinkingmachines/inkling":{"draws":4,"losses":1,"wins":7},"x-ai/grok-4.5":{"draws":8,"losses":24,"wins":20},"x-ai/grok-build-0.1":{"draws":4,"losses":2,"wins":10},"xiaomi/mimo-v2.5":{"draws":11,"losses":1,"wins":22},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":1,"wins":9},"z-ai/glm-5.2":{"draws":11,"losses":12,"wins":23}},"gpt-5.6-terra":{"claude-fable-5":{"draws":2,"losses":11,"wins":1},"claude-opus-4-5":{"draws":17,"losses":10,"wins":13},"claude-opus-4-8":{"draws":9,"losses":4,"wins":7},"claude-opus-5":{"draws":11,"losses":32,"wins":3},"claude-sonnet-5":{"draws":8,"losses":8,"wins":8},"cohere/north-mini-code":{"draws":5,"losses":2,"wins":11},"deepseek/deepseek-v4-flash":{"draws":5,"losses":3,"wins":14},"deepseek/deepseek-v4-pro":{"draws":2,"losses":2,"wins":2},"google/gemini-3.1-flash-lite":{"draws":5,"losses":1,"wins":8},"google/gemini-3.5-flash":{"draws":6,"losses":11,"wins":1},"google/gemini-3.5-flash-lite":{"draws":11,"losses":0,"wins":7},"google/gemini-3.6-flash":{"draws":6,"losses":12,"wins":4},"google/gemma-4-31b-it":{"draws":1,"losses":2,"wins":9},"gpt-4.1":{"draws":2,"losses":4,"wins":0},"gpt-5":{"draws":5,"losses":6,"wins":7},"gpt-5.4":{"draws":10,"losses":11,"wins":3},"gpt-5.4-mini":{"draws":33,"losses":11,"wins":24},"gpt-5.4-nano":{"draws":21,"losses":21,"wins":30},"gpt-5.5":{"draws":11,"losses":8,"wins":3},"gpt-5.6-luna":{"draws":9,"losses":8,"wins":5},"gpt-5.6-sol":{"draws":4,"losses":15,"wins":5},"gpt-5.6-terra":{"draws":2,"losses":1,"wins":3},"inclusionai/ling-3.0-flash":{"draws":2,"losses":2,"wins":4},"meituan/longcat-2.0":{"draws":6,"losses":8,"wins":14},"minimax/minimax-m3":{"draws":7,"losses":3,"wins":10},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":5,"wins":5},"moonshotai/kimi-k3":{"draws":13,"losses":6,"wins":9},"nex-agi/nex-n2-pro":{"draws":3,"losses":2,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":3,"wins":8},"o3":{"draws":4,"losses":5,"wins":3},"openai/gpt-oss-120b":{"draws":6,"losses":0,"wins":8},"poolside/laguna-s-2.1":{"draws":13,"losses":7,"wins":6},"qwen/qwen3.7-max":{"draws":6,"losses":3,"wins":5},"qwen/qwen3.7-plus":{"draws":11,"losses":9,"wins":4},"stepfun/step-3.7-flash":{"draws":4,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":2,"losses":2,"wins":0},"thinkingmachines/inkling":{"draws":8,"losses":6,"wins":2},"x-ai/grok-4.5":{"draws":13,"losses":24,"wins":3},"x-ai/grok-build-0.1":{"draws":11,"losses":0,"wins":7},"xiaomi/mimo-v2.5":{"draws":19,"losses":5,"wins":20},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":2,"wins":6},"z-ai/glm-5.2":{"draws":18,"losses":14,"wins":12}},"inclusionai/ling-3.0-flash":{"claude-opus-4-5":{"draws":4,"losses":7,"wins":5},"claude-opus-4-8":{"draws":4,"losses":0,"wins":0},"claude-opus-5":{"draws":4,"losses":5,"wins":1},"claude-sonnet-5":{"draws":1,"losses":7,"wins":2},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":4},"deepseek/deepseek-v4-flash":{"draws":0,"losses":0,"wins":2},"google/gemini-3.1-flash-lite":{"draws":1,"losses":2,"wins":1},"google/gemini-3.5-flash":{"draws":0,"losses":2,"wins":2},"google/gemini-3.5-flash-lite":{"draws":17,"losses":24,"wins":11},"google/gemini-3.6-flash":{"draws":20,"losses":26,"wins":10},"google/gemma-4-31b-it":{"draws":0,"losses":2,"wins":2},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":2,"losses":4,"wins":0},"gpt-5.4":{"draws":1,"losses":4,"wins":1},"gpt-5.4-mini":{"draws":2,"losses":9,"wins":7},"gpt-5.4-nano":{"draws":9,"losses":10,"wins":3},"gpt-5.5":{"draws":1,"losses":1,"wins":2},"gpt-5.6-luna":{"draws":4,"losses":2,"wins":2},"gpt-5.6-sol":{"draws":2,"losses":2,"wins":0},"gpt-5.6-terra":{"draws":0,"losses":4,"wins":2},"inclusionai/ling-3.0-flash":{"draws":4,"losses":5,"wins":7},"meituan/longcat-2.0":{"draws":7,"losses":15,"wins":14},"minimax/minimax-m3":{"draws":5,"losses":3,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":6,"wins":2},"moonshotai/kimi-k3":{"draws":5,"losses":16,"wins":11},"nex-agi/nex-n2-pro":{"draws":0,"losses":1,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":0,"wins":0},"o3":{"draws":2,"losses":22,"wins":6},"openai/gpt-oss-120b":{"draws":6,"losses":7,"wins":5},"poolside/laguna-s-2.1":{"draws":8,"losses":10,"wins":4},"qwen/qwen3.7-max":{"draws":4,"losses":4,"wins":0},"qwen/qwen3.7-plus":{"draws":0,"losses":2,"wins":2},"stepfun/step-3.7-flash":{"draws":0,"losses":4,"wins":4},"thinkingmachines/inkling":{"draws":10,"losses":9,"wins":11},"x-ai/grok-4.5":{"draws":14,"losses":27,"wins":3},"x-ai/grok-build-0.1":{"draws":2,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":2,"losses":5,"wins":1},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":2,"wins":2}},"meituan/longcat-2.0":{"claude-fable-5":{"draws":0,"losses":3,"wins":1},"claude-opus-4-5":{"draws":12,"losses":18,"wins":9},"claude-opus-4-8":{"draws":4,"losses":4,"wins":2},"claude-opus-5":{"draws":3,"losses":17,"wins":4},"claude-sonnet-5":{"draws":0,"losses":10,"wins":2},"cohere/north-mini-code":{"draws":4,"losses":5,"wins":7},"google/gemini-3.1-flash-lite":{"draws":1,"losses":4,"wins":7},"google/gemini-3.5-flash":{"draws":2,"losses":0,"wins":2},"google/gemini-3.5-flash-lite":{"draws":18,"losses":27,"wins":38},"google/gemini-3.6-flash":{"draws":19,"losses":34,"wins":11},"google/gemma-4-31b-it":{"draws":0,"losses":5,"wins":5},"gpt-5":{"draws":1,"losses":7,"wins":0},"gpt-5.4":{"draws":2,"losses":3,"wins":5},"gpt-5.4-mini":{"draws":12,"losses":19,"wins":7},"gpt-5.4-nano":{"draws":5,"losses":21,"wins":12},"gpt-5.5":{"draws":3,"losses":8,"wins":3},"gpt-5.6-luna":{"draws":6,"losses":5,"wins":3},"gpt-5.6-sol":{"draws":2,"losses":2,"wins":2},"gpt-5.6-terra":{"draws":2,"losses":7,"wins":5},"inclusionai/ling-3.0-flash":{"draws":9,"losses":8,"wins":13},"meituan/longcat-2.0":{"draws":8,"losses":8,"wins":6},"minimax/minimax-m3":{"draws":1,"losses":7,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":3,"wins":1},"moonshotai/kimi-k3":{"draws":21,"losses":44,"wins":11},"nex-agi/nex-n2-pro":{"draws":1,"losses":5,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":1,"losses":4,"wins":3},"o3":{"draws":5,"losses":41,"wins":12},"openai/gpt-oss-120b":{"draws":7,"losses":7,"wins":14},"poolside/laguna-s-2.1":{"draws":13,"losses":7,"wins":14},"qwen/qwen3.7-max":{"draws":1,"losses":12,"wins":1},"qwen/qwen3.7-plus":{"draws":4,"losses":5,"wins":1},"stepfun/step-3.7-flash":{"draws":2,"losses":11,"wins":7},"thinkingmachines/inkling":{"draws":8,"losses":16,"wins":16},"x-ai/grok-4.5":{"draws":18,"losses":56,"wins":16},"x-ai/grok-build-0.1":{"draws":5,"losses":8,"wins":3},"xiaomi/mimo-v2.5":{"draws":5,"losses":5,"wins":6},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":2,"wins":7},"z-ai/glm-5.2":{"draws":0,"losses":1,"wins":1}},"minimax/minimax-m3":{"claude-fable-5":{"draws":2,"losses":14,"wins":0},"claude-opus-4-5":{"draws":5,"losses":13,"wins":2},"claude-opus-4-8":{"draws":10,"losses":8,"wins":2},"claude-opus-5":{"draws":0,"losses":4,"wins":0},"claude-sonnet-5":{"draws":9,"losses":10,"wins":5},"cohere/north-mini-code":{"draws":3,"losses":4,"wins":7},"deepseek/deepseek-v4-flash":{"draws":10,"losses":11,"wins":11},"deepseek/deepseek-v4-pro":{"draws":0,"losses":1,"wins":1},"google/gemini-3.1-flash-lite":{"draws":3,"losses":13,"wins":6},"google/gemini-3.5-flash":{"draws":3,"losses":12,"wins":1},"google/gemini-3.5-flash-lite":{"draws":6,"losses":9,"wins":3},"google/gemini-3.6-flash":{"draws":5,"losses":5,"wins":2},"google/gemma-4-31b-it":{"draws":6,"losses":6,"wins":4},"gpt-4.1":{"draws":4,"losses":3,"wins":1},"gpt-5":{"draws":5,"losses":9,"wins":2},"gpt-5.4":{"draws":6,"losses":10,"wins":0},"gpt-5.4-mini":{"draws":23,"losses":31,"wins":12},"gpt-5.4-nano":{"draws":31,"losses":39,"wins":26},"gpt-5.5":{"draws":5,"losses":12,"wins":3},"gpt-5.6-luna":{"draws":10,"losses":11,"wins":3},"gpt-5.6-sol":{"draws":8,"losses":12,"wins":0},"gpt-5.6-terra":{"draws":7,"losses":9,"wins":4},"inclusionai/ling-3.0-flash":{"draws":13,"losses":5,"wins":8},"meituan/longcat-2.0":{"draws":3,"losses":12,"wins":9},"mistralai/mistral-medium-3-5":{"draws":0,"losses":4,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":8,"wins":1},"moonshotai/kimi-k3":{"draws":4,"losses":4,"wins":4},"nex-agi/nex-n2-pro":{"draws":3,"losses":3,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":7,"wins":3},"o3":{"draws":4,"losses":7,"wins":1},"openai/gpt-oss-120b":{"draws":6,"losses":4,"wins":4},"poolside/laguna-s-2.1":{"draws":9,"losses":9,"wins":4},"qwen/qwen3.7-max":{"draws":7,"losses":7,"wins":6},"qwen/qwen3.7-plus":{"draws":3,"losses":8,"wins":7},"stepfun/step-3.7-flash":{"draws":5,"losses":2,"wins":3},"tencent/hy3-preview":{"draws":6,"losses":4,"wins":0},"thinkingmachines/inkling":{"draws":2,"losses":8,"wins":4},"x-ai/grok-4.5":{"draws":3,"losses":19,"wins":0},"x-ai/grok-build-0.1":{"draws":7,"losses":7,"wins":2},"xiaomi/mimo-v2.5":{"draws":20,"losses":17,"wins":13},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":9,"wins":2},"z-ai/glm-5.2":{"draws":14,"losses":11,"wins":3}},"moonshotai/kimi-k2.7-code":{"claude-fable-5":{"draws":0,"losses":16,"wins":2},"claude-opus-4-5":{"draws":10,"losses":13,"wins":11},"claude-opus-4-8":{"draws":4,"losses":8,"wins":4},"claude-opus-5":{"draws":6,"losses":29,"wins":1},"claude-sonnet-5":{"draws":6,"losses":8,"wins":6},"cohere/north-mini-code":{"draws":3,"losses":4,"wins":3},"deepseek/deepseek-v4-flash":{"draws":5,"losses":4,"wins":7},"deepseek/deepseek-v4-pro":{"draws":4,"losses":3,"wins":1},"google/gemini-3.1-flash-lite":{"draws":6,"losses":0,"wins":8},"google/gemini-3.5-flash":{"draws":4,"losses":4,"wins":6},"google/gemini-3.5-flash-lite":{"draws":4,"losses":4,"wins":0},"google/gemini-3.6-flash":{"draws":5,"losses":9,"wins":2},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":10},"gpt-4.1":{"draws":4,"losses":1,"wins":1},"gpt-5":{"draws":4,"losses":9,"wins":5},"gpt-5.4":{"draws":8,"losses":6,"wins":6},"gpt-5.4-mini":{"draws":17,"losses":10,"wins":29},"gpt-5.4-nano":{"draws":13,"losses":14,"wins":29},"gpt-5.5":{"draws":9,"losses":5,"wins":6},"gpt-5.6-luna":{"draws":5,"losses":5,"wins":10},"gpt-5.6-sol":{"draws":2,"losses":11,"wins":3},"gpt-5.6-terra":{"draws":8,"losses":9,"wins":7},"inclusionai/ling-3.0-flash":{"draws":2,"losses":3,"wins":7},"meituan/longcat-2.0":{"draws":6,"losses":2,"wins":6},"minimax/minimax-m3":{"draws":5,"losses":1,"wins":10},"moonshotai/kimi-k3":{"draws":2,"losses":4,"wins":12},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":2,"wins":8},"o3":{"draws":1,"losses":4,"wins":7},"openai/gpt-oss-120b":{"draws":4,"losses":0,"wins":6},"poolside/laguna-s-2.1":{"draws":8,"losses":9,"wins":1},"qwen/qwen3.7-max":{"draws":4,"losses":4,"wins":4},"qwen/qwen3.7-plus":{"draws":8,"losses":2,"wins":6},"stepfun/step-3.7-flash":{"draws":6,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":2,"losses":2,"wins":2},"thinkingmachines/inkling":{"draws":2,"losses":5,"wins":7},"x-ai/grok-4.5":{"draws":5,"losses":26,"wins":1},"x-ai/grok-build-0.1":{"draws":3,"losses":1,"wins":8},"xiaomi/mimo-v2.5":{"draws":14,"losses":6,"wins":22},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":0,"wins":6},"z-ai/glm-5.2":{"draws":6,"losses":19,"wins":13}},"moonshotai/kimi-k3":{"claude-fable-5":{"draws":0,"losses":10,"wins":0},"claude-opus-4-5":{"draws":10,"losses":20,"wins":12},"claude-opus-4-8":{"draws":7,"losses":4,"wins":7},"claude-opus-5":{"draws":5,"losses":35,"wins":4},"claude-sonnet-5":{"draws":9,"losses":10,"wins":9},"cohere/north-mini-code":{"draws":4,"losses":7,"wins":3},"google/gemini-3.1-flash-lite":{"draws":4,"losses":1,"wins":5},"google/gemini-3.5-flash":{"draws":12,"losses":7,"wins":5},"google/gemini-3.5-flash-lite":{"draws":39,"losses":23,"wins":52},"google/gemini-3.6-flash":{"draws":27,"losses":49,"wins":26},"google/gemma-4-31b-it":{"draws":0,"losses":5,"wins":5},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":5,"losses":4,"wins":3},"gpt-5.4":{"draws":7,"losses":6,"wins":5},"gpt-5.4-mini":{"draws":30,"losses":18,"wins":12},"gpt-5.4-nano":{"draws":12,"losses":6,"wins":20},"gpt-5.5":{"draws":13,"losses":3,"wins":4},"gpt-5.6-luna":{"draws":6,"losses":10,"wins":2},"gpt-5.6-sol":{"draws":6,"losses":10,"wins":2},"gpt-5.6-terra":{"draws":13,"losses":9,"wins":6},"inclusionai/ling-3.0-flash":{"draws":4,"losses":9,"wins":9},"meituan/longcat-2.0":{"draws":11,"losses":4,"wins":23},"minimax/minimax-m3":{"draws":4,"losses":4,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":12,"wins":4},"moonshotai/kimi-k3":{"draws":52,"losses":52,"wins":26},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":7,"wins":4},"o3":{"draws":13,"losses":29,"wins":28},"openai/gpt-oss-120b":{"draws":10,"losses":1,"wins":13},"poolside/laguna-s-2.1":{"draws":18,"losses":1,"wins":17},"qwen/qwen3.7-max":{"draws":6,"losses":1,"wins":9},"qwen/qwen3.7-plus":{"draws":8,"losses":6,"wins":8},"stepfun/step-3.7-flash":{"draws":8,"losses":4,"wins":10},"thinkingmachines/inkling":{"draws":16,"losses":6,"wins":20},"x-ai/grok-4.5":{"draws":48,"losses":49,"wins":32},"x-ai/grok-build-0.1":{"draws":7,"losses":3,"wins":12},"xiaomi/mimo-v2.5":{"draws":8,"losses":3,"wins":5},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":9,"wins":3},"z-ai/glm-5.2":{"draws":1,"losses":1,"wins":2}},"nex-agi/nex-n2-pro":{"claude-fable-5":{"draws":0,"losses":10,"wins":0},"claude-opus-4-5":{"draws":2,"losses":11,"wins":1},"claude-opus-4-8":{"draws":3,"losses":9,"wins":0},"claude-opus-5":{"draws":0,"losses":2,"wins":0},"claude-sonnet-5":{"draws":2,"losses":15,"wins":1},"cohere/north-mini-code":{"draws":6,"losses":7,"wins":5},"deepseek/deepseek-v4-flash":{"draws":2,"losses":13,"wins":17},"deepseek/deepseek-v4-pro":{"draws":0,"losses":1,"wins":3},"google/gemini-3.1-flash-lite":{"draws":0,"losses":8,"wins":12},"google/gemini-3.5-flash":{"draws":4,"losses":6,"wins":2},"google/gemini-3.5-flash-lite":{"draws":1,"losses":6,"wins":5},"google/gemini-3.6-flash":{"draws":0,"losses":3,"wins":1},"google/gemma-4-31b-it":{"draws":0,"losses":7,"wins":5},"gpt-4.1":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":0,"losses":10,"wins":2},"gpt-5.4":{"draws":0,"losses":12,"wins":2},"gpt-5.4-mini":{"draws":9,"losses":31,"wins":12},"gpt-5.4-nano":{"draws":5,"losses":23,"wins":24},"gpt-5.5":{"draws":0,"losses":11,"wins":1},"gpt-5.6-luna":{"draws":5,"losses":11,"wins":8},"gpt-5.6-sol":{"draws":0,"losses":12,"wins":0},"gpt-5.6-terra":{"draws":1,"losses":7,"wins":2},"inclusionai/ling-3.0-flash":{"draws":2,"losses":5,"wins":5},"meituan/longcat-2.0":{"draws":2,"losses":14,"wins":10},"minimax/minimax-m3":{"draws":0,"losses":9,"wins":3},"mistralai/mistral-medium-3-5":{"draws":0,"losses":2,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":6,"wins":0},"moonshotai/kimi-k3":{"draws":0,"losses":8,"wins":0},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":12,"wins":4},"o3":{"draws":0,"losses":8,"wins":0},"openai/gpt-oss-120b":{"draws":2,"losses":5,"wins":1},"poolside/laguna-s-2.1":{"draws":3,"losses":4,"wins":1},"qwen/qwen3.7-max":{"draws":1,"losses":8,"wins":1},"qwen/qwen3.7-plus":{"draws":2,"losses":6,"wins":4},"stepfun/step-3.7-flash":{"draws":1,"losses":3,"wins":2},"tencent/hy3-preview":{"draws":0,"losses":1,"wins":1},"thinkingmachines/inkling":{"draws":0,"losses":2,"wins":4},"x-ai/grok-4.5":{"draws":5,"losses":13,"wins":2},"x-ai/grok-build-0.1":{"draws":3,"losses":7,"wins":2},"xiaomi/mimo-v2.5":{"draws":0,"losses":16,"wins":8},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":8,"wins":2},"z-ai/glm-5.2":{"draws":6,"losses":8,"wins":2}},"nvidia/nemotron-3-ultra-550b-a55b":{"claude-fable-5":{"draws":1,"losses":9,"wins":0},"claude-opus-4-5":{"draws":8,"losses":4,"wins":8},"claude-opus-4-8":{"draws":4,"losses":8,"wins":0},"claude-opus-5":{"draws":2,"losses":12,"wins":0},"claude-sonnet-5":{"draws":8,"losses":2,"wins":8},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":6},"deepseek/deepseek-v4-flash":{"draws":10,"losses":1,"wins":1},"deepseek/deepseek-v4-pro":{"draws":2,"losses":0,"wins":2},"google/gemini-3.1-flash-lite":{"draws":3,"losses":2,"wins":7},"google/gemini-3.5-flash":{"draws":6,"losses":8,"wins":0},"google/gemini-3.5-flash-lite":{"draws":4,"losses":2,"wins":2},"google/gemini-3.6-flash":{"draws":3,"losses":7,"wins":0},"google/gemma-4-31b-it":{"draws":0,"losses":6,"wins":2},"gpt-4.1":{"draws":0,"losses":3,"wins":1},"gpt-5":{"draws":2,"losses":4,"wins":4},"gpt-5.4":{"draws":5,"losses":7,"wins":0},"gpt-5.4-mini":{"draws":16,"losses":13,"wins":9},"gpt-5.4-nano":{"draws":21,"losses":12,"wins":17},"gpt-5.5":{"draws":3,"losses":6,"wins":3},"gpt-5.6-luna":{"draws":10,"losses":7,"wins":1},"gpt-5.6-sol":{"draws":1,"losses":11,"wins":2},"gpt-5.6-terra":{"draws":6,"losses":3,"wins":1},"inclusionai/ling-3.0-flash":{"draws":3,"losses":2,"wins":1},"meituan/longcat-2.0":{"draws":5,"losses":4,"wins":7},"minimax/minimax-m3":{"draws":6,"losses":2,"wins":4},"mistralai/mistral-medium-3-5":{"draws":2,"losses":2,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":5,"wins":1},"moonshotai/kimi-k3":{"draws":3,"losses":4,"wins":7},"nex-agi/nex-n2-pro":{"draws":4,"losses":2,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":2,"wins":2},"o3":{"draws":3,"losses":5,"wins":0},"openai/gpt-oss-120b":{"draws":8,"losses":1,"wins":5},"poolside/laguna-s-2.1":{"draws":7,"losses":2,"wins":1},"qwen/qwen3.7-max":{"draws":4,"losses":4,"wins":4},"qwen/qwen3.7-plus":{"draws":4,"losses":4,"wins":4},"stepfun/step-3.7-flash":{"draws":1,"losses":1,"wins":2},"tencent/hy3-preview":{"draws":4,"losses":0,"wins":0},"thinkingmachines/inkling":{"draws":2,"losses":3,"wins":1},"x-ai/grok-4.5":{"draws":3,"losses":14,"wins":5},"x-ai/grok-build-0.1":{"draws":8,"losses":2,"wins":6},"xiaomi/mimo-v2.5":{"draws":16,"losses":5,"wins":11},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":6,"wins":1},"z-ai/glm-5.2":{"draws":13,"losses":8,"wins":5}},"o3":{"claude-fable-5":{"draws":1,"losses":15,"wins":0},"claude-opus-4-5":{"draws":7,"losses":16,"wins":9},"claude-opus-4-8":{"draws":4,"losses":7,"wins":3},"claude-opus-5":{"draws":2,"losses":19,"wins":3},"claude-sonnet-5":{"draws":4,"losses":11,"wins":7},"cohere/north-mini-code":{"draws":6,"losses":2,"wins":6},"deepseek/deepseek-v4-flash":{"draws":4,"losses":5,"wins":9},"deepseek/deepseek-v4-pro":{"draws":2,"losses":2,"wins":0},"google/gemini-3.1-flash-lite":{"draws":6,"losses":0,"wins":8},"google/gemini-3.5-flash":{"draws":3,"losses":6,"wins":7},"google/gemini-3.5-flash-lite":{"draws":2,"losses":1,"wins":15},"google/gemini-3.6-flash":{"draws":4,"losses":10,"wins":4},"google/gemma-4-31b-it":{"draws":5,"losses":0,"wins":7},"gpt-4.1":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":3,"losses":7,"wins":4},"gpt-5.4":{"draws":4,"losses":9,"wins":3},"gpt-5.4-mini":{"draws":8,"losses":19,"wins":23},"gpt-5.4-nano":{"draws":12,"losses":15,"wins":33},"gpt-5.5":{"draws":7,"losses":10,"wins":3},"gpt-5.6-luna":{"draws":4,"losses":7,"wins":3},"gpt-5.6-sol":{"draws":3,"losses":13,"wins":2},"gpt-5.6-terra":{"draws":5,"losses":6,"wins":5},"inclusionai/ling-3.0-flash":{"draws":0,"losses":1,"wins":11},"meituan/longcat-2.0":{"draws":5,"losses":6,"wins":13},"minimax/minimax-m3":{"draws":5,"losses":1,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":7,"wins":4},"moonshotai/kimi-k3":{"draws":6,"losses":9,"wins":3},"nex-agi/nex-n2-pro":{"draws":0,"losses":2,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":3,"wins":5},"openai/gpt-oss-120b":{"draws":4,"losses":1,"wins":5},"poolside/laguna-s-2.1":{"draws":4,"losses":1,"wins":15},"qwen/qwen3.7-max":{"draws":8,"losses":5,"wins":5},"qwen/qwen3.7-plus":{"draws":2,"losses":4,"wins":4},"stepfun/step-3.7-flash":{"draws":2,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":5,"losses":1,"wins":2},"thinkingmachines/inkling":{"draws":4,"losses":5,"wins":3},"x-ai/grok-4.5":{"draws":7,"losses":22,"wins":5},"x-ai/grok-build-0.1":{"draws":3,"losses":0,"wins":9},"xiaomi/mimo-v2.5":{"draws":11,"losses":1,"wins":24},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":4,"wins":5},"z-ai/glm-5.2":{"draws":16,"losses":26,"wins":10}},"openai/gpt-oss-120b":{"claude-fable-5":{"draws":3,"losses":9,"wins":0},"claude-opus-4-5":{"draws":13,"losses":14,"wins":3},"claude-opus-4-8":{"draws":7,"losses":6,"wins":3},"claude-opus-5":{"draws":0,"losses":6,"wins":0},"claude-sonnet-5":{"draws":7,"losses":9,"wins":4},"cohere/north-mini-code":{"draws":10,"losses":3,"wins":1},"deepseek/deepseek-v4-flash":{"draws":10,"losses":5,"wins":17},"deepseek/deepseek-v4-pro":{"draws":0,"losses":0,"wins":2},"google/gemini-3.1-flash-lite":{"draws":6,"losses":4,"wins":8},"google/gemini-3.5-flash":{"draws":9,"losses":7,"wins":0},"google/gemini-3.5-flash-lite":{"draws":9,"losses":4,"wins":7},"google/gemini-3.6-flash":{"draws":9,"losses":3,"wins":0},"google/gemma-4-31b-it":{"draws":6,"losses":6,"wins":2},"gpt-4.1":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":7,"losses":4,"wins":1},"gpt-5.4":{"draws":6,"losses":10,"wins":0},"gpt-5.4-mini":{"draws":25,"losses":24,"wins":11},"gpt-5.4-nano":{"draws":28,"losses":17,"wins":15},"gpt-5.5":{"draws":10,"losses":8,"wins":0},"gpt-5.6-luna":{"draws":10,"losses":7,"wins":5},"gpt-5.6-sol":{"draws":7,"losses":11,"wins":0},"gpt-5.6-terra":{"draws":6,"losses":10,"wins":0},"inclusionai/ling-3.0-flash":{"draws":16,"losses":2,"wins":8},"meituan/longcat-2.0":{"draws":15,"losses":6,"wins":9},"minimax/minimax-m3":{"draws":5,"losses":4,"wins":5},"mistralai/mistral-medium-3-5":{"draws":3,"losses":1,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":6,"wins":0},"moonshotai/kimi-k3":{"draws":7,"losses":5,"wins":0},"nex-agi/nex-n2-pro":{"draws":6,"losses":1,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":7,"wins":6},"o3":{"draws":4,"losses":5,"wins":1},"openai/gpt-oss-120b":{"draws":5,"losses":1,"wins":0},"poolside/laguna-s-2.1":{"draws":14,"losses":4,"wins":8},"qwen/qwen3.7-max":{"draws":13,"losses":5,"wins":2},"qwen/qwen3.7-plus":{"draws":6,"losses":7,"wins":4},"stepfun/step-3.7-flash":{"draws":5,"losses":5,"wins":0},"tencent/hy3-preview":{"draws":3,"losses":1,"wins":0},"thinkingmachines/inkling":{"draws":7,"losses":1,"wins":10},"x-ai/grok-4.5":{"draws":7,"losses":18,"wins":3},"x-ai/grok-build-0.1":{"draws":7,"losses":11,"wins":2},"xiaomi/mimo-v2.5":{"draws":20,"losses":12,"wins":12},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":4,"wins":0},"z-ai/glm-5.2":{"draws":28,"losses":7,"wins":13}},"poolside/laguna-s-2.1":{"claude-opus-4-5":{"draws":15,"losses":14,"wins":1},"claude-opus-4-8":{"draws":8,"losses":5,"wins":1},"claude-opus-5":{"draws":2,"losses":25,"wins":3},"claude-sonnet-5":{"draws":8,"losses":7,"wins":1},"cohere/north-mini-code":{"draws":4,"losses":6,"wins":0},"google/gemini-3.1-flash-lite":{"draws":2,"losses":4,"wins":4},"google/gemini-3.5-flash":{"draws":1,"losses":2,"wins":1},"google/gemini-3.5-flash-lite":{"draws":45,"losses":23,"wins":28},"google/gemini-3.6-flash":{"draws":42,"losses":27,"wins":9},"google/gemma-4-31b-it":{"draws":0,"losses":5,"wins":1},"gpt-4.1-nano":{"draws":0,"losses":1,"wins":1},"gpt-5":{"draws":2,"losses":2,"wins":0},"gpt-5.4":{"draws":6,"losses":6,"wins":0},"gpt-5.4-mini":{"draws":24,"losses":18,"wins":8},"gpt-5.4-nano":{"draws":7,"losses":7,"wins":12},"gpt-5.5":{"draws":2,"losses":4,"wins":2},"gpt-5.6-luna":{"draws":8,"losses":1,"wins":3},"gpt-5.6-terra":{"draws":9,"losses":5,"wins":2},"inclusionai/ling-3.0-flash":{"draws":21,"losses":5,"wins":10},"meituan/longcat-2.0":{"draws":27,"losses":19,"wins":18},"minimax/minimax-m3":{"draws":5,"losses":2,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":32,"losses":35,"wins":1},"nex-agi/nex-n2-pro":{"draws":3,"losses":1,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":0,"wins":0},"o3":{"draws":13,"losses":19,"wins":12},"openai/gpt-oss-120b":{"draws":11,"losses":8,"wins":11},"poolside/laguna-s-2.1":{"draws":22,"losses":13,"wins":7},"qwen/qwen3.7-max":{"draws":4,"losses":6,"wins":0},"qwen/qwen3.7-plus":{"draws":8,"losses":2,"wins":2},"stepfun/step-3.7-flash":{"draws":2,"losses":7,"wins":3},"thinkingmachines/inkling":{"draws":23,"losses":13,"wins":20},"x-ai/grok-4.5":{"draws":21,"losses":43,"wins":10},"x-ai/grok-build-0.1":{"draws":10,"losses":6,"wins":4},"xiaomi/mimo-v2.5":{"draws":7,"losses":5,"wins":4},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":2,"wins":3},"z-ai/glm-5.2":{"draws":2,"losses":2,"wins":0}},"qwen/qwen3.7-max":{"claude-fable-5":{"draws":3,"losses":13,"wins":2},"claude-opus-4-5":{"draws":14,"losses":16,"wins":8},"claude-opus-4-8":{"draws":8,"losses":8,"wins":6},"claude-opus-5":{"draws":5,"losses":25,"wins":6},"claude-sonnet-5":{"draws":11,"losses":8,"wins":9},"cohere/north-mini-code":{"draws":6,"losses":0,"wins":8},"deepseek/deepseek-v4-flash":{"draws":8,"losses":0,"wins":2},"deepseek/deepseek-v4-pro":{"draws":4,"losses":4,"wins":0},"google/gemini-3.1-flash-lite":{"draws":8,"losses":2,"wins":6},"google/gemini-3.5-flash":{"draws":6,"losses":6,"wins":6},"google/gemini-3.5-flash-lite":{"draws":5,"losses":3,"wins":4},"google/gemini-3.6-flash":{"draws":1,"losses":11,"wins":2},"google/gemma-4-31b-it":{"draws":2,"losses":1,"wins":5},"gpt-4.1":{"draws":6,"losses":0,"wins":0},"gpt-5":{"draws":8,"losses":7,"wins":3},"gpt-5.4":{"draws":3,"losses":14,"wins":3},"gpt-5.4-mini":{"draws":24,"losses":18,"wins":22},"gpt-5.4-nano":{"draws":27,"losses":13,"wins":30},"gpt-5.5":{"draws":7,"losses":12,"wins":5},"gpt-5.6-luna":{"draws":10,"losses":9,"wins":1},"gpt-5.6-sol":{"draws":3,"losses":13,"wins":4},"gpt-5.6-terra":{"draws":7,"losses":8,"wins":3},"inclusionai/ling-3.0-flash":{"draws":7,"losses":1,"wins":4},"meituan/longcat-2.0":{"draws":11,"losses":1,"wins":14},"minimax/minimax-m3":{"draws":7,"losses":5,"wins":6},"mistralai/mistral-medium-3-5":{"draws":2,"losses":2,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":4,"wins":4},"moonshotai/kimi-k3":{"draws":6,"losses":9,"wins":1},"nex-agi/nex-n2-pro":{"draws":3,"losses":1,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":5,"wins":7},"o3":{"draws":7,"losses":2,"wins":5},"openai/gpt-oss-120b":{"draws":10,"losses":0,"wins":4},"poolside/laguna-s-2.1":{"draws":6,"losses":0,"wins":8},"qwen/qwen3.7-max":{"draws":2,"losses":2,"wins":2},"qwen/qwen3.7-plus":{"draws":7,"losses":6,"wins":7},"stepfun/step-3.7-flash":{"draws":3,"losses":2,"wins":7},"tencent/hy3-preview":{"draws":1,"losses":1,"wins":2},"thinkingmachines/inkling":{"draws":7,"losses":1,"wins":6},"x-ai/grok-4.5":{"draws":10,"losses":19,"wins":7},"x-ai/grok-build-0.1":{"draws":6,"losses":6,"wins":4},"xiaomi/mimo-v2.5":{"draws":15,"losses":8,"wins":17},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":2,"wins":11},"z-ai/glm-5.2":{"draws":17,"losses":23,"wins":12}},"qwen/qwen3.7-plus":{"claude-fable-5":{"draws":1,"losses":12,"wins":1},"claude-opus-4-5":{"draws":7,"losses":11,"wins":8},"claude-opus-4-8":{"draws":6,"losses":11,"wins":3},"claude-opus-5":{"draws":4,"losses":18,"wins":0},"claude-sonnet-5":{"draws":6,"losses":5,"wins":5},"cohere/north-mini-code":{"draws":4,"losses":3,"wins":9},"deepseek/deepseek-v4-flash":{"draws":8,"losses":9,"wins":13},"deepseek/deepseek-v4-pro":{"draws":2,"losses":2,"wins":0},"google/gemini-3.1-flash-lite":{"draws":4,"losses":2,"wins":10},"google/gemini-3.5-flash":{"draws":4,"losses":11,"wins":1},"google/gemini-3.5-flash-lite":{"draws":8,"losses":2,"wins":6},"google/gemini-3.6-flash":{"draws":2,"losses":13,"wins":1},"google/gemma-4-31b-it":{"draws":0,"losses":3,"wins":5},"gpt-4.1":{"draws":2,"losses":2,"wins":0},"gpt-5":{"draws":2,"losses":5,"wins":5},"gpt-5.4":{"draws":6,"losses":11,"wins":3},"gpt-5.4-mini":{"draws":24,"losses":7,"wins":25},"gpt-5.4-nano":{"draws":20,"losses":10,"wins":36},"gpt-5.5":{"draws":8,"losses":8,"wins":2},"gpt-5.6-luna":{"draws":4,"losses":8,"wins":6},"gpt-5.6-sol":{"draws":6,"losses":6,"wins":6},"gpt-5.6-terra":{"draws":9,"losses":2,"wins":11},"inclusionai/ling-3.0-flash":{"draws":5,"losses":2,"wins":3},"meituan/longcat-2.0":{"draws":8,"losses":2,"wins":8},"minimax/minimax-m3":{"draws":3,"losses":4,"wins":9},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":6,"wins":2},"moonshotai/kimi-k3":{"draws":8,"losses":8,"wins":6},"nex-agi/nex-n2-pro":{"draws":2,"losses":1,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":5,"wins":7},"o3":{"draws":2,"losses":4,"wins":4},"openai/gpt-oss-120b":{"draws":8,"losses":1,"wins":7},"poolside/laguna-s-2.1":{"draws":13,"losses":4,"wins":3},"qwen/qwen3.7-max":{"draws":5,"losses":7,"wins":6},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":4},"stepfun/step-3.7-flash":{"draws":2,"losses":2,"wins":4},"tencent/hy3-preview":{"draws":2,"losses":2,"wins":2},"thinkingmachines/inkling":{"draws":2,"losses":1,"wins":7},"x-ai/grok-4.5":{"draws":2,"losses":23,"wins":3},"x-ai/grok-build-0.1":{"draws":4,"losses":1,"wins":9},"xiaomi/mimo-v2.5":{"draws":11,"losses":2,"wins":15},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":5,"wins":3},"z-ai/glm-5.2":{"draws":17,"losses":18,"wins":5}},"stepfun/step-3.7-flash":{"claude-fable-5":{"draws":3,"losses":7,"wins":0},"claude-opus-4-5":{"draws":9,"losses":8,"wins":1},"claude-opus-4-8":{"draws":5,"losses":4,"wins":3},"claude-opus-5":{"draws":5,"losses":18,"wins":1},"claude-sonnet-5":{"draws":7,"losses":9,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":3},"deepseek/deepseek-v4-flash":{"draws":6,"losses":4,"wins":10},"deepseek/deepseek-v4-pro":{"draws":2,"losses":0,"wins":0},"google/gemini-3.1-flash-lite":{"draws":4,"losses":2,"wins":4},"google/gemini-3.5-flash":{"draws":3,"losses":4,"wins":3},"google/gemini-3.5-flash-lite":{"draws":5,"losses":1,"wins":8},"google/gemini-3.6-flash":{"draws":2,"losses":4,"wins":0},"google/gemma-4-31b-it":{"draws":1,"losses":2,"wins":7},"gpt-5":{"draws":4,"losses":4,"wins":0},"gpt-5.4":{"draws":3,"losses":2,"wins":3},"gpt-5.4-mini":{"draws":16,"losses":10,"wins":8},"gpt-5.4-nano":{"draws":15,"losses":12,"wins":3},"gpt-5.5":{"draws":4,"losses":6,"wins":2},"gpt-5.6-luna":{"draws":3,"losses":7,"wins":2},"gpt-5.6-sol":{"draws":3,"losses":7,"wins":0},"gpt-5.6-terra":{"draws":6,"losses":4,"wins":0},"inclusionai/ling-3.0-flash":{"draws":0,"losses":2,"wins":4},"meituan/longcat-2.0":{"draws":1,"losses":3,"wins":6},"minimax/minimax-m3":{"draws":4,"losses":2,"wins":2},"mistralai/mistral-medium-3-5":{"draws":0,"losses":1,"wins":1},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":6,"losses":6,"wins":0},"nex-agi/nex-n2-pro":{"draws":0,"losses":1,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":6,"wins":1},"o3":{"draws":2,"losses":2,"wins":2},"openai/gpt-oss-120b":{"draws":3,"losses":0,"wins":5},"poolside/laguna-s-2.1":{"draws":2,"losses":4,"wins":4},"qwen/qwen3.7-max":{"draws":5,"losses":5,"wins":4},"qwen/qwen3.7-plus":{"draws":4,"losses":2,"wins":4},"tencent/hy3-preview":{"draws":2,"losses":0,"wins":2},"thinkingmachines/inkling":{"draws":4,"losses":3,"wins":3},"x-ai/grok-4.5":{"draws":5,"losses":7,"wins":2},"x-ai/grok-build-0.1":{"draws":4,"losses":4,"wins":0},"xiaomi/mimo-v2.5":{"draws":18,"losses":7,"wins":7},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":3,"wins":2},"z-ai/glm-5.2":{"draws":3,"losses":10,"wins":5}},"thinkingmachines/inkling":{"claude-opus-4-5":{"draws":3,"losses":8,"wins":1},"claude-opus-4-8":{"draws":2,"losses":3,"wins":1},"claude-opus-5":{"draws":2,"losses":8,"wins":2},"claude-sonnet-5":{"draws":4,"losses":8,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":6,"wins":0},"deepseek/deepseek-v4-flash":{"draws":0,"losses":1,"wins":7},"deepseek/deepseek-v4-pro":{"draws":0,"losses":1,"wins":1},"google/gemini-3.1-flash-lite":{"draws":1,"losses":2,"wins":5},"google/gemini-3.5-flash":{"draws":1,"losses":3,"wins":0},"google/gemini-3.5-flash-lite":{"draws":15,"losses":16,"wins":11},"google/gemini-3.6-flash":{"draws":21,"losses":14,"wins":7},"google/gemma-4-31b-it":{"draws":0,"losses":4,"wins":2},"gpt-4.1":{"draws":0,"losses":1,"wins":1},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":1,"losses":0,"wins":1},"gpt-5.4":{"draws":3,"losses":1,"wins":2},"gpt-5.4-mini":{"draws":7,"losses":18,"wins":7},"gpt-5.4-nano":{"draws":6,"losses":9,"wins":11},"gpt-5.5":{"draws":3,"losses":1,"wins":2},"gpt-5.6-luna":{"draws":2,"losses":2,"wins":4},"gpt-5.6-sol":{"draws":2,"losses":4,"wins":0},"gpt-5.6-terra":{"draws":4,"losses":1,"wins":3},"inclusionai/ling-3.0-flash":{"draws":2,"losses":5,"wins":3},"meituan/longcat-2.0":{"draws":2,"losses":9,"wins":9},"minimax/minimax-m3":{"draws":2,"losses":4,"wins":4},"mistralai/mistral-medium-3-5":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":4,"wins":0},"moonshotai/kimi-k3":{"draws":16,"losses":25,"wins":5},"nex-agi/nex-n2-pro":{"draws":0,"losses":5,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":5,"wins":1},"o3":{"draws":6,"losses":8,"wins":3},"openai/gpt-oss-120b":{"draws":2,"losses":4,"wins":2},"poolside/laguna-s-2.1":{"draws":6,"losses":6,"wins":6},"qwen/qwen3.7-max":{"draws":2,"losses":2,"wins":0},"qwen/qwen3.7-plus":{"draws":2,"losses":5,"wins":1},"stepfun/step-3.7-flash":{"draws":0,"losses":6,"wins":0},"tencent/hy3-preview":{"draws":0,"losses":1,"wins":1},"thinkingmachines/inkling":{"draws":2,"losses":5,"wins":5},"x-ai/grok-4.5":{"draws":4,"losses":4,"wins":6},"x-ai/grok-build-0.1":{"draws":2,"losses":4,"wins":0},"xiaomi/mimo-v2.5":{"draws":2,"losses":9,"wins":3},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":3,"wins":3},"z-ai/glm-5.2":{"draws":0,"losses":6,"wins":4}},"x-ai/grok-4.5":{"claude-fable-5":{"draws":12,"losses":25,"wins":15},"claude-opus-4-5":{"draws":19,"losses":18,"wins":41},"claude-opus-4-8":{"draws":5,"losses":12,"wins":37},"claude-opus-5":{"draws":11,"losses":71,"wins":24},"claude-sonnet-5":{"draws":11,"losses":7,"wins":22},"cohere/north-mini-code":{"draws":5,"losses":1,"wins":20},"deepseek/deepseek-v4-flash":{"draws":4,"losses":4,"wins":4},"deepseek/deepseek-v4-pro":{"draws":0,"losses":2,"wins":0},"google/gemini-3.1-flash-lite":{"draws":6,"losses":0,"wins":14},"google/gemini-3.5-flash":{"draws":10,"losses":13,"wins":17},"google/gemini-3.5-flash-lite":{"draws":11,"losses":14,"wins":45},"google/gemini-3.6-flash":{"draws":23,"losses":41,"wins":46},"google/gemma-4-31b-it":{"draws":2,"losses":2,"wins":8},"gpt-4.1":{"draws":1,"losses":2,"wins":3},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":9,"losses":3,"wins":24},"gpt-5.4":{"draws":12,"losses":22,"wins":16},"gpt-5.4-mini":{"draws":29,"losses":17,"wins":64},"gpt-5.4-nano":{"draws":14,"losses":20,"wins":74},"gpt-5.5":{"draws":18,"losses":19,"wins":23},"gpt-5.6-luna":{"draws":9,"losses":9,"wins":26},"gpt-5.6-sol":{"draws":13,"losses":23,"wins":22},"gpt-5.6-terra":{"draws":18,"losses":7,"wins":29},"inclusionai/ling-3.0-flash":{"draws":10,"losses":1,"wins":23},"meituan/longcat-2.0":{"draws":10,"losses":11,"wins":41},"minimax/minimax-m3":{"draws":3,"losses":0,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":1,"wins":22},"moonshotai/kimi-k3":{"draws":46,"losses":35,"wins":62},"nex-agi/nex-n2-pro":{"draws":5,"losses":2,"wins":13},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":5,"wins":15},"o3":{"draws":5,"losses":9,"wins":38},"openai/gpt-oss-120b":{"draws":8,"losses":3,"wins":17},"poolside/laguna-s-2.1":{"draws":11,"losses":8,"wins":37},"qwen/qwen3.7-max":{"draws":10,"losses":6,"wins":18},"qwen/qwen3.7-plus":{"draws":4,"losses":3,"wins":21},"stepfun/step-3.7-flash":{"draws":5,"losses":2,"wins":9},"tencent/hy3-preview":{"draws":2,"losses":1,"wins":5},"thinkingmachines/inkling":{"draws":7,"losses":9,"wins":22},"x-ai/grok-4.5":{"draws":40,"losses":42,"wins":68},"x-ai/grok-build-0.1":{"draws":9,"losses":1,"wins":26},"xiaomi/mimo-v2.5":{"draws":14,"losses":4,"wins":38},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":9,"wins":15},"z-ai/glm-5.2":{"draws":13,"losses":7,"wins":22}},"x-ai/grok-build-0.1":{"claude-fable-5":{"draws":2,"losses":11,"wins":3},"claude-opus-4-5":{"draws":13,"losses":11,"wins":6},"claude-opus-4-8":{"draws":9,"losses":9,"wins":6},"claude-opus-5":{"draws":6,"losses":10,"wins":2},"claude-sonnet-5":{"draws":9,"losses":14,"wins":1},"cohere/north-mini-code":{"draws":4,"losses":3,"wins":7},"deepseek/deepseek-v4-flash":{"draws":16,"losses":9,"wins":11},"deepseek/deepseek-v4-pro":{"draws":8,"losses":3,"wins":1},"google/gemini-3.1-flash-lite":{"draws":9,"losses":2,"wins":13},"google/gemini-3.5-flash":{"draws":8,"losses":9,"wins":1},"google/gemini-3.5-flash-lite":{"draws":10,"losses":2,"wins":10},"google/gemini-3.6-flash":{"draws":6,"losses":6,"wins":0},"google/gemma-4-31b-it":{"draws":7,"losses":5,"wins":8},"gpt-4.1":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":7,"losses":11,"wins":4},"gpt-5.4":{"draws":8,"losses":13,"wins":5},"gpt-5.4-mini":{"draws":20,"losses":21,"wins":23},"gpt-5.4-nano":{"draws":21,"losses":25,"wins":24},"gpt-5.5":{"draws":15,"losses":5,"wins":6},"gpt-5.6-luna":{"draws":19,"losses":12,"wins":1},"gpt-5.6-sol":{"draws":6,"losses":14,"wins":6},"gpt-5.6-terra":{"draws":12,"losses":10,"wins":2},"inclusionai/ling-3.0-flash":{"draws":7,"losses":0,"wins":11},"meituan/longcat-2.0":{"draws":9,"losses":8,"wins":13},"minimax/minimax-m3":{"draws":8,"losses":6,"wins":8},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":8,"wins":1},"moonshotai/kimi-k3":{"draws":7,"losses":12,"wins":3},"nex-agi/nex-n2-pro":{"draws":7,"losses":2,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":8,"wins":8},"o3":{"draws":3,"losses":9,"wins":0},"openai/gpt-oss-120b":{"draws":9,"losses":2,"wins":11},"poolside/laguna-s-2.1":{"draws":12,"losses":6,"wins":10},"qwen/qwen3.7-max":{"draws":6,"losses":4,"wins":8},"qwen/qwen3.7-plus":{"draws":6,"losses":10,"wins":2},"stepfun/step-3.7-flash":{"draws":6,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":0,"losses":4,"wins":0},"thinkingmachines/inkling":{"draws":4,"losses":4,"wins":6},"x-ai/grok-4.5":{"draws":9,"losses":26,"wins":1},"xiaomi/mimo-v2.5":{"draws":24,"losses":10,"wins":18},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":8,"wins":0},"z-ai/glm-5.2":{"draws":10,"losses":11,"wins":11}},"xiaomi/mimo-v2.5":{"claude-fable-5":{"draws":3,"losses":31,"wins":2},"claude-opus-4-5":{"draws":31,"losses":25,"wins":12},"claude-opus-4-8":{"draws":18,"losses":19,"wins":5},"claude-opus-5":{"draws":2,"losses":17,"wins":1},"claude-sonnet-5":{"draws":33,"losses":22,"wins":5},"cohere/north-mini-code":{"draws":10,"losses":10,"wins":10},"deepseek/deepseek-v4-flash":{"draws":24,"losses":12,"wins":26},"deepseek/deepseek-v4-pro":{"draws":3,"losses":3,"wins":2},"google/gemini-3.1-flash-lite":{"draws":15,"losses":11,"wins":22},"google/gemini-3.5-flash":{"draws":14,"losses":22,"wins":6},"google/gemini-3.5-flash-lite":{"draws":7,"losses":3,"wins":14},"google/gemini-3.6-flash":{"draws":10,"losses":5,"wins":1},"google/gemma-4-31b-it":{"draws":7,"losses":12,"wins":9},"gpt-4.1":{"draws":3,"losses":3,"wins":4},"gpt-5":{"draws":16,"losses":15,"wins":11},"gpt-5.4":{"draws":19,"losses":20,"wins":5},"gpt-5.4-mini":{"draws":64,"losses":42,"wins":36},"gpt-5.4-nano":{"draws":53,"losses":47,"wins":54},"gpt-5.5":{"draws":20,"losses":16,"wins":2},"gpt-5.6-luna":{"draws":15,"losses":13,"wins":12},"gpt-5.6-sol":{"draws":16,"losses":26,"wins":4},"gpt-5.6-terra":{"draws":19,"losses":18,"wins":7},"inclusionai/ling-3.0-flash":{"draws":7,"losses":8,"wins":9},"meituan/longcat-2.0":{"draws":9,"losses":15,"wins":14},"minimax/minimax-m3":{"draws":19,"losses":11,"wins":12},"mistralai/mistral-medium-3-5":{"draws":3,"losses":4,"wins":7},"moonshotai/kimi-k2.7-code":{"draws":11,"losses":17,"wins":4},"moonshotai/kimi-k3":{"draws":8,"losses":5,"wins":3},"nex-agi/nex-n2-pro":{"draws":2,"losses":8,"wins":14},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":17,"wins":9},"o3":{"draws":8,"losses":20,"wins":0},"openai/gpt-oss-120b":{"draws":17,"losses":8,"wins":7},"poolside/laguna-s-2.1":{"draws":11,"losses":10,"wins":13},"qwen/qwen3.7-max":{"draws":14,"losses":15,"wins":9},"qwen/qwen3.7-plus":{"draws":15,"losses":13,"wins":6},"stepfun/step-3.7-flash":{"draws":18,"losses":5,"wins":5},"tencent/hy3-preview":{"draws":6,"losses":5,"wins":7},"thinkingmachines/inkling":{"draws":9,"losses":7,"wins":22},"x-ai/grok-4.5":{"draws":12,"losses":34,"wins":4},"x-ai/grok-build-0.1":{"draws":14,"losses":11,"wins":7},"xiaomi/mimo-v2.5":{"draws":41,"losses":18,"wins":23},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":10,"wins":9},"z-ai/glm-5.2":{"draws":27,"losses":38,"wins":23}},"xiaomi/mimo-v2.5-pro":{"claude-fable-5":{"draws":0,"losses":20,"wins":0},"claude-opus-4-5":{"draws":3,"losses":12,"wins":11},"claude-opus-4-8":{"draws":3,"losses":14,"wins":5},"claude-opus-5":{"draws":8,"losses":14,"wins":0},"claude-sonnet-5":{"draws":7,"losses":8,"wins":11},"cohere/north-mini-code":{"draws":3,"losses":4,"wins":5},"deepseek/deepseek-v4-flash":{"draws":10,"losses":8,"wins":8},"deepseek/deepseek-v4-pro":{"draws":1,"losses":1,"wins":0},"google/gemini-3.1-flash-lite":{"draws":4,"losses":2,"wins":10},"google/gemini-3.5-flash":{"draws":4,"losses":8,"wins":4},"google/gemini-3.5-flash-lite":{"draws":2,"losses":1,"wins":7},"google/gemini-3.6-flash":{"draws":2,"losses":9,"wins":3},"google/gemma-4-31b-it":{"draws":2,"losses":3,"wins":7},"gpt-4.1":{"draws":0,"losses":5,"wins":3},"gpt-5":{"draws":5,"losses":7,"wins":4},"gpt-5.4":{"draws":4,"losses":20,"wins":6},"gpt-5.4-mini":{"draws":10,"losses":13,"wins":17},"gpt-5.4-nano":{"draws":14,"losses":16,"wins":34},"gpt-5.5":{"draws":5,"losses":10,"wins":5},"gpt-5.6-luna":{"draws":4,"losses":7,"wins":9},"gpt-5.6-sol":{"draws":5,"losses":15,"wins":2},"gpt-5.6-terra":{"draws":5,"losses":9,"wins":4},"inclusionai/ling-3.0-flash":{"draws":0,"losses":2,"wins":4},"meituan/longcat-2.0":{"draws":7,"losses":7,"wins":10},"minimax/minimax-m3":{"draws":5,"losses":6,"wins":7},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":6,"wins":0},"moonshotai/kimi-k3":{"draws":8,"losses":5,"wins":15},"nex-agi/nex-n2-pro":{"draws":0,"losses":2,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":3,"wins":8},"o3":{"draws":3,"losses":5,"wins":8},"openai/gpt-oss-120b":{"draws":6,"losses":1,"wins":5},"poolside/laguna-s-2.1":{"draws":3,"losses":3,"wins":6},"qwen/qwen3.7-max":{"draws":5,"losses":9,"wins":2},"qwen/qwen3.7-plus":{"draws":2,"losses":3,"wins":5},"stepfun/step-3.7-flash":{"draws":1,"losses":2,"wins":3},"tencent/hy3-preview":{"draws":2,"losses":5,"wins":1},"thinkingmachines/inkling":{"draws":0,"losses":2,"wins":2},"x-ai/grok-4.5":{"draws":4,"losses":19,"wins":17},"x-ai/grok-build-0.1":{"draws":4,"losses":0,"wins":6},"xiaomi/mimo-v2.5":{"draws":10,"losses":7,"wins":19},"z-ai/glm-5.2":{"draws":7,"losses":15,"wins":8}},"z-ai/glm-5.2":{"claude-fable-5":{"draws":1,"losses":16,"wins":7},"claude-opus-4-5":{"draws":14,"losses":19,"wins":29},"claude-opus-4-8":{"draws":16,"losses":18,"wins":14},"claude-opus-5":{"draws":5,"losses":47,"wins":4},"claude-sonnet-5":{"draws":22,"losses":10,"wins":20},"cohere/north-mini-code":{"draws":9,"losses":3,"wins":4},"deepseek/deepseek-v4-flash":{"draws":40,"losses":7,"wins":23},"deepseek/deepseek-v4-pro":{"draws":13,"losses":11,"wins":6},"google/gemini-3.1-flash-lite":{"draws":14,"losses":2,"wins":6},"google/gemini-3.5-flash":{"draws":5,"losses":13,"wins":12},"google/gemini-3.5-flash-lite":{"draws":4,"losses":1,"wins":1},"google/gemini-3.6-flash":{"draws":2,"losses":0,"wins":0},"google/gemma-4-31b-it":{"draws":11,"losses":3,"wins":6},"gpt-4.1":{"draws":7,"losses":6,"wins":7},"gpt-5":{"draws":9,"losses":10,"wins":19},"gpt-5.4":{"draws":24,"losses":19,"wins":9},"gpt-5.4-mini":{"draws":52,"losses":25,"wins":31},"gpt-5.4-nano":{"draws":44,"losses":28,"wins":42},"gpt-5.5":{"draws":17,"losses":17,"wins":10},"gpt-5.6-luna":{"draws":11,"losses":8,"wins":17},"gpt-5.6-sol":{"draws":7,"losses":21,"wins":14},"gpt-5.6-terra":{"draws":15,"losses":16,"wins":17},"inclusionai/ling-3.0-flash":{"draws":20,"losses":1,"wins":1},"meituan/longcat-2.0":{"draws":17,"losses":5,"wins":8},"minimax/minimax-m3":{"draws":10,"losses":4,"wins":4},"mistralai/mistral-medium-3-5":{"draws":0,"losses":2,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":4,"wins":6},"nex-agi/nex-n2-pro":{"draws":6,"losses":3,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":17,"losses":3,"wins":8},"o3":{"draws":10,"losses":4,"wins":10},"openai/gpt-oss-120b":{"draws":16,"losses":1,"wins":7},"poolside/laguna-s-2.1":{"draws":13,"losses":7,"wins":9},"qwen/qwen3.7-max":{"draws":12,"losses":5,"wins":17},"qwen/qwen3.7-plus":{"draws":10,"losses":4,"wins":10},"stepfun/step-3.7-flash":{"draws":0,"losses":1,"wins":7},"tencent/hy3-preview":{"draws":16,"losses":5,"wins":5},"thinkingmachines/inkling":{"draws":8,"losses":2,"wins":4},"x-ai/grok-4.5":{"draws":3,"losses":7,"wins":10},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":22,"losses":5,"wins":27},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":3,"wins":13},"z-ai/glm-5.2":{"draws":52,"losses":45,"wins":49}}},"none":{"claude-opus-4-5":{"claude-fable-5":{"draws":3,"losses":3,"wins":4},"claude-opus-4-5":{"draws":13,"losses":4,"wins":9},"claude-opus-4-8":{"draws":3,"losses":12,"wins":9},"claude-opus-5":{"draws":10,"losses":38,"wins":6},"claude-sonnet-5":{"draws":14,"losses":14,"wins":2},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":8},"deepseek/deepseek-v4-flash":{"draws":20,"losses":6,"wins":24},"deepseek/deepseek-v4-pro":{"draws":4,"losses":5,"wins":5},"google/gemini-3.1-flash-lite":{"draws":2,"losses":1,"wins":5},"google/gemini-3.5-flash":{"draws":4,"losses":0,"wins":0},"google/gemini-3.5-flash-lite":{"draws":11,"losses":5,"wins":0},"google/gemini-3.6-flash":{"draws":7,"losses":8,"wins":7},"google/gemma-4-31b-it":{"draws":3,"losses":3,"wins":10},"gpt-4.1":{"draws":5,"losses":5,"wins":0},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":4,"losses":0,"wins":0},"gpt-5.4":{"draws":7,"losses":8,"wins":11},"gpt-5.4-mini":{"draws":22,"losses":11,"wins":33},"gpt-5.4-nano":{"draws":22,"losses":12,"wins":32},"gpt-5.5":{"draws":10,"losses":6,"wins":4},"gpt-5.6-luna":{"draws":11,"losses":1,"wins":12},"gpt-5.6-sol":{"draws":9,"losses":12,"wins":3},"gpt-5.6-terra":{"draws":14,"losses":6,"wins":10},"inclusionai/ling-3.0-flash":{"draws":10,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":11,"losses":3,"wins":6},"minimax/minimax-m3":{"draws":4,"losses":3,"wins":5},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":13,"losses":15,"wins":4},"nex-agi/nex-n2-pro":{"draws":5,"losses":3,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":3,"wins":8},"o3":{"draws":2,"losses":3,"wins":3},"openai/gpt-oss-120b":{"draws":6,"losses":0,"wins":14},"poolside/laguna-s-2.1":{"draws":9,"losses":3,"wins":4},"qwen/qwen3.7-max":{"draws":2,"losses":5,"wins":9},"qwen/qwen3.7-plus":{"draws":6,"losses":3,"wins":7},"stepfun/step-3.7-flash":{"draws":0,"losses":2,"wins":6},"tencent/hy3-preview":{"draws":4,"losses":3,"wins":7},"thinkingmachines/inkling":{"draws":7,"losses":3,"wins":10},"x-ai/grok-4.5":{"draws":12,"losses":18,"wins":10},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":16,"losses":9,"wins":23},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":8,"wins":3},"z-ai/glm-5.2":{"draws":8,"losses":17,"wins":25}},"claude-opus-4-8":{"claude-fable-5":{"draws":0,"losses":6,"wins":2},"claude-opus-4-5":{"draws":8,"losses":6,"wins":14},"claude-opus-4-8":{"draws":4,"losses":1,"wins":3},"claude-opus-5":{"draws":4,"losses":19,"wins":7},"claude-sonnet-5":{"draws":3,"losses":8,"wins":5},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":10},"deepseek/deepseek-v4-flash":{"draws":13,"losses":6,"wins":27},"deepseek/deepseek-v4-pro":{"draws":4,"losses":6,"wins":8},"google/gemini-3.1-flash-lite":{"draws":2,"losses":3,"wins":5},"google/gemini-3.5-flash":{"draws":1,"losses":1,"wins":0},"google/gemini-3.5-flash-lite":{"draws":3,"losses":7,"wins":6},"google/gemini-3.6-flash":{"draws":9,"losses":5,"wins":2},"google/gemma-4-31b-it":{"draws":3,"losses":0,"wins":9},"gpt-4.1":{"draws":2,"losses":1,"wins":7},"gpt-5":{"draws":4,"losses":3,"wins":1},"gpt-5.4":{"draws":3,"losses":9,"wins":6},"gpt-5.4-mini":{"draws":15,"losses":13,"wins":36},"gpt-5.4-nano":{"draws":13,"losses":14,"wins":31},"gpt-5.5":{"draws":5,"losses":12,"wins":5},"gpt-5.6-luna":{"draws":3,"losses":6,"wins":9},"gpt-5.6-sol":{"draws":4,"losses":9,"wins":3},"gpt-5.6-terra":{"draws":7,"losses":5,"wins":6},"inclusionai/ling-3.0-flash":{"draws":8,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":1,"losses":1,"wins":10},"minimax/minimax-m3":{"draws":3,"losses":2,"wins":7},"mistralai/mistral-medium-3-5":{"draws":0,"losses":2,"wins":8},"moonshotai/kimi-k3":{"draws":7,"losses":14,"wins":7},"nex-agi/nex-n2-pro":{"draws":4,"losses":2,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":4,"wins":6},"o3":{"draws":0,"losses":0,"wins":2},"openai/gpt-oss-120b":{"draws":2,"losses":5,"wins":9},"poolside/laguna-s-2.1":{"draws":4,"losses":2,"wins":6},"qwen/qwen3.7-max":{"draws":2,"losses":7,"wins":5},"qwen/qwen3.7-plus":{"draws":6,"losses":2,"wins":6},"stepfun/step-3.7-flash":{"draws":2,"losses":3,"wins":7},"tencent/hy3-preview":{"draws":3,"losses":3,"wins":6},"thinkingmachines/inkling":{"draws":0,"losses":4,"wins":4},"x-ai/grok-4.5":{"draws":6,"losses":22,"wins":8},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":16,"losses":9,"wins":23},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":5,"wins":7},"z-ai/glm-5.2":{"draws":18,"losses":19,"wins":11}},"claude-opus-5":{"claude-fable-5":{"draws":8,"losses":17,"wins":15},"claude-opus-4-5":{"draws":17,"losses":15,"wins":44},"claude-opus-4-8":{"draws":11,"losses":10,"wins":25},"claude-opus-5":{"draws":19,"losses":62,"wins":37},"claude-sonnet-5":{"draws":22,"losses":6,"wins":36},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":8},"deepseek/deepseek-v4-flash":{"draws":12,"losses":4,"wins":38},"deepseek/deepseek-v4-pro":{"draws":5,"losses":0,"wins":25},"google/gemini-3.1-flash-lite":{"draws":3,"losses":0,"wins":5},"google/gemini-3.5-flash":{"draws":5,"losses":5,"wins":16},"google/gemini-3.5-flash-lite":{"draws":7,"losses":4,"wins":31},"google/gemini-3.6-flash":{"draws":7,"losses":14,"wins":29},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":16},"gpt-4.1":{"draws":7,"losses":1,"wins":15},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":7,"losses":1,"wins":18},"gpt-5.4":{"draws":19,"losses":21,"wins":20},"gpt-5.4-mini":{"draws":27,"losses":14,"wins":69},"gpt-5.4-nano":{"draws":17,"losses":11,"wins":62},"gpt-5.5":{"draws":14,"losses":10,"wins":36},"gpt-5.6-luna":{"draws":9,"losses":7,"wins":30},"gpt-5.6-sol":{"draws":16,"losses":8,"wins":46},"gpt-5.6-terra":{"draws":17,"losses":11,"wins":36},"inclusionai/ling-3.0-flash":{"draws":10,"losses":1,"wins":13},"meituan/longcat-2.0":{"draws":6,"losses":1,"wins":25},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":0,"wins":9},"moonshotai/kimi-k3":{"draws":8,"losses":11,"wins":39},"nex-agi/nex-n2-pro":{"draws":0,"losses":1,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":0,"wins":12},"o3":{"draws":2,"losses":3,"wins":13},"openai/gpt-oss-120b":{"draws":2,"losses":2,"wins":4},"poolside/laguna-s-2.1":{"draws":6,"losses":5,"wins":27},"qwen/qwen3.7-max":{"draws":6,"losses":4,"wins":22},"qwen/qwen3.7-plus":{"draws":4,"losses":2,"wins":6},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":12},"tencent/hy3-preview":{"draws":8,"losses":2,"wins":16},"thinkingmachines/inkling":{"draws":2,"losses":7,"wins":9},"x-ai/grok-4.5":{"draws":17,"losses":18,"wins":57},"x-ai/grok-build-0.1":{"draws":3,"losses":1,"wins":4},"xiaomi/mimo-v2.5":{"draws":7,"losses":1,"wins":22},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":0,"wins":20},"z-ai/glm-5.2":{"draws":24,"losses":9,"wins":75}},"claude-sonnet-5":{"claude-fable-5":{"draws":2,"losses":6,"wins":0},"claude-opus-4-5":{"draws":13,"losses":7,"wins":10},"claude-opus-4-8":{"draws":6,"losses":11,"wins":5},"claude-opus-5":{"draws":14,"losses":33,"wins":5},"claude-sonnet-5":{"draws":12,"losses":5,"wins":7},"cohere/north-mini-code":{"draws":7,"losses":0,"wins":5},"deepseek/deepseek-v4-flash":{"draws":25,"losses":7,"wins":12},"deepseek/deepseek-v4-pro":{"draws":4,"losses":4,"wins":10},"google/gemini-3.1-flash-lite":{"draws":4,"losses":3,"wins":5},"google/gemini-3.5-flash":{"draws":5,"losses":4,"wins":3},"google/gemini-3.5-flash-lite":{"draws":17,"losses":7,"wins":6},"google/gemini-3.6-flash":{"draws":16,"losses":7,"wins":5},"google/gemma-4-31b-it":{"draws":8,"losses":0,"wins":2},"gpt-4.1":{"draws":3,"losses":8,"wins":5},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":7,"losses":4,"wins":5},"gpt-5.4":{"draws":10,"losses":8,"wins":4},"gpt-5.4-mini":{"draws":31,"losses":16,"wins":25},"gpt-5.4-nano":{"draws":35,"losses":12,"wins":17},"gpt-5.5":{"draws":15,"losses":3,"wins":6},"gpt-5.6-luna":{"draws":17,"losses":6,"wins":5},"gpt-5.6-sol":{"draws":5,"losses":10,"wins":5},"gpt-5.6-terra":{"draws":11,"losses":6,"wins":11},"inclusionai/ling-3.0-flash":{"draws":14,"losses":0,"wins":6},"meituan/longcat-2.0":{"draws":12,"losses":3,"wins":13},"minimax/minimax-m3":{"draws":4,"losses":3,"wins":7},"mistralai/mistral-medium-3-5":{"draws":2,"losses":6,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":1},"moonshotai/kimi-k3":{"draws":10,"losses":7,"wins":5},"nex-agi/nex-n2-pro":{"draws":5,"losses":3,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":19,"losses":4,"wins":9},"o3":{"draws":4,"losses":8,"wins":4},"openai/gpt-oss-120b":{"draws":10,"losses":3,"wins":5},"poolside/laguna-s-2.1":{"draws":14,"losses":2,"wins":10},"qwen/qwen3.7-max":{"draws":10,"losses":4,"wins":2},"qwen/qwen3.7-plus":{"draws":3,"losses":0,"wins":5},"stepfun/step-3.7-flash":{"draws":6,"losses":3,"wins":7},"tencent/hy3-preview":{"draws":6,"losses":4,"wins":2},"thinkingmachines/inkling":{"draws":10,"losses":2,"wins":8},"x-ai/grok-4.5":{"draws":12,"losses":12,"wins":8},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":25,"losses":9,"wins":14},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":8,"wins":4},"z-ai/glm-5.2":{"draws":23,"losses":26,"wins":19}},"cohere/north-mini-code":{"claude-opus-4-5":{"draws":5,"losses":11,"wins":0},"claude-opus-4-8":{"draws":2,"losses":10,"wins":0},"claude-opus-5":{"draws":4,"losses":14,"wins":2},"claude-sonnet-5":{"draws":4,"losses":4,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":7,"wins":3},"deepseek/deepseek-v4-flash":{"draws":16,"losses":14,"wins":12},"deepseek/deepseek-v4-pro":{"draws":5,"losses":8,"wins":1},"google/gemini-3.1-flash-lite":{"draws":0,"losses":6,"wins":6},"google/gemini-3.5-flash":{"draws":0,"losses":2,"wins":0},"google/gemini-3.5-flash-lite":{"draws":9,"losses":0,"wins":1},"google/gemini-3.6-flash":{"draws":7,"losses":5,"wins":4},"google/gemma-4-31b-it":{"draws":3,"losses":5,"wins":2},"gpt-4.1":{"draws":4,"losses":3,"wins":1},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":2,"losses":4,"wins":2},"gpt-5.4":{"draws":4,"losses":8,"wins":2},"gpt-5.4-mini":{"draws":16,"losses":19,"wins":7},"gpt-5.4-nano":{"draws":14,"losses":31,"wins":15},"gpt-5.5":{"draws":7,"losses":4,"wins":1},"gpt-5.6-luna":{"draws":2,"losses":2,"wins":6},"gpt-5.6-sol":{"draws":2,"losses":9,"wins":1},"gpt-5.6-terra":{"draws":4,"losses":12,"wins":0},"inclusionai/ling-3.0-flash":{"draws":12,"losses":2,"wins":0},"meituan/longcat-2.0":{"draws":16,"losses":8,"wins":2},"minimax/minimax-m3":{"draws":0,"losses":11,"wins":3},"mistralai/mistral-medium-3-5":{"draws":5,"losses":3,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":4,"losses":15,"wins":1},"nex-agi/nex-n2-pro":{"draws":2,"losses":6,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":2,"wins":4},"o3":{"draws":8,"losses":0,"wins":2},"openai/gpt-oss-120b":{"draws":6,"losses":5,"wins":3},"poolside/laguna-s-2.1":{"draws":13,"losses":1,"wins":4},"qwen/qwen3.7-max":{"draws":3,"losses":10,"wins":1},"qwen/qwen3.7-plus":{"draws":5,"losses":6,"wins":3},"stepfun/step-3.7-flash":{"draws":2,"losses":8,"wins":2},"tencent/hy3-preview":{"draws":2,"losses":6,"wins":0},"thinkingmachines/inkling":{"draws":5,"losses":10,"wins":5},"x-ai/grok-4.5":{"draws":4,"losses":7,"wins":1},"x-ai/grok-build-0.1":{"draws":0,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":14,"losses":15,"wins":5},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":6,"wins":2},"z-ai/glm-5.2":{"draws":13,"losses":9,"wins":2}},"deepseek/deepseek-v4-flash":{"claude-fable-5":{"draws":1,"losses":3,"wins":0},"claude-opus-4-5":{"draws":29,"losses":27,"wins":6},"claude-opus-4-8":{"draws":17,"losses":25,"wins":4},"claude-opus-5":{"draws":8,"losses":27,"wins":5},"claude-sonnet-5":{"draws":26,"losses":9,"wins":9},"cohere/north-mini-code":{"draws":15,"losses":20,"wins":11},"deepseek/deepseek-v4-flash":{"draws":46,"losses":43,"wins":41},"deepseek/deepseek-v4-pro":{"draws":13,"losses":16,"wins":13},"google/gemini-3.1-flash-lite":{"draws":15,"losses":10,"wins":17},"google/gemini-3.5-flash":{"draws":13,"losses":4,"wins":1},"google/gemini-3.5-flash-lite":{"draws":27,"losses":5,"wins":6},"google/gemini-3.6-flash":{"draws":26,"losses":20,"wins":6},"google/gemma-4-31b-it":{"draws":15,"losses":13,"wins":14},"gpt-4.1":{"draws":9,"losses":7,"wins":6},"gpt-4.1-nano":{"draws":0,"losses":1,"wins":1},"gpt-5":{"draws":9,"losses":1,"wins":0},"gpt-5.4":{"draws":20,"losses":21,"wins":7},"gpt-5.4-mini":{"draws":70,"losses":52,"wins":40},"gpt-5.4-nano":{"draws":62,"losses":39,"wins":51},"gpt-5.5":{"draws":22,"losses":17,"wins":3},"gpt-5.6-luna":{"draws":27,"losses":13,"wins":16},"gpt-5.6-sol":{"draws":11,"losses":30,"wins":5},"gpt-5.6-terra":{"draws":18,"losses":32,"wins":6},"inclusionai/ling-3.0-flash":{"draws":28,"losses":7,"wins":23},"meituan/longcat-2.0":{"draws":20,"losses":14,"wins":16},"minimax/minimax-m3":{"draws":11,"losses":18,"wins":9},"mistralai/mistral-medium-3-5":{"draws":6,"losses":11,"wins":7},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":3,"wins":1},"moonshotai/kimi-k3":{"draws":23,"losses":49,"wins":4},"nex-agi/nex-n2-pro":{"draws":18,"losses":21,"wins":13},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":26,"losses":13,"wins":11},"o3":{"draws":6,"losses":6,"wins":2},"openai/gpt-oss-120b":{"draws":18,"losses":15,"wins":19},"poolside/laguna-s-2.1":{"draws":17,"losses":14,"wins":7},"qwen/qwen3.7-max":{"draws":16,"losses":19,"wins":3},"qwen/qwen3.7-plus":{"draws":13,"losses":12,"wins":15},"stepfun/step-3.7-flash":{"draws":10,"losses":17,"wins":13},"tencent/hy3-preview":{"draws":17,"losses":14,"wins":9},"thinkingmachines/inkling":{"draws":15,"losses":16,"wins":13},"x-ai/grok-4.5":{"draws":14,"losses":31,"wins":5},"x-ai/grok-build-0.1":{"draws":8,"losses":4,"wins":2},"xiaomi/mimo-v2.5":{"draws":46,"losses":40,"wins":32},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":15,"wins":11},"z-ai/glm-5.2":{"draws":47,"losses":23,"wins":22}},"deepseek/deepseek-v4-pro":{"claude-fable-5":{"draws":1,"losses":7,"wins":0},"claude-opus-4-5":{"draws":10,"losses":7,"wins":9},"claude-opus-4-8":{"draws":6,"losses":10,"wins":6},"claude-opus-5":{"draws":3,"losses":23,"wins":2},"claude-sonnet-5":{"draws":7,"losses":8,"wins":5},"cohere/north-mini-code":{"draws":4,"losses":1,"wins":9},"deepseek/deepseek-v4-flash":{"draws":20,"losses":13,"wins":19},"deepseek/deepseek-v4-pro":{"draws":0,"losses":4,"wins":0},"google/gemini-3.1-flash-lite":{"draws":4,"losses":2,"wins":4},"google/gemini-3.5-flash":{"draws":0,"losses":2,"wins":0},"google/gemini-3.5-flash-lite":{"draws":9,"losses":4,"wins":5},"google/gemini-3.6-flash":{"draws":9,"losses":6,"wins":1},"google/gemma-4-31b-it":{"draws":4,"losses":1,"wins":5},"gpt-4.1":{"draws":4,"losses":4,"wins":2},"gpt-4.1-nano":{"draws":1,"losses":1,"wins":0},"gpt-5":{"draws":1,"losses":2,"wins":3},"gpt-5.4":{"draws":8,"losses":9,"wins":3},"gpt-5.4-mini":{"draws":27,"losses":9,"wins":26},"gpt-5.4-nano":{"draws":23,"losses":17,"wins":18},"gpt-5.5":{"draws":7,"losses":6,"wins":1},"gpt-5.6-luna":{"draws":10,"losses":4,"wins":8},"gpt-5.6-sol":{"draws":2,"losses":9,"wins":5},"gpt-5.6-terra":{"draws":7,"losses":9,"wins":6},"inclusionai/ling-3.0-flash":{"draws":14,"losses":4,"wins":6},"meituan/longcat-2.0":{"draws":5,"losses":3,"wins":12},"minimax/minimax-m3":{"draws":3,"losses":6,"wins":3},"mistralai/mistral-medium-3-5":{"draws":2,"losses":1,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":1,"wins":1},"moonshotai/kimi-k3":{"draws":6,"losses":15,"wins":7},"nex-agi/nex-n2-pro":{"draws":4,"losses":6,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":4,"wins":2},"o3":{"draws":4,"losses":2,"wins":0},"openai/gpt-oss-120b":{"draws":4,"losses":5,"wins":7},"poolside/laguna-s-2.1":{"draws":6,"losses":7,"wins":1},"qwen/qwen3.7-max":{"draws":11,"losses":3,"wins":8},"qwen/qwen3.7-plus":{"draws":6,"losses":0,"wins":8},"stepfun/step-3.7-flash":{"draws":4,"losses":2,"wins":6},"tencent/hy3-preview":{"draws":5,"losses":4,"wins":3},"thinkingmachines/inkling":{"draws":5,"losses":2,"wins":9},"x-ai/grok-4.5":{"draws":7,"losses":15,"wins":6},"x-ai/grok-build-0.1":{"draws":4,"losses":1,"wins":1},"xiaomi/mimo-v2.5":{"draws":9,"losses":8,"wins":21},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":6,"wins":5},"z-ai/glm-5.2":{"draws":14,"losses":13,"wins":21}},"google/gemini-3.1-flash-lite":{"claude-opus-4-5":{"draws":6,"losses":6,"wins":0},"claude-opus-4-8":{"draws":0,"losses":4,"wins":0},"claude-opus-5":{"draws":1,"losses":1,"wins":0},"claude-sonnet-5":{"draws":0,"losses":5,"wins":1},"cohere/north-mini-code":{"draws":0,"losses":7,"wins":3},"deepseek/deepseek-v4-flash":{"draws":13,"losses":28,"wins":9},"deepseek/deepseek-v4-pro":{"draws":4,"losses":5,"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-3.6-flash":{"draws":0,"losses":2,"wins":0},"google/gemma-4-31b-it":{"draws":0,"losses":4,"wins":6},"gpt-4.1":{"draws":2,"losses":2,"wins":0},"gpt-5":{"draws":2,"losses":4,"wins":0},"gpt-5.4":{"draws":0,"losses":2,"wins":0},"gpt-5.4-mini":{"draws":12,"losses":21,"wins":7},"gpt-5.4-nano":{"draws":8,"losses":28,"wins":14},"gpt-5.5":{"draws":4,"losses":3,"wins":1},"gpt-5.6-luna":{"draws":3,"losses":3,"wins":4},"gpt-5.6-sol":{"draws":2,"losses":2,"wins":2},"gpt-5.6-terra":{"draws":0,"losses":8,"wins":0},"inclusionai/ling-3.0-flash":{"draws":0,"losses":3,"wins":3},"meituan/longcat-2.0":{"draws":3,"losses":7,"wins":2},"minimax/minimax-m3":{"draws":0,"losses":5,"wins":5},"mistralai/mistral-medium-3-5":{"draws":4,"losses":4,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":0,"wins":0},"nex-agi/nex-n2-pro":{"draws":0,"losses":5,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":10,"wins":2},"o3":{"draws":0,"losses":2,"wins":0},"openai/gpt-oss-120b":{"draws":2,"losses":6,"wins":2},"poolside/laguna-s-2.1":{"draws":2,"losses":2,"wins":2},"qwen/qwen3.7-max":{"draws":4,"losses":1,"wins":1},"qwen/qwen3.7-plus":{"draws":5,"losses":7,"wins":0},"stepfun/step-3.7-flash":{"draws":2,"losses":9,"wins":1},"tencent/hy3-preview":{"draws":0,"losses":5,"wins":1},"thinkingmachines/inkling":{"draws":6,"losses":6,"wins":4},"x-ai/grok-4.5":{"draws":0,"losses":1,"wins":1},"x-ai/grok-build-0.1":{"draws":2,"losses":4,"wins":0},"xiaomi/mimo-v2.5":{"draws":7,"losses":21,"wins":6},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":7,"wins":0},"z-ai/glm-5.2":{"draws":8,"losses":20,"wins":4}},"google/gemini-3.5-flash-lite":{"claude-opus-4-5":{"draws":19,"losses":10,"wins":11},"claude-opus-4-8":{"draws":2,"losses":5,"wins":7},"claude-opus-5":{"draws":8,"losses":40,"wins":6},"claude-sonnet-5":{"draws":11,"losses":6,"wins":9},"cohere/north-mini-code":{"draws":7,"losses":1,"wins":0},"deepseek/deepseek-v4-flash":{"draws":25,"losses":5,"wins":4},"deepseek/deepseek-v4-pro":{"draws":8,"losses":5,"wins":3},"google/gemini-3.5-flash-lite":{"draws":35,"losses":32,"wins":21},"google/gemini-3.6-flash":{"draws":39,"losses":36,"wins":23},"google/gemma-4-31b-it":{"draws":5,"losses":4,"wins":3},"gpt-4.1":{"draws":6,"losses":4,"wins":10},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":2},"gpt-5.4":{"draws":11,"losses":5,"wins":0},"gpt-5.4-mini":{"draws":26,"losses":13,"wins":15},"gpt-5.4-nano":{"draws":28,"losses":12,"wins":12},"gpt-5.5":{"draws":11,"losses":3,"wins":4},"gpt-5.6-luna":{"draws":12,"losses":0,"wins":2},"gpt-5.6-sol":{"draws":5,"losses":2,"wins":5},"gpt-5.6-terra":{"draws":8,"losses":1,"wins":7},"inclusionai/ling-3.0-flash":{"draws":37,"losses":3,"wins":22},"meituan/longcat-2.0":{"draws":17,"losses":18,"wins":34},"minimax/minimax-m3":{"draws":3,"losses":2,"wins":1},"mistralai/mistral-medium-3-5":{"draws":4,"losses":4,"wins":2},"moonshotai/kimi-k3":{"draws":41,"losses":58,"wins":19},"nex-agi/nex-n2-pro":{"draws":10,"losses":3,"wins":1},"o3":{"draws":8,"losses":15,"wins":15},"openai/gpt-oss-120b":{"draws":2,"losses":2,"wins":4},"poolside/laguna-s-2.1":{"draws":30,"losses":22,"wins":18},"qwen/qwen3.7-max":{"draws":2,"losses":0,"wins":4},"qwen/qwen3.7-plus":{"draws":2,"losses":3,"wins":1},"stepfun/step-3.7-flash":{"draws":0,"losses":3,"wins":5},"tencent/hy3-preview":{"draws":6,"losses":4,"wins":0},"thinkingmachines/inkling":{"draws":26,"losses":23,"wins":29},"x-ai/grok-4.5":{"draws":21,"losses":52,"wins":33},"xiaomi/mimo-v2.5":{"draws":0,"losses":2,"wins":4},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":2,"wins":8},"z-ai/glm-5.2":{"draws":1,"losses":1,"wins":2}},"google/gemini-3.6-flash":{"claude-opus-4-5":{"draws":14,"losses":14,"wins":12},"claude-opus-4-8":{"draws":7,"losses":2,"wins":3},"claude-opus-5":{"draws":3,"losses":37,"wins":8},"claude-sonnet-5":{"draws":14,"losses":7,"wins":5},"cohere/north-mini-code":{"draws":7,"losses":2,"wins":3},"deepseek/deepseek-v4-flash":{"draws":24,"losses":4,"wins":16},"deepseek/deepseek-v4-pro":{"draws":9,"losses":0,"wins":5},"google/gemini-3.5-flash-lite":{"draws":57,"losses":30,"wins":29},"google/gemini-3.6-flash":{"draws":29,"losses":29,"wins":18},"google/gemma-4-31b-it":{"draws":9,"losses":6,"wins":1},"gpt-4.1":{"draws":6,"losses":4,"wins":4},"gpt-4.1-nano":{"draws":1,"losses":3,"wins":0},"gpt-5.4":{"draws":11,"losses":4,"wins":1},"gpt-5.4-mini":{"draws":29,"losses":13,"wins":14},"gpt-5.4-nano":{"draws":32,"losses":7,"wins":9},"gpt-5.5":{"draws":12,"losses":4,"wins":8},"gpt-5.6-luna":{"draws":13,"losses":2,"wins":5},"gpt-5.6-sol":{"draws":5,"losses":5,"wins":4},"gpt-5.6-terra":{"draws":9,"losses":5,"wins":4},"inclusionai/ling-3.0-flash":{"draws":47,"losses":16,"wins":23},"meituan/longcat-2.0":{"draws":22,"losses":19,"wins":25},"minimax/minimax-m3":{"draws":4,"losses":4,"wins":8},"mistralai/mistral-medium-3-5":{"draws":3,"losses":3,"wins":6},"moonshotai/kimi-k3":{"draws":40,"losses":54,"wins":18},"nex-agi/nex-n2-pro":{"draws":12,"losses":3,"wins":7},"o3":{"draws":13,"losses":32,"wins":13},"openai/gpt-oss-120b":{"draws":2,"losses":0,"wins":9},"poolside/laguna-s-2.1":{"draws":42,"losses":21,"wins":23},"qwen/qwen3.7-max":{"draws":5,"losses":1,"wins":8},"qwen/qwen3.7-plus":{"draws":7,"losses":1,"wins":6},"stepfun/step-3.7-flash":{"draws":0,"losses":3,"wins":3},"tencent/hy3-preview":{"draws":6,"losses":1,"wins":5},"thinkingmachines/inkling":{"draws":40,"losses":14,"wins":34},"x-ai/grok-4.5":{"draws":29,"losses":53,"wins":28},"xiaomi/mimo-v2.5":{"draws":2,"losses":7,"wins":7},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":2,"wins":7},"z-ai/glm-5.2":{"draws":2,"losses":1,"wins":1}},"google/gemma-4-31b-it":{"claude-fable-5":{"draws":0,"losses":2,"wins":0},"claude-opus-4-5":{"draws":7,"losses":8,"wins":3},"claude-opus-4-8":{"draws":6,"losses":10,"wins":0},"claude-opus-5":{"draws":4,"losses":12,"wins":0},"claude-sonnet-5":{"draws":8,"losses":2,"wins":0},"cohere/north-mini-code":{"draws":3,"losses":2,"wins":5},"deepseek/deepseek-v4-flash":{"draws":22,"losses":19,"wins":19},"deepseek/deepseek-v4-pro":{"draws":6,"losses":8,"wins":2},"google/gemini-3.1-flash-lite":{"draws":4,"losses":10,"wins":10},"google/gemini-3.5-flash":{"draws":2,"losses":1,"wins":1},"google/gemini-3.5-flash-lite":{"draws":7,"losses":3,"wins":6},"google/gemini-3.6-flash":{"draws":10,"losses":3,"wins":7},"google/gemma-4-31b-it":{"draws":2,"losses":2,"wins":2},"gpt-4.1":{"draws":3,"losses":3,"wins":2},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":2,"losses":3,"wins":1},"gpt-5.4":{"draws":4,"losses":7,"wins":1},"gpt-5.4-mini":{"draws":16,"losses":15,"wins":17},"gpt-5.4-nano":{"draws":13,"losses":20,"wins":23},"gpt-5.5":{"draws":5,"losses":4,"wins":1},"gpt-5.6-luna":{"draws":6,"losses":1,"wins":7},"gpt-5.6-sol":{"draws":4,"losses":10,"wins":0},"gpt-5.6-terra":{"draws":6,"losses":12,"wins":0},"inclusionai/ling-3.0-flash":{"draws":12,"losses":2,"wins":14},"meituan/longcat-2.0":{"draws":6,"losses":5,"wins":5},"minimax/minimax-m3":{"draws":4,"losses":9,"wins":3},"mistralai/mistral-medium-3-5":{"draws":2,"losses":6,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":6,"wins":0},"moonshotai/kimi-k3":{"draws":7,"losses":15,"wins":2},"nex-agi/nex-n2-pro":{"draws":4,"losses":7,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":1,"wins":5},"o3":{"draws":4,"losses":1,"wins":3},"openai/gpt-oss-120b":{"draws":5,"losses":3,"wins":8},"poolside/laguna-s-2.1":{"draws":4,"losses":5,"wins":3},"qwen/qwen3.7-max":{"draws":1,"losses":7,"wins":2},"qwen/qwen3.7-plus":{"draws":1,"losses":4,"wins":7},"stepfun/step-3.7-flash":{"draws":2,"losses":6,"wins":2},"tencent/hy3-preview":{"draws":5,"losses":7,"wins":4},"thinkingmachines/inkling":{"draws":2,"losses":8,"wins":4},"x-ai/grok-4.5":{"draws":4,"losses":12,"wins":0},"x-ai/grok-build-0.1":{"draws":5,"losses":4,"wins":1},"xiaomi/mimo-v2.5":{"draws":12,"losses":22,"wins":12},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":8,"wins":2},"z-ai/glm-5.2":{"draws":16,"losses":7,"wins":5}},"gpt-4.1":{"claude-fable-5":{"draws":2,"losses":0,"wins":2},"claude-opus-4-5":{"draws":12,"losses":3,"wins":7},"claude-opus-4-8":{"draws":4,"losses":11,"wins":3},"claude-opus-5":{"draws":10,"losses":41,"wins":2},"claude-sonnet-5":{"draws":9,"losses":15,"wins":12},"cohere/north-mini-code":{"draws":7,"losses":1,"wins":4},"deepseek/deepseek-v4-flash":{"draws":17,"losses":13,"wins":18},"deepseek/deepseek-v4-pro":{"draws":6,"losses":3,"wins":9},"google/gemini-3.1-flash-lite":{"draws":6,"losses":4,"wins":6},"google/gemini-3.5-flash":{"draws":2,"losses":6,"wins":2},"google/gemini-3.5-flash-lite":{"draws":6,"losses":10,"wins":6},"google/gemini-3.6-flash":{"draws":9,"losses":7,"wins":4},"google/gemma-4-31b-it":{"draws":5,"losses":2,"wins":3},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":5,"losses":3,"wins":4},"gpt-5.4":{"draws":8,"losses":9,"wins":1},"gpt-5.4-mini":{"draws":36,"losses":26,"wins":16},"gpt-5.4-nano":{"draws":24,"losses":22,"wins":20},"gpt-5.5":{"draws":10,"losses":9,"wins":7},"gpt-5.6-luna":{"draws":12,"losses":10,"wins":4},"gpt-5.6-sol":{"draws":3,"losses":13,"wins":2},"gpt-5.6-terra":{"draws":10,"losses":3,"wins":7},"inclusionai/ling-3.0-flash":{"draws":10,"losses":0,"wins":10},"meituan/longcat-2.0":{"draws":4,"losses":4,"wins":12},"minimax/minimax-m3":{"draws":4,"losses":5,"wins":7},"mistralai/mistral-medium-3-5":{"draws":0,"losses":4,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":1,"wins":1},"moonshotai/kimi-k3":{"draws":7,"losses":2,"wins":5},"nex-agi/nex-n2-pro":{"draws":3,"losses":3,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":5,"wins":7},"o3":{"draws":4,"losses":2,"wins":4},"openai/gpt-oss-120b":{"draws":5,"losses":7,"wins":2},"poolside/laguna-s-2.1":{"draws":6,"losses":6,"wins":10},"qwen/qwen3.7-max":{"draws":7,"losses":3,"wins":0},"qwen/qwen3.7-plus":{"draws":2,"losses":2,"wins":2},"stepfun/step-3.7-flash":{"draws":0,"losses":3,"wins":3},"tencent/hy3-preview":{"draws":11,"losses":3,"wins":6},"thinkingmachines/inkling":{"draws":4,"losses":9,"wins":5},"x-ai/grok-4.5":{"draws":9,"losses":24,"wins":7},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":13,"losses":10,"wins":13},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":6,"wins":12},"z-ai/glm-5.2":{"draws":20,"losses":26,"wins":22}},"gpt-4.1-nano":{"claude-opus-4-5":{"draws":2,"losses":0,"wins":0},"claude-opus-5":{"draws":2,"losses":2,"wins":0},"claude-sonnet-5":{"draws":2,"losses":2,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":0},"deepseek/deepseek-v4-flash":{"draws":0,"losses":1,"wins":1},"deepseek/deepseek-v4-pro":{"draws":1,"losses":0,"wins":1},"google/gemini-3.5-flash-lite":{"draws":1,"losses":4,"wins":5},"google/gemini-3.6-flash":{"draws":5,"losses":2,"wins":3},"google/gemma-4-31b-it":{"draws":0,"losses":2,"wins":0},"gpt-4.1":{"draws":0,"losses":2,"wins":0},"gpt-5.4-mini":{"draws":1,"losses":0,"wins":1},"gpt-5.4-nano":{"draws":3,"losses":1,"wins":0},"gpt-5.5":{"draws":2,"losses":0,"wins":0},"inclusionai/ling-3.0-flash":{"draws":1,"losses":1,"wins":4},"meituan/longcat-2.0":{"draws":1,"losses":0,"wins":3},"minimax/minimax-m3":{"draws":0,"losses":1,"wins":1},"moonshotai/kimi-k3":{"draws":5,"losses":3,"wins":0},"o3":{"draws":0,"losses":2,"wins":4},"openai/gpt-oss-120b":{"draws":0,"losses":1,"wins":1},"poolside/laguna-s-2.1":{"draws":0,"losses":4,"wins":2},"thinkingmachines/inkling":{"draws":0,"losses":0,"wins":8},"x-ai/grok-4.5":{"draws":2,"losses":4,"wins":0},"xiaomi/mimo-v2.5":{"draws":0,"losses":0,"wins":2}},"gpt-5.4":{"claude-fable-5":{"draws":1,"losses":7,"wins":4},"claude-opus-4-5":{"draws":8,"losses":10,"wins":6},"claude-opus-4-8":{"draws":3,"losses":6,"wins":7},"claude-opus-5":{"draws":10,"losses":20,"wins":8},"claude-sonnet-5":{"draws":9,"losses":1,"wins":10},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":6},"deepseek/deepseek-v4-flash":{"draws":27,"losses":8,"wins":21},"deepseek/deepseek-v4-pro":{"draws":6,"losses":4,"wins":8},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":6},"google/gemini-3.5-flash":{"draws":0,"losses":3,"wins":1},"google/gemini-3.5-flash-lite":{"draws":12,"losses":0,"wins":6},"google/gemini-3.6-flash":{"draws":15,"losses":3,"wins":6},"google/gemma-4-31b-it":{"draws":4,"losses":3,"wins":7},"gpt-4.1":{"draws":5,"losses":0,"wins":5},"gpt-5":{"draws":2,"losses":0,"wins":6},"gpt-5.4":{"draws":4,"losses":7,"wins":5},"gpt-5.4-mini":{"draws":26,"losses":8,"wins":32},"gpt-5.4-nano":{"draws":27,"losses":12,"wins":35},"gpt-5.5":{"draws":8,"losses":8,"wins":10},"gpt-5.6-luna":{"draws":10,"losses":2,"wins":16},"gpt-5.6-sol":{"draws":4,"losses":9,"wins":17},"gpt-5.6-terra":{"draws":10,"losses":4,"wins":10},"inclusionai/ling-3.0-flash":{"draws":12,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":5,"losses":3,"wins":2},"minimax/minimax-m3":{"draws":4,"losses":5,"wins":5},"mistralai/mistral-medium-3-5":{"draws":1,"losses":0,"wins":7},"moonshotai/kimi-k3":{"draws":9,"losses":10,"wins":13},"nex-agi/nex-n2-pro":{"draws":7,"losses":4,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":1,"wins":4},"o3":{"draws":2,"losses":2,"wins":0},"openai/gpt-oss-120b":{"draws":5,"losses":3,"wins":10},"poolside/laguna-s-2.1":{"draws":6,"losses":2,"wins":2},"qwen/qwen3.7-max":{"draws":4,"losses":2,"wins":10},"qwen/qwen3.7-plus":{"draws":6,"losses":3,"wins":9},"stepfun/step-3.7-flash":{"draws":2,"losses":1,"wins":3},"tencent/hy3-preview":{"draws":8,"losses":3,"wins":7},"thinkingmachines/inkling":{"draws":6,"losses":2,"wins":4},"x-ai/grok-4.5":{"draws":5,"losses":5,"wins":20},"x-ai/grok-build-0.1":{"draws":2,"losses":2,"wins":4},"xiaomi/mimo-v2.5":{"draws":18,"losses":6,"wins":20},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":6,"wins":10},"z-ai/glm-5.2":{"draws":35,"losses":7,"wins":6}},"gpt-5.4-mini":{"claude-fable-5":{"draws":3,"losses":3,"wins":0},"claude-opus-4-5":{"draws":39,"losses":40,"wins":9},"claude-opus-4-8":{"draws":23,"losses":29,"wins":8},"claude-opus-5":{"draws":21,"losses":44,"wins":5},"claude-sonnet-5":{"draws":40,"losses":24,"wins":4},"cohere/north-mini-code":{"draws":13,"losses":10,"wins":17},"deepseek/deepseek-v4-flash":{"draws":83,"losses":52,"wins":59},"deepseek/deepseek-v4-pro":{"draws":24,"losses":25,"wins":9},"google/gemini-3.1-flash-lite":{"draws":13,"losses":13,"wins":30},"google/gemini-3.5-flash":{"draws":12,"losses":4,"wins":2},"google/gemini-3.5-flash-lite":{"draws":32,"losses":17,"wins":13},"google/gemini-3.6-flash":{"draws":32,"losses":21,"wins":13},"google/gemma-4-31b-it":{"draws":15,"losses":21,"wins":12},"gpt-4.1":{"draws":17,"losses":8,"wins":11},"gpt-4.1-nano":{"draws":1,"losses":1,"wins":0},"gpt-5":{"draws":11,"losses":9,"wins":0},"gpt-5.4":{"draws":26,"losses":31,"wins":5},"gpt-5.4-mini":{"draws":67,"losses":44,"wins":37},"gpt-5.4-nano":{"draws":80,"losses":81,"wins":61},"gpt-5.5":{"draws":29,"losses":16,"wins":7},"gpt-5.6-luna":{"draws":26,"losses":10,"wins":22},"gpt-5.6-sol":{"draws":16,"losses":34,"wins":4},"gpt-5.6-terra":{"draws":27,"losses":40,"wins":9},"inclusionai/ling-3.0-flash":{"draws":39,"losses":11,"wins":26},"meituan/longcat-2.0":{"draws":23,"losses":17,"wins":12},"minimax/minimax-m3":{"draws":14,"losses":24,"wins":12},"mistralai/mistral-medium-3-5":{"draws":8,"losses":10,"wins":20},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":37,"losses":51,"wins":8},"nex-agi/nex-n2-pro":{"draws":23,"losses":24,"wins":13},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":26,"losses":8,"wins":14},"o3":{"draws":10,"losses":10,"wins":4},"openai/gpt-oss-120b":{"draws":17,"losses":18,"wins":23},"poolside/laguna-s-2.1":{"draws":19,"losses":10,"wins":7},"qwen/qwen3.7-max":{"draws":20,"losses":22,"wins":6},"qwen/qwen3.7-plus":{"draws":16,"losses":20,"wins":12},"stepfun/step-3.7-flash":{"draws":13,"losses":22,"wins":9},"tencent/hy3-preview":{"draws":20,"losses":19,"wins":9},"thinkingmachines/inkling":{"draws":26,"losses":18,"wins":22},"x-ai/grok-4.5":{"draws":35,"losses":33,"wins":4},"x-ai/grok-build-0.1":{"draws":6,"losses":8,"wins":2},"xiaomi/mimo-v2.5":{"draws":65,"losses":62,"wins":33},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":16,"wins":13},"z-ai/glm-5.2":{"draws":49,"losses":39,"wins":26}},"gpt-5.4-nano":{"claude-fable-5":{"draws":2,"losses":12,"wins":0},"claude-opus-4-5":{"draws":34,"losses":34,"wins":16},"claude-opus-4-8":{"draws":21,"losses":31,"wins":12},"claude-opus-5":{"draws":17,"losses":46,"wins":3},"claude-sonnet-5":{"draws":25,"losses":10,"wins":9},"cohere/north-mini-code":{"draws":17,"losses":11,"wins":20},"deepseek/deepseek-v4-flash":{"draws":82,"losses":58,"wins":48},"deepseek/deepseek-v4-pro":{"draws":23,"losses":16,"wins":13},"google/gemini-3.1-flash-lite":{"draws":15,"losses":17,"wins":20},"google/gemini-3.5-flash":{"draws":6,"losses":5,"wins":3},"google/gemini-3.5-flash-lite":{"draws":35,"losses":12,"wins":13},"google/gemini-3.6-flash":{"draws":39,"losses":14,"wins":7},"google/gemma-4-31b-it":{"draws":11,"losses":15,"wins":16},"gpt-4.1":{"draws":11,"losses":10,"wins":11},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":1},"gpt-5":{"draws":13,"losses":5,"wins":4},"gpt-5.4":{"draws":24,"losses":30,"wins":6},"gpt-5.4-mini":{"draws":76,"losses":63,"wins":61},"gpt-5.4-nano":{"draws":65,"losses":84,"wins":59},"gpt-5.5":{"draws":28,"losses":20,"wins":10},"gpt-5.6-luna":{"draws":26,"losses":21,"wins":27},"gpt-5.6-sol":{"draws":13,"losses":40,"wins":15},"gpt-5.6-terra":{"draws":23,"losses":23,"wins":24},"inclusionai/ling-3.0-flash":{"draws":50,"losses":14,"wins":20},"meituan/longcat-2.0":{"draws":25,"losses":19,"wins":18},"minimax/minimax-m3":{"draws":19,"losses":26,"wins":17},"mistralai/mistral-medium-3-5":{"draws":9,"losses":10,"wins":21},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":0,"wins":3},"moonshotai/kimi-k3":{"draws":30,"losses":57,"wins":13},"nex-agi/nex-n2-pro":{"draws":21,"losses":22,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":28,"losses":6,"wins":14},"o3":{"draws":11,"losses":7,"wins":8},"openai/gpt-oss-120b":{"draws":31,"losses":13,"wins":20},"poolside/laguna-s-2.1":{"draws":25,"losses":15,"wins":6},"qwen/qwen3.7-max":{"draws":27,"losses":19,"wins":8},"qwen/qwen3.7-plus":{"draws":16,"losses":13,"wins":17},"stepfun/step-3.7-flash":{"draws":11,"losses":14,"wins":9},"tencent/hy3-preview":{"draws":28,"losses":22,"wins":2},"thinkingmachines/inkling":{"draws":15,"losses":19,"wins":12},"x-ai/grok-4.5":{"draws":21,"losses":58,"wins":15},"x-ai/grok-build-0.1":{"draws":3,"losses":2,"wins":5},"xiaomi/mimo-v2.5":{"draws":63,"losses":53,"wins":48},"xiaomi/mimo-v2.5-pro":{"draws":17,"losses":28,"wins":13},"z-ai/glm-5.2":{"draws":66,"losses":59,"wins":27}},"gpt-5.5":{"claude-opus-4-5":{"draws":14,"losses":10,"wins":6},"claude-opus-4-8":{"draws":9,"losses":9,"wins":4},"claude-opus-5":{"draws":10,"losses":28,"wins":0},"claude-sonnet-5":{"draws":12,"losses":9,"wins":3},"cohere/north-mini-code":{"draws":7,"losses":1,"wins":4},"deepseek/deepseek-v4-flash":{"draws":26,"losses":3,"wins":17},"deepseek/deepseek-v4-pro":{"draws":8,"losses":1,"wins":5},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":2},"google/gemini-3.5-flash":{"draws":1,"losses":1,"wins":2},"google/gemini-3.5-flash-lite":{"draws":15,"losses":4,"wins":3},"google/gemini-3.6-flash":{"draws":12,"losses":11,"wins":7},"google/gemma-4-31b-it":{"draws":5,"losses":2,"wins":5},"gpt-4.1":{"draws":6,"losses":4,"wins":2},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":3,"losses":1,"wins":0},"gpt-5.4":{"draws":10,"losses":7,"wins":3},"gpt-5.4-mini":{"draws":27,"losses":6,"wins":17},"gpt-5.4-nano":{"draws":29,"losses":2,"wins":17},"gpt-5.5":{"draws":5,"losses":4,"wins":1},"gpt-5.6-luna":{"draws":7,"losses":2,"wins":7},"gpt-5.6-sol":{"draws":7,"losses":12,"wins":5},"gpt-5.6-terra":{"draws":14,"losses":4,"wins":4},"inclusionai/ling-3.0-flash":{"draws":22,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":13,"losses":5,"wins":2},"minimax/minimax-m3":{"draws":2,"losses":7,"wins":5},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":3,"wins":1},"moonshotai/kimi-k3":{"draws":11,"losses":8,"wins":9},"nex-agi/nex-n2-pro":{"draws":8,"losses":2,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":3,"wins":1},"o3":{"draws":7,"losses":1,"wins":2},"openai/gpt-oss-120b":{"draws":9,"losses":1,"wins":6},"poolside/laguna-s-2.1":{"draws":10,"losses":6,"wins":2},"qwen/qwen3.7-max":{"draws":10,"losses":5,"wins":1},"qwen/qwen3.7-plus":{"draws":5,"losses":2,"wins":5},"stepfun/step-3.7-flash":{"draws":3,"losses":2,"wins":3},"tencent/hy3-preview":{"draws":10,"losses":5,"wins":3},"thinkingmachines/inkling":{"draws":9,"losses":3,"wins":6},"x-ai/grok-4.5":{"draws":11,"losses":15,"wins":0},"x-ai/grok-build-0.1":{"draws":6,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":19,"losses":4,"wins":13},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":4,"wins":3},"z-ai/glm-5.2":{"draws":27,"losses":16,"wins":15}},"gpt-5.6-luna":{"claude-opus-4-5":{"draws":17,"losses":9,"wins":0},"claude-opus-4-8":{"draws":7,"losses":9,"wins":2},"claude-opus-5":{"draws":4,"losses":5,"wins":1},"claude-sonnet-5":{"draws":9,"losses":1,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":10,"wins":2},"deepseek/deepseek-v4-flash":{"draws":25,"losses":29,"wins":8},"deepseek/deepseek-v4-pro":{"draws":9,"losses":8,"wins":1},"google/gemini-3.1-flash-lite":{"draws":11,"losses":13,"wins":4},"google/gemini-3.5-flash-lite":{"draws":13,"losses":2,"wins":1},"google/gemini-3.6-flash":{"draws":15,"losses":7,"wins":2},"google/gemma-4-31b-it":{"draws":4,"losses":11,"wins":1},"gpt-4.1":{"draws":6,"losses":3,"wins":1},"gpt-5":{"draws":3,"losses":3,"wins":0},"gpt-5.4":{"draws":8,"losses":15,"wins":1},"gpt-5.4-mini":{"draws":26,"losses":27,"wins":9},"gpt-5.4-nano":{"draws":33,"losses":38,"wins":17},"gpt-5.5":{"draws":8,"losses":6,"wins":2},"gpt-5.6-luna":{"draws":8,"losses":10,"wins":0},"gpt-5.6-sol":{"draws":4,"losses":11,"wins":1},"gpt-5.6-terra":{"draws":5,"losses":13,"wins":0},"inclusionai/ling-3.0-flash":{"draws":17,"losses":8,"wins":3},"meituan/longcat-2.0":{"draws":8,"losses":6,"wins":6},"minimax/minimax-m3":{"draws":10,"losses":8,"wins":2},"mistralai/mistral-medium-3-5":{"draws":4,"losses":9,"wins":2},"moonshotai/kimi-k3":{"draws":9,"losses":20,"wins":3},"nex-agi/nex-n2-pro":{"draws":9,"losses":11,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":6,"wins":1},"o3":{"draws":2,"losses":4,"wins":0},"openai/gpt-oss-120b":{"draws":8,"losses":10,"wins":4},"poolside/laguna-s-2.1":{"draws":7,"losses":2,"wins":1},"qwen/qwen3.7-max":{"draws":8,"losses":8,"wins":0},"qwen/qwen3.7-plus":{"draws":5,"losses":7,"wins":2},"stepfun/step-3.7-flash":{"draws":3,"losses":7,"wins":2},"tencent/hy3-preview":{"draws":4,"losses":9,"wins":5},"thinkingmachines/inkling":{"draws":8,"losses":6,"wins":2},"x-ai/grok-4.5":{"draws":8,"losses":11,"wins":3},"x-ai/grok-build-0.1":{"draws":6,"losses":1,"wins":1},"xiaomi/mimo-v2.5":{"draws":15,"losses":31,"wins":4},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":9,"wins":0},"z-ai/glm-5.2":{"draws":10,"losses":13,"wins":5}},"gpt-5.6-sol":{"claude-fable-5":{"draws":1,"losses":7,"wins":0},"claude-opus-4-5":{"draws":14,"losses":8,"wins":14},"claude-opus-4-8":{"draws":9,"losses":8,"wins":7},"claude-opus-5":{"draws":7,"losses":38,"wins":1},"claude-sonnet-5":{"draws":5,"losses":7,"wins":4},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":7},"deepseek/deepseek-v4-flash":{"draws":15,"losses":10,"wins":29},"deepseek/deepseek-v4-pro":{"draws":2,"losses":6,"wins":8},"google/gemini-3.1-flash-lite":{"draws":3,"losses":4,"wins":1},"google/gemini-3.5-flash-lite":{"draws":7,"losses":5,"wins":4},"google/gemini-3.6-flash":{"draws":7,"losses":6,"wins":5},"google/gemma-4-31b-it":{"draws":6,"losses":2,"wins":8},"gpt-4.1":{"draws":3,"losses":2,"wins":5},"gpt-5":{"draws":3,"losses":3,"wins":2},"gpt-5.4":{"draws":7,"losses":10,"wins":7},"gpt-5.4-mini":{"draws":18,"losses":7,"wins":31},"gpt-5.4-nano":{"draws":10,"losses":15,"wins":31},"gpt-5.5":{"draws":8,"losses":7,"wins":7},"gpt-5.6-luna":{"draws":6,"losses":7,"wins":13},"gpt-5.6-sol":{"draws":1,"losses":6,"wins":3},"gpt-5.6-terra":{"draws":9,"losses":11,"wins":8},"inclusionai/ling-3.0-flash":{"draws":4,"losses":2,"wins":8},"meituan/longcat-2.0":{"draws":3,"losses":5,"wins":4},"minimax/minimax-m3":{"draws":5,"losses":2,"wins":9},"mistralai/mistral-medium-3-5":{"draws":0,"losses":1,"wins":5},"moonshotai/kimi-k3":{"draws":7,"losses":11,"wins":14},"nex-agi/nex-n2-pro":{"draws":5,"losses":3,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":4,"wins":4},"o3":{"draws":1,"losses":2,"wins":3},"openai/gpt-oss-120b":{"draws":4,"losses":1,"wins":11},"poolside/laguna-s-2.1":{"draws":0,"losses":9,"wins":5},"qwen/qwen3.7-max":{"draws":3,"losses":7,"wins":6},"qwen/qwen3.7-plus":{"draws":4,"losses":3,"wins":7},"stepfun/step-3.7-flash":{"draws":0,"losses":3,"wins":5},"tencent/hy3-preview":{"draws":9,"losses":5,"wins":8},"thinkingmachines/inkling":{"draws":4,"losses":4,"wins":4},"x-ai/grok-4.5":{"draws":8,"losses":16,"wins":10},"x-ai/grok-build-0.1":{"draws":2,"losses":4,"wins":2},"xiaomi/mimo-v2.5":{"draws":16,"losses":10,"wins":22},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":4,"wins":7},"z-ai/glm-5.2":{"draws":14,"losses":27,"wins":17}},"gpt-5.6-terra":{"claude-fable-5":{"draws":1,"losses":7,"wins":0},"claude-opus-4-5":{"draws":14,"losses":11,"wins":7},"claude-opus-4-8":{"draws":12,"losses":7,"wins":5},"claude-opus-5":{"draws":14,"losses":23,"wins":5},"claude-sonnet-5":{"draws":13,"losses":14,"wins":1},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":10},"deepseek/deepseek-v4-flash":{"draws":24,"losses":10,"wins":32},"deepseek/deepseek-v4-pro":{"draws":8,"losses":5,"wins":5},"google/gemini-3.1-flash-lite":{"draws":0,"losses":4,"wins":4},"google/gemini-3.5-flash":{"draws":4,"losses":4,"wins":2},"google/gemini-3.5-flash-lite":{"draws":8,"losses":7,"wins":1},"google/gemini-3.6-flash":{"draws":11,"losses":6,"wins":7},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":10},"gpt-4.1":{"draws":8,"losses":3,"wins":1},"gpt-5":{"draws":2,"losses":0,"wins":0},"gpt-5.4":{"draws":12,"losses":15,"wins":5},"gpt-5.4-mini":{"draws":27,"losses":16,"wins":25},"gpt-5.4-nano":{"draws":23,"losses":13,"wins":20},"gpt-5.5":{"draws":12,"losses":7,"wins":3},"gpt-5.6-luna":{"draws":10,"losses":5,"wins":15},"gpt-5.6-sol":{"draws":9,"losses":12,"wins":3},"gpt-5.6-terra":{"draws":5,"losses":3,"wins":0},"inclusionai/ling-3.0-flash":{"draws":8,"losses":2,"wins":8},"meituan/longcat-2.0":{"draws":5,"losses":5,"wins":2},"minimax/minimax-m3":{"draws":6,"losses":6,"wins":6},"mistralai/mistral-medium-3-5":{"draws":2,"losses":1,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":2,"wins":1},"moonshotai/kimi-k3":{"draws":12,"losses":13,"wins":7},"nex-agi/nex-n2-pro":{"draws":5,"losses":4,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":5,"wins":6},"o3":{"draws":0,"losses":2,"wins":4},"openai/gpt-oss-120b":{"draws":3,"losses":4,"wins":11},"poolside/laguna-s-2.1":{"draws":8,"losses":6,"wins":6},"qwen/qwen3.7-max":{"draws":5,"losses":4,"wins":5},"qwen/qwen3.7-plus":{"draws":4,"losses":2,"wins":6},"stepfun/step-3.7-flash":{"draws":6,"losses":4,"wins":2},"tencent/hy3-preview":{"draws":8,"losses":4,"wins":2},"thinkingmachines/inkling":{"draws":7,"losses":4,"wins":3},"x-ai/grok-4.5":{"draws":7,"losses":20,"wins":5},"x-ai/grok-build-0.1":{"draws":0,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":17,"losses":11,"wins":12},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":5,"wins":4},"z-ai/glm-5.2":{"draws":18,"losses":16,"wins":10}},"inclusionai/ling-3.0-flash":{"claude-opus-4-5":{"draws":14,"losses":6,"wins":2},"claude-opus-4-8":{"draws":14,"losses":4,"wins":0},"claude-opus-5":{"draws":8,"losses":17,"wins":1},"claude-sonnet-5":{"draws":22,"losses":15,"wins":1},"cohere/north-mini-code":{"draws":16,"losses":4,"wins":6},"deepseek/deepseek-v4-flash":{"draws":44,"losses":37,"wins":15},"deepseek/deepseek-v4-pro":{"draws":14,"losses":12,"wins":4},"google/gemini-3.1-flash-lite":{"draws":8,"losses":11,"wins":7},"google/gemini-3.5-flash":{"draws":6,"losses":0,"wins":0},"google/gemini-3.5-flash-lite":{"draws":33,"losses":15,"wins":4},"google/gemini-3.6-flash":{"draws":47,"losses":20,"wins":9},"google/gemma-4-31b-it":{"draws":12,"losses":17,"wins":3},"gpt-4.1":{"draws":10,"losses":10,"wins":0},"gpt-4.1-nano":{"draws":1,"losses":2,"wins":1},"gpt-5":{"draws":4,"losses":2,"wins":8},"gpt-5.4":{"draws":16,"losses":5,"wins":1},"gpt-5.4-mini":{"draws":57,"losses":35,"wins":14},"gpt-5.4-nano":{"draws":69,"losses":22,"wins":27},"gpt-5.5":{"draws":26,"losses":6,"wins":2},"gpt-5.6-luna":{"draws":26,"losses":3,"wins":9},"gpt-5.6-sol":{"draws":5,"losses":9,"wins":2},"gpt-5.6-terra":{"draws":11,"losses":9,"wins":2},"inclusionai/ling-3.0-flash":{"draws":16,"losses":13,"wins":11},"meituan/longcat-2.0":{"draws":35,"losses":22,"wins":13},"minimax/minimax-m3":{"draws":13,"losses":12,"wins":3},"mistralai/mistral-medium-3-5":{"draws":8,"losses":10,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":1},"moonshotai/kimi-k3":{"draws":22,"losses":8,"wins":0},"nex-agi/nex-n2-pro":{"draws":20,"losses":11,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":6,"wins":5},"o3":{"draws":5,"losses":5,"wins":2},"openai/gpt-oss-120b":{"draws":19,"losses":8,"wins":5},"poolside/laguna-s-2.1":{"draws":39,"losses":21,"wins":10},"qwen/qwen3.7-max":{"draws":17,"losses":6,"wins":5},"qwen/qwen3.7-plus":{"draws":13,"losses":7,"wins":6},"stepfun/step-3.7-flash":{"draws":4,"losses":10,"wins":2},"tencent/hy3-preview":{"draws":11,"losses":11,"wins":2},"thinkingmachines/inkling":{"draws":23,"losses":23,"wins":16},"x-ai/grok-4.5":{"draws":16,"losses":26,"wins":6},"x-ai/grok-build-0.1":{"draws":5,"losses":9,"wins":0},"xiaomi/mimo-v2.5":{"draws":28,"losses":19,"wins":15},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":11,"wins":6},"z-ai/glm-5.2":{"draws":48,"losses":10,"wins":10}},"meituan/longcat-2.0":{"claude-fable-5":{"draws":1,"losses":3,"wins":0},"claude-opus-4-5":{"draws":16,"losses":12,"wins":8},"claude-opus-4-8":{"draws":4,"losses":13,"wins":5},"claude-opus-5":{"draws":7,"losses":31,"wins":6},"claude-sonnet-5":{"draws":21,"losses":27,"wins":8},"cohere/north-mini-code":{"draws":18,"losses":3,"wins":11},"deepseek/deepseek-v4-flash":{"draws":32,"losses":33,"wins":27},"deepseek/deepseek-v4-pro":{"draws":5,"losses":16,"wins":7},"google/gemini-3.1-flash-lite":{"draws":9,"losses":12,"wins":17},"google/gemini-3.5-flash":{"draws":5,"losses":2,"wins":1},"google/gemini-3.5-flash-lite":{"draws":20,"losses":27,"wins":9},"google/gemini-3.6-flash":{"draws":26,"losses":25,"wins":17},"google/gemma-4-31b-it":{"draws":6,"losses":6,"wins":8},"gpt-4.1":{"draws":4,"losses":12,"wins":4},"gpt-4.1-nano":{"draws":1,"losses":3,"wins":0},"gpt-5":{"draws":7,"losses":9,"wins":6},"gpt-5.4":{"draws":11,"losses":8,"wins":5},"gpt-5.4-mini":{"draws":41,"losses":39,"wins":32},"gpt-5.4-nano":{"draws":42,"losses":40,"wins":42},"gpt-5.5":{"draws":13,"losses":4,"wins":9},"gpt-5.6-luna":{"draws":20,"losses":10,"wins":8},"gpt-5.6-sol":{"draws":3,"losses":6,"wins":7},"gpt-5.6-terra":{"draws":14,"losses":9,"wins":9},"inclusionai/ling-3.0-flash":{"draws":33,"losses":19,"wins":24},"meituan/longcat-2.0":{"draws":10,"losses":9,"wins":11},"minimax/minimax-m3":{"draws":5,"losses":11,"wins":10},"mistralai/mistral-medium-3-5":{"draws":4,"losses":6,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":3,"wins":1},"moonshotai/kimi-k3":{"draws":15,"losses":12,"wins":7},"nex-agi/nex-n2-pro":{"draws":10,"losses":8,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":14,"wins":6},"o3":{"draws":7,"losses":4,"wins":13},"openai/gpt-oss-120b":{"draws":16,"losses":7,"wins":7},"poolside/laguna-s-2.1":{"draws":33,"losses":25,"wins":12},"qwen/qwen3.7-max":{"draws":17,"losses":4,"wins":3},"qwen/qwen3.7-plus":{"draws":5,"losses":3,"wins":6},"stepfun/step-3.7-flash":{"draws":3,"losses":11,"wins":8},"tencent/hy3-preview":{"draws":11,"losses":7,"wins":6},"thinkingmachines/inkling":{"draws":16,"losses":27,"wins":17},"x-ai/grok-4.5":{"draws":18,"losses":37,"wins":11},"x-ai/grok-build-0.1":{"draws":4,"losses":5,"wins":5},"xiaomi/mimo-v2.5":{"draws":18,"losses":24,"wins":26},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":16,"wins":7},"z-ai/glm-5.2":{"draws":46,"losses":43,"wins":19}},"minimax/minimax-m3":{"claude-fable-5":{"draws":0,"losses":2,"wins":0},"claude-opus-4-5":{"draws":6,"losses":15,"wins":5},"claude-opus-4-8":{"draws":1,"losses":11,"wins":2},"claude-opus-5":{"draws":3,"losses":29,"wins":4},"claude-sonnet-5":{"draws":2,"losses":6,"wins":2},"cohere/north-mini-code":{"draws":0,"losses":6,"wins":8},"deepseek/deepseek-v4-flash":{"draws":9,"losses":15,"wins":22},"deepseek/deepseek-v4-pro":{"draws":3,"losses":3,"wins":8},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":4},"google/gemini-3.5-flash":{"draws":2,"losses":0,"wins":0},"google/gemini-3.5-flash-lite":{"draws":3,"losses":2,"wins":3},"google/gemini-3.6-flash":{"draws":6,"losses":12,"wins":4},"google/gemma-4-31b-it":{"draws":0,"losses":2,"wins":8},"gpt-4.1":{"draws":0,"losses":4,"wins":4},"gpt-4.1-nano":{"draws":0,"losses":1,"wins":1},"gpt-5":{"draws":2,"losses":2,"wins":4},"gpt-5.4":{"draws":4,"losses":9,"wins":7},"gpt-5.4-mini":{"draws":18,"losses":9,"wins":29},"gpt-5.4-nano":{"draws":17,"losses":11,"wins":22},"gpt-5.5":{"draws":4,"losses":9,"wins":7},"gpt-5.6-luna":{"draws":6,"losses":3,"wins":7},"gpt-5.6-sol":{"draws":3,"losses":11,"wins":2},"gpt-5.6-terra":{"draws":6,"losses":9,"wins":5},"inclusionai/ling-3.0-flash":{"draws":5,"losses":2,"wins":7},"meituan/longcat-2.0":{"draws":3,"losses":4,"wins":9},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":6,"losses":15,"wins":3},"nex-agi/nex-n2-pro":{"draws":4,"losses":3,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":4,"wins":6},"o3":{"draws":1,"losses":5,"wins":2},"openai/gpt-oss-120b":{"draws":3,"losses":2,"wins":9},"poolside/laguna-s-2.1":{"draws":4,"losses":5,"wins":5},"qwen/qwen3.7-max":{"draws":6,"losses":5,"wins":1},"qwen/qwen3.7-plus":{"draws":3,"losses":3,"wins":4},"stepfun/step-3.7-flash":{"draws":0,"losses":1,"wins":7},"tencent/hy3-preview":{"draws":2,"losses":5,"wins":5},"thinkingmachines/inkling":{"draws":4,"losses":4,"wins":10},"x-ai/grok-4.5":{"draws":3,"losses":12,"wins":3},"x-ai/grok-build-0.1":{"draws":1,"losses":1,"wins":4},"xiaomi/mimo-v2.5":{"draws":8,"losses":9,"wins":17},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":5,"wins":7},"z-ai/glm-5.2":{"draws":14,"losses":8,"wins":14}},"mistralai/mistral-medium-3-5":{"claude-opus-4-5":{"draws":0,"losses":12,"wins":0},"claude-opus-4-8":{"draws":2,"losses":8,"wins":2},"claude-sonnet-5":{"draws":2,"losses":0,"wins":4},"cohere/north-mini-code":{"draws":6,"losses":2,"wins":2},"deepseek/deepseek-v4-flash":{"draws":11,"losses":14,"wins":17},"deepseek/deepseek-v4-pro":{"draws":4,"losses":6,"wins":2},"google/gemini-3.1-flash-lite":{"draws":4,"losses":4,"wins":4},"google/gemini-3.5-flash":{"draws":4,"losses":0,"wins":0},"google/gemini-3.5-flash-lite":{"draws":4,"losses":2,"wins":4},"google/gemini-3.6-flash":{"draws":3,"losses":6,"wins":3},"google/gemma-4-31b-it":{"draws":3,"losses":4,"wins":3},"gpt-4.1":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":0,"losses":2,"wins":4},"gpt-5.4":{"draws":1,"losses":5,"wins":0},"gpt-5.4-mini":{"draws":8,"losses":16,"wins":10},"gpt-5.4-nano":{"draws":11,"losses":18,"wins":11},"gpt-5.5":{"draws":2,"losses":4,"wins":0},"gpt-5.6-luna":{"draws":2,"losses":1,"wins":4},"gpt-5.6-sol":{"draws":0,"losses":9,"wins":1},"gpt-5.6-terra":{"draws":2,"losses":9,"wins":1},"inclusionai/ling-3.0-flash":{"draws":8,"losses":0,"wins":6},"meituan/longcat-2.0":{"draws":4,"losses":2,"wins":4},"minimax/minimax-m3":{"draws":0,"losses":8,"wins":2},"mistralai/mistral-medium-3-5":{"draws":0,"losses":1,"wins":5},"moonshotai/kimi-k3":{"draws":2,"losses":14,"wins":0},"nex-agi/nex-n2-pro":{"draws":2,"losses":1,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":7,"wins":3},"o3":{"draws":3,"losses":0,"wins":3},"openai/gpt-oss-120b":{"draws":8,"losses":4,"wins":2},"poolside/laguna-s-2.1":{"draws":0,"losses":3,"wins":1},"qwen/qwen3.7-max":{"draws":2,"losses":3,"wins":3},"qwen/qwen3.7-plus":{"draws":2,"losses":3,"wins":3},"stepfun/step-3.7-flash":{"draws":4,"losses":3,"wins":5},"tencent/hy3-preview":{"draws":2,"losses":0,"wins":4},"thinkingmachines/inkling":{"draws":1,"losses":3,"wins":8},"x-ai/grok-4.5":{"draws":0,"losses":12,"wins":0},"x-ai/grok-build-0.1":{"draws":2,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":9,"losses":14,"wins":11},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":5,"wins":1},"z-ai/glm-5.2":{"draws":4,"losses":10,"wins":12}},"moonshotai/kimi-k3":{"claude-opus-4-5":{"draws":23,"losses":13,"wins":32},"claude-opus-4-8":{"draws":7,"losses":7,"wins":14},"claude-opus-5":{"draws":11,"losses":59,"wins":12},"claude-sonnet-5":{"draws":8,"losses":5,"wins":5},"cohere/north-mini-code":{"draws":4,"losses":1,"wins":15},"deepseek/deepseek-v4-flash":{"draws":23,"losses":4,"wins":49},"deepseek/deepseek-v4-pro":{"draws":6,"losses":7,"wins":15},"google/gemini-3.5-flash-lite":{"draws":29,"losses":21,"wins":28},"google/gemini-3.6-flash":{"draws":27,"losses":47,"wins":32},"google/gemma-4-31b-it":{"draws":7,"losses":2,"wins":15},"gpt-4.1":{"draws":7,"losses":5,"wins":2},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5.4":{"draws":9,"losses":13,"wins":10},"gpt-5.4-mini":{"draws":37,"losses":8,"wins":51},"gpt-5.4-nano":{"draws":30,"losses":13,"wins":57},"gpt-5.5":{"draws":11,"losses":9,"wins":8},"gpt-5.6-luna":{"draws":9,"losses":3,"wins":20},"gpt-5.6-sol":{"draws":7,"losses":14,"wins":11},"gpt-5.6-terra":{"draws":12,"losses":7,"wins":13},"inclusionai/ling-3.0-flash":{"draws":21,"losses":1,"wins":10},"meituan/longcat-2.0":{"draws":14,"losses":8,"wins":14},"minimax/minimax-m3":{"draws":6,"losses":3,"wins":15},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":14},"moonshotai/kimi-k3":{"draws":29,"losses":56,"wins":37},"nex-agi/nex-n2-pro":{"draws":10,"losses":5,"wins":13},"o3":{"draws":6,"losses":18,"wins":16},"openai/gpt-oss-120b":{"draws":5,"losses":3,"wins":20},"poolside/laguna-s-2.1":{"draws":19,"losses":9,"wins":16},"qwen/qwen3.7-max":{"draws":7,"losses":6,"wins":15},"qwen/qwen3.7-plus":{"draws":10,"losses":3,"wins":11},"stepfun/step-3.7-flash":{"draws":1,"losses":1,"wins":8},"tencent/hy3-preview":{"draws":7,"losses":4,"wins":13},"thinkingmachines/inkling":{"draws":14,"losses":9,"wins":29},"x-ai/grok-4.5":{"draws":29,"losses":53,"wins":40},"xiaomi/mimo-v2.5":{"draws":19,"losses":12,"wins":37},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":10,"wins":11},"z-ai/glm-5.2":{"draws":2,"losses":2,"wins":0}},"nex-agi/nex-n2-pro":{"claude-fable-5":{"draws":0,"losses":4,"wins":0},"claude-opus-4-5":{"draws":7,"losses":9,"wins":6},"claude-opus-4-8":{"draws":11,"losses":12,"wins":3},"claude-opus-5":{"draws":0,"losses":13,"wins":1},"claude-sonnet-5":{"draws":6,"losses":4,"wins":6},"cohere/north-mini-code":{"draws":3,"losses":3,"wins":8},"deepseek/deepseek-v4-flash":{"draws":28,"losses":12,"wins":20},"deepseek/deepseek-v4-pro":{"draws":6,"losses":7,"wins":5},"google/gemini-3.1-flash-lite":{"draws":4,"losses":3,"wins":3},"google/gemini-3.5-flash":{"draws":0,"losses":0,"wins":2},"google/gemini-3.5-flash-lite":{"draws":12,"losses":1,"wins":3},"google/gemini-3.6-flash":{"draws":15,"losses":8,"wins":3},"google/gemma-4-31b-it":{"draws":4,"losses":4,"wins":4},"gpt-4.1":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":4,"losses":0,"wins":0},"gpt-5.4":{"draws":10,"losses":9,"wins":3},"gpt-5.4-mini":{"draws":25,"losses":11,"wins":16},"gpt-5.4-nano":{"draws":28,"losses":15,"wins":15},"gpt-5.5":{"draws":8,"losses":4,"wins":2},"gpt-5.6-luna":{"draws":13,"losses":3,"wins":6},"gpt-5.6-sol":{"draws":5,"losses":7,"wins":4},"gpt-5.6-terra":{"draws":9,"losses":9,"wins":4},"inclusionai/ling-3.0-flash":{"draws":18,"losses":3,"wins":7},"meituan/longcat-2.0":{"draws":9,"losses":0,"wins":3},"minimax/minimax-m3":{"draws":7,"losses":6,"wins":3},"mistralai/mistral-medium-3-5":{"draws":2,"losses":5,"wins":3},"moonshotai/kimi-k3":{"draws":10,"losses":13,"wins":5},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":4,"wins":5},"o3":{"draws":2,"losses":3,"wins":3},"openai/gpt-oss-120b":{"draws":12,"losses":8,"wins":4},"poolside/laguna-s-2.1":{"draws":4,"losses":3,"wins":3},"qwen/qwen3.7-max":{"draws":6,"losses":6,"wins":2},"qwen/qwen3.7-plus":{"draws":4,"losses":2,"wins":4},"stepfun/step-3.7-flash":{"draws":4,"losses":3,"wins":5},"tencent/hy3-preview":{"draws":11,"losses":1,"wins":4},"thinkingmachines/inkling":{"draws":4,"losses":3,"wins":5},"x-ai/grok-4.5":{"draws":5,"losses":13,"wins":2},"x-ai/grok-build-0.1":{"draws":4,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":18,"losses":13,"wins":11},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":2,"wins":4},"z-ai/glm-5.2":{"draws":20,"losses":15,"wins":9}},"nvidia/nemotron-3-ultra-550b-a55b":{"claude-fable-5":{"draws":0,"losses":3,"wins":1},"claude-opus-4-5":{"draws":2,"losses":7,"wins":3},"claude-opus-4-8":{"draws":2,"losses":5,"wins":7},"claude-opus-5":{"draws":8,"losses":18,"wins":0},"claude-sonnet-5":{"draws":9,"losses":6,"wins":7},"cohere/north-mini-code":{"draws":3,"losses":9,"wins":2},"deepseek/deepseek-v4-flash":{"draws":16,"losses":23,"wins":9},"deepseek/deepseek-v4-pro":{"draws":4,"losses":6,"wins":0},"google/gemini-3.1-flash-lite":{"draws":4,"losses":7,"wins":5},"google/gemini-3.5-flash":{"draws":2,"losses":4,"wins":0},"google/gemini-3.6-flash":{"draws":2,"losses":3,"wins":1},"google/gemma-4-31b-it":{"draws":2,"losses":7,"wins":3},"gpt-4.1":{"draws":2,"losses":2,"wins":0},"gpt-5":{"draws":5,"losses":2,"wins":1},"gpt-5.4":{"draws":7,"losses":6,"wins":3},"gpt-5.4-mini":{"draws":18,"losses":17,"wins":9},"gpt-5.4-nano":{"draws":14,"losses":15,"wins":7},"gpt-5.5":{"draws":12,"losses":4,"wins":2},"gpt-5.6-luna":{"draws":11,"losses":4,"wins":7},"gpt-5.6-sol":{"draws":2,"losses":10,"wins":2},"gpt-5.6-terra":{"draws":7,"losses":7,"wins":6},"inclusionai/ling-3.0-flash":{"draws":8,"losses":2,"wins":4},"meituan/longcat-2.0":{"draws":7,"losses":3,"wins":2},"minimax/minimax-m3":{"draws":4,"losses":5,"wins":5},"mistralai/mistral-medium-3-5":{"draws":0,"losses":4,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":1},"nex-agi/nex-n2-pro":{"draws":7,"losses":4,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":0,"wins":2},"o3":{"draws":3,"losses":0,"wins":3},"openai/gpt-oss-120b":{"draws":3,"losses":5,"wins":2},"poolside/laguna-s-2.1":{"draws":4,"losses":4,"wins":4},"qwen/qwen3.7-max":{"draws":6,"losses":6,"wins":4},"qwen/qwen3.7-plus":{"draws":3,"losses":6,"wins":7},"stepfun/step-3.7-flash":{"draws":2,"losses":4,"wins":4},"tencent/hy3-preview":{"draws":5,"losses":5,"wins":2},"thinkingmachines/inkling":{"draws":4,"losses":4,"wins":2},"x-ai/grok-4.5":{"draws":3,"losses":5,"wins":2},"x-ai/grok-build-0.1":{"draws":4,"losses":6,"wins":2},"xiaomi/mimo-v2.5":{"draws":9,"losses":12,"wins":11},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":3,"wins":3},"z-ai/glm-5.2":{"draws":20,"losses":10,"wins":16}},"o3":{"claude-opus-4-5":{"draws":3,"losses":4,"wins":3},"claude-opus-4-8":{"draws":0,"losses":2,"wins":0},"claude-opus-5":{"draws":0,"losses":6,"wins":0},"claude-sonnet-5":{"draws":4,"losses":1,"wins":1},"cohere/north-mini-code":{"draws":6,"losses":2,"wins":0},"deepseek/deepseek-v4-flash":{"draws":6,"losses":2,"wins":4},"deepseek/deepseek-v4-pro":{"draws":4,"losses":0,"wins":2},"google/gemini-3.5-flash-lite":{"draws":9,"losses":18,"wins":5},"google/gemini-3.6-flash":{"draws":10,"losses":12,"wins":6},"google/gemma-4-31b-it":{"draws":3,"losses":3,"wins":0},"gpt-4.1":{"draws":2,"losses":4,"wins":0},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":0},"gpt-5.4":{"draws":2,"losses":0,"wins":2},"gpt-5.4-mini":{"draws":7,"losses":4,"wins":5},"gpt-5.4-nano":{"draws":7,"losses":6,"wins":3},"gpt-5.5":{"draws":4,"losses":1,"wins":1},"gpt-5.6-luna":{"draws":2,"losses":0,"wins":4},"gpt-5.6-sol":{"draws":1,"losses":1,"wins":2},"gpt-5.6-terra":{"draws":0,"losses":2,"wins":2},"inclusionai/ling-3.0-flash":{"draws":7,"losses":4,"wins":5},"meituan/longcat-2.0":{"draws":5,"losses":10,"wins":5},"minimax/minimax-m3":{"draws":0,"losses":2,"wins":2},"mistralai/mistral-medium-3-5":{"draws":3,"losses":3,"wins":0},"moonshotai/kimi-k3":{"draws":3,"losses":17,"wins":4},"nex-agi/nex-n2-pro":{"draws":2,"losses":1,"wins":1},"o3":{"draws":3,"losses":12,"wins":3},"openai/gpt-oss-120b":{"draws":2,"losses":1,"wins":3},"poolside/laguna-s-2.1":{"draws":10,"losses":9,"wins":1},"qwen/qwen3.7-max":{"draws":2,"losses":1,"wins":1},"qwen/qwen3.7-plus":{"draws":1,"losses":1,"wins":2},"stepfun/step-3.7-flash":{"draws":0,"losses":3,"wins":1},"tencent/hy3-preview":{"draws":2,"losses":0,"wins":0},"thinkingmachines/inkling":{"draws":8,"losses":5,"wins":5},"x-ai/grok-4.5":{"draws":3,"losses":14,"wins":1},"xiaomi/mimo-v2.5":{"draws":1,"losses":3,"wins":0},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":4,"wins":1}},"openai/gpt-oss-120b":{"claude-opus-4-5":{"draws":5,"losses":26,"wins":1},"claude-opus-4-8":{"draws":0,"losses":9,"wins":3},"claude-opus-5":{"draws":1,"losses":2,"wins":1},"claude-sonnet-5":{"draws":4,"losses":1,"wins":1},"cohere/north-mini-code":{"draws":4,"losses":2,"wins":4},"deepseek/deepseek-v4-flash":{"draws":13,"losses":16,"wins":5},"deepseek/deepseek-v4-pro":{"draws":4,"losses":6,"wins":2},"google/gemini-3.5-flash-lite":{"draws":8,"losses":28,"wins":8},"google/gemini-3.6-flash":{"draws":5,"losses":17,"wins":1},"google/gemma-4-31b-it":{"draws":3,"losses":7,"wins":2},"gpt-4.1":{"draws":0,"losses":0,"wins":2},"gpt-4.1-nano":{"draws":0,"losses":1,"wins":1},"gpt-5.4":{"draws":3,"losses":10,"wins":1},"gpt-5.4-mini":{"draws":8,"losses":20,"wins":14},"gpt-5.4-nano":{"draws":18,"losses":15,"wins":9},"gpt-5.5":{"draws":6,"losses":5,"wins":1},"gpt-5.6-luna":{"draws":3,"losses":4,"wins":7},"gpt-5.6-sol":{"draws":2,"losses":11,"wins":1},"gpt-5.6-terra":{"draws":3,"losses":8,"wins":3},"inclusionai/ling-3.0-flash":{"draws":9,"losses":8,"wins":7},"meituan/longcat-2.0":{"draws":6,"losses":13,"wins":3},"minimax/minimax-m3":{"draws":1,"losses":8,"wins":1},"mistralai/mistral-medium-3-5":{"draws":3,"losses":1,"wins":4},"moonshotai/kimi-k3":{"draws":10,"losses":30,"wins":4},"nex-agi/nex-n2-pro":{"draws":4,"losses":4,"wins":4},"o3":{"draws":6,"losses":19,"wins":3},"poolside/laguna-s-2.1":{"draws":3,"losses":8,"wins":5},"qwen/qwen3.7-max":{"draws":2,"losses":7,"wins":3},"qwen/qwen3.7-plus":{"draws":1,"losses":1,"wins":8},"stepfun/step-3.7-flash":{"draws":2,"losses":4,"wins":2},"tencent/hy3-preview":{"draws":4,"losses":6,"wins":0},"thinkingmachines/inkling":{"draws":5,"losses":17,"wins":6},"x-ai/grok-4.5":{"draws":3,"losses":14,"wins":3},"xiaomi/mimo-v2.5":{"draws":9,"losses":13,"wins":10},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":8,"wins":0}},"poolside/laguna-s-2.1":{"claude-fable-5":{"draws":0,"losses":4,"wins":6},"claude-opus-4-5":{"draws":14,"losses":10,"wins":4},"claude-opus-4-8":{"draws":4,"losses":18,"wins":4},"claude-opus-5":{"draws":6,"losses":41,"wins":5},"claude-sonnet-5":{"draws":16,"losses":19,"wins":9},"cohere/north-mini-code":{"draws":17,"losses":9,"wins":2},"deepseek/deepseek-v4-flash":{"draws":33,"losses":15,"wins":30},"deepseek/deepseek-v4-pro":{"draws":6,"losses":8,"wins":10},"google/gemini-3.1-flash-lite":{"draws":6,"losses":8,"wins":4},"google/gemini-3.5-flash":{"draws":9,"losses":5,"wins":6},"google/gemini-3.5-flash-lite":{"draws":15,"losses":15,"wins":16},"google/gemini-3.6-flash":{"draws":21,"losses":22,"wins":17},"google/gemma-4-31b-it":{"draws":4,"losses":6,"wins":8},"gpt-4.1":{"draws":6,"losses":10,"wins":6},"gpt-4.1-nano":{"draws":0,"losses":1,"wins":3},"gpt-5":{"draws":9,"losses":4,"wins":9},"gpt-5.4":{"draws":6,"losses":11,"wins":3},"gpt-5.4-mini":{"draws":29,"losses":25,"wins":20},"gpt-5.4-nano":{"draws":41,"losses":14,"wins":25},"gpt-5.5":{"draws":13,"losses":9,"wins":12},"gpt-5.6-luna":{"draws":15,"losses":6,"wins":9},"gpt-5.6-sol":{"draws":0,"losses":16,"wins":12},"gpt-5.6-terra":{"draws":14,"losses":7,"wins":13},"inclusionai/ling-3.0-flash":{"draws":26,"losses":9,"wins":21},"meituan/longcat-2.0":{"draws":19,"losses":7,"wins":14},"minimax/minimax-m3":{"draws":8,"losses":7,"wins":9},"mistralai/mistral-medium-3-5":{"draws":0,"losses":2,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":1,"wins":7},"moonshotai/kimi-k3":{"draws":17,"losses":12,"wins":13},"nex-agi/nex-n2-pro":{"draws":4,"losses":3,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":6,"wins":9},"o3":{"draws":7,"losses":7,"wins":6},"openai/gpt-oss-120b":{"draws":6,"losses":6,"wins":2},"poolside/laguna-s-2.1":{"draws":20,"losses":10,"wins":16},"qwen/qwen3.7-max":{"draws":5,"losses":4,"wins":5},"qwen/qwen3.7-plus":{"draws":7,"losses":1,"wins":6},"stepfun/step-3.7-flash":{"draws":0,"losses":9,"wins":3},"tencent/hy3-preview":{"draws":6,"losses":9,"wins":7},"thinkingmachines/inkling":{"draws":11,"losses":12,"wins":21},"x-ai/grok-4.5":{"draws":17,"losses":52,"wins":11},"x-ai/grok-build-0.1":{"draws":2,"losses":4,"wins":2},"xiaomi/mimo-v2.5":{"draws":16,"losses":14,"wins":20},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":10,"wins":6},"z-ai/glm-5.2":{"draws":38,"losses":32,"wins":35}},"qwen/qwen3.7-max":{"claude-fable-5":{"draws":0,"losses":4,"wins":2},"claude-opus-4-5":{"draws":8,"losses":12,"wins":6},"claude-opus-4-8":{"draws":4,"losses":9,"wins":5},"claude-opus-5":{"draws":7,"losses":30,"wins":1},"claude-sonnet-5":{"draws":12,"losses":2,"wins":2},"cohere/north-mini-code":{"draws":3,"losses":4,"wins":9},"deepseek/deepseek-v4-flash":{"draws":18,"losses":12,"wins":22},"deepseek/deepseek-v4-pro":{"draws":7,"losses":7,"wins":6},"google/gemini-3.1-flash-lite":{"draws":1,"losses":3,"wins":4},"google/gemini-3.5-flash":{"draws":2,"losses":3,"wins":3},"google/gemini-3.5-flash-lite":{"draws":2,"losses":4,"wins":0},"google/gemini-3.6-flash":{"draws":5,"losses":10,"wins":1},"google/gemma-4-31b-it":{"draws":1,"losses":4,"wins":9},"gpt-4.1":{"draws":1,"losses":0,"wins":3},"gpt-5":{"draws":2,"losses":3,"wins":1},"gpt-5.4":{"draws":6,"losses":12,"wins":4},"gpt-5.4-mini":{"draws":20,"losses":15,"wins":29},"gpt-5.4-nano":{"draws":25,"losses":8,"wins":19},"gpt-5.5":{"draws":10,"losses":4,"wins":6},"gpt-5.6-luna":{"draws":12,"losses":6,"wins":10},"gpt-5.6-sol":{"draws":3,"losses":10,"wins":5},"gpt-5.6-terra":{"draws":5,"losses":6,"wins":5},"inclusionai/ling-3.0-flash":{"draws":14,"losses":4,"wins":6},"meituan/longcat-2.0":{"draws":7,"losses":3,"wins":2},"minimax/minimax-m3":{"draws":6,"losses":2,"wins":6},"mistralai/mistral-medium-3-5":{"draws":2,"losses":3,"wins":3},"moonshotai/kimi-k3":{"draws":7,"losses":15,"wins":6},"nex-agi/nex-n2-pro":{"draws":4,"losses":2,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":3,"wins":3},"o3":{"draws":3,"losses":4,"wins":1},"openai/gpt-oss-120b":{"draws":7,"losses":5,"wins":8},"poolside/laguna-s-2.1":{"draws":3,"losses":5,"wins":2},"qwen/qwen3.7-max":{"draws":2,"losses":2,"wins":2},"qwen/qwen3.7-plus":{"draws":4,"losses":3,"wins":7},"stepfun/step-3.7-flash":{"draws":6,"losses":3,"wins":5},"tencent/hy3-preview":{"draws":8,"losses":2,"wins":6},"thinkingmachines/inkling":{"draws":4,"losses":2,"wins":4},"x-ai/grok-4.5":{"draws":9,"losses":13,"wins":8},"x-ai/grok-build-0.1":{"draws":0,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":13,"losses":11,"wins":14},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":2,"wins":6},"z-ai/glm-5.2":{"draws":18,"losses":18,"wins":10}},"qwen/qwen3.7-plus":{"claude-fable-5":{"draws":0,"losses":2,"wins":0},"claude-opus-4-5":{"draws":16,"losses":7,"wins":3},"claude-opus-4-8":{"draws":6,"losses":9,"wins":3},"claude-opus-5":{"draws":0,"losses":2,"wins":2},"claude-sonnet-5":{"draws":5,"losses":3,"wins":0},"cohere/north-mini-code":{"draws":3,"losses":6,"wins":5},"deepseek/deepseek-v4-flash":{"draws":14,"losses":21,"wins":15},"deepseek/deepseek-v4-pro":{"draws":4,"losses":6,"wins":0},"google/gemini-3.1-flash-lite":{"draws":5,"losses":4,"wins":7},"google/gemini-3.5-flash":{"draws":0,"losses":2,"wins":0},"google/gemini-3.5-flash-lite":{"draws":4,"losses":1,"wins":3},"google/gemini-3.6-flash":{"draws":10,"losses":8,"wins":2},"google/gemma-4-31b-it":{"draws":1,"losses":9,"wins":2},"gpt-4.1":{"draws":0,"losses":0,"wins":2},"gpt-5.4":{"draws":4,"losses":8,"wins":0},"gpt-5.4-mini":{"draws":17,"losses":14,"wins":15},"gpt-5.4-nano":{"draws":15,"losses":20,"wins":21},"gpt-5.5":{"draws":5,"losses":5,"wins":2},"gpt-5.6-luna":{"draws":7,"losses":2,"wins":5},"gpt-5.6-sol":{"draws":4,"losses":7,"wins":1},"gpt-5.6-terra":{"draws":6,"losses":12,"wins":2},"inclusionai/ling-3.0-flash":{"draws":8,"losses":6,"wins":6},"meituan/longcat-2.0":{"draws":1,"losses":5,"wins":0},"minimax/minimax-m3":{"draws":3,"losses":7,"wins":2},"mistralai/mistral-medium-3-5":{"draws":1,"losses":6,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":10,"losses":11,"wins":3},"nex-agi/nex-n2-pro":{"draws":4,"losses":7,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":6,"wins":6},"o3":{"draws":1,"losses":2,"wins":1},"openai/gpt-oss-120b":{"draws":3,"losses":12,"wins":2},"poolside/laguna-s-2.1":{"draws":2,"losses":4,"wins":0},"qwen/qwen3.7-max":{"draws":6,"losses":7,"wins":3},"qwen/qwen3.7-plus":{"draws":2,"losses":4,"wins":0},"stepfun/step-3.7-flash":{"draws":2,"losses":6,"wins":6},"tencent/hy3-preview":{"draws":3,"losses":9,"wins":2},"thinkingmachines/inkling":{"draws":5,"losses":7,"wins":6},"x-ai/grok-4.5":{"draws":4,"losses":10,"wins":0},"x-ai/grok-build-0.1":{"draws":2,"losses":1,"wins":1},"xiaomi/mimo-v2.5":{"draws":12,"losses":23,"wins":5},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":8,"wins":0},"z-ai/glm-5.2":{"draws":19,"losses":10,"wins":11}},"stepfun/step-3.7-flash":{"claude-opus-4-5":{"draws":2,"losses":13,"wins":5},"claude-opus-4-8":{"draws":0,"losses":7,"wins":1},"claude-opus-5":{"draws":0,"losses":2,"wins":0},"claude-sonnet-5":{"draws":2,"losses":2,"wins":2},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":3},"deepseek/deepseek-v4-flash":{"draws":6,"losses":6,"wins":6},"deepseek/deepseek-v4-pro":{"draws":2,"losses":3,"wins":1},"google/gemini-3.5-flash-lite":{"draws":4,"losses":10,"wins":14},"google/gemini-3.6-flash":{"draws":1,"losses":7,"wins":4},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":4},"gpt-4.1":{"draws":0,"losses":1,"wins":1},"gpt-5.4":{"draws":2,"losses":1,"wins":1},"gpt-5.4-mini":{"draws":5,"losses":5,"wins":10},"gpt-5.4-nano":{"draws":6,"losses":6,"wins":8},"gpt-5.5":{"draws":2,"losses":2,"wins":0},"gpt-5.6-luna":{"draws":1,"losses":2,"wins":1},"gpt-5.6-sol":{"draws":0,"losses":4,"wins":2},"gpt-5.6-terra":{"draws":2,"losses":1,"wins":3},"inclusionai/ling-3.0-flash":{"draws":4,"losses":2,"wins":6},"meituan/longcat-2.0":{"draws":2,"losses":8,"wins":10},"minimax/minimax-m3":{"draws":0,"losses":3,"wins":1},"mistralai/mistral-medium-3-5":{"draws":2,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":3,"losses":17,"wins":6},"nex-agi/nex-n2-pro":{"draws":2,"losses":4,"wins":0},"o3":{"draws":2,"losses":15,"wins":7},"openai/gpt-oss-120b":{"draws":2,"losses":2,"wins":4},"poolside/laguna-s-2.1":{"draws":0,"losses":1,"wins":9},"qwen/qwen3.7-max":{"draws":2,"losses":2,"wins":0},"qwen/qwen3.7-plus":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":2,"losses":0,"wins":2},"thinkingmachines/inkling":{"draws":2,"losses":8,"wins":8},"x-ai/grok-4.5":{"draws":1,"losses":12,"wins":3},"xiaomi/mimo-v2.5":{"draws":4,"losses":1,"wins":5},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":3,"wins":3}},"tencent/hy3-preview":{"claude-fable-5":{"draws":1,"losses":3,"wins":4},"claude-opus-4-5":{"draws":6,"losses":7,"wins":3},"claude-opus-4-8":{"draws":8,"losses":7,"wins":3},"claude-opus-5":{"draws":8,"losses":13,"wins":5},"claude-sonnet-5":{"draws":10,"losses":2,"wins":6},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":6},"deepseek/deepseek-v4-flash":{"draws":23,"losses":7,"wins":12},"deepseek/deepseek-v4-pro":{"draws":5,"losses":1,"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":6,"losses":0,"wins":4},"google/gemini-3.6-flash":{"draws":8,"losses":5,"wins":3},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":4},"gpt-4.1":{"draws":5,"losses":2,"wins":3},"gpt-5":{"draws":2,"losses":0,"wins":0},"gpt-5.4":{"draws":11,"losses":9,"wins":2},"gpt-5.4-mini":{"draws":21,"losses":11,"wins":14},"gpt-5.4-nano":{"draws":24,"losses":4,"wins":24},"gpt-5.5":{"draws":12,"losses":6,"wins":4},"gpt-5.6-luna":{"draws":6,"losses":6,"wins":6},"gpt-5.6-sol":{"draws":9,"losses":8,"wins":3},"gpt-5.6-terra":{"draws":11,"losses":3,"wins":2},"inclusionai/ling-3.0-flash":{"draws":9,"losses":1,"wins":6},"meituan/longcat-2.0":{"draws":8,"losses":4,"wins":4},"minimax/minimax-m3":{"draws":8,"losses":4,"wins":6},"mistralai/mistral-medium-3-5":{"draws":2,"losses":3,"wins":1},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":7,"losses":13,"wins":4},"nex-agi/nex-n2-pro":{"draws":7,"losses":4,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":2,"wins":2},"o3":{"draws":5,"losses":0,"wins":1},"openai/gpt-oss-120b":{"draws":8,"losses":0,"wins":6},"poolside/laguna-s-2.1":{"draws":4,"losses":4,"wins":4},"qwen/qwen3.7-max":{"draws":5,"losses":3,"wins":2},"qwen/qwen3.7-plus":{"draws":5,"losses":1,"wins":4},"stepfun/step-3.7-flash":{"draws":4,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":1,"losses":1,"wins":0},"thinkingmachines/inkling":{"draws":1,"losses":7,"wins":4},"x-ai/grok-4.5":{"draws":7,"losses":7,"wins":8},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":12,"losses":9,"wins":9},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":2,"wins":9},"z-ai/glm-5.2":{"draws":23,"losses":11,"wins":6}},"thinkingmachines/inkling":{"claude-fable-5":{"draws":3,"losses":5,"wins":0},"claude-opus-4-5":{"draws":20,"losses":22,"wins":8},"claude-opus-4-8":{"draws":4,"losses":13,"wins":5},"claude-opus-5":{"draws":6,"losses":29,"wins":7},"claude-sonnet-5":{"draws":16,"losses":10,"wins":6},"cohere/north-mini-code":{"draws":7,"losses":10,"wins":11},"deepseek/deepseek-v4-flash":{"draws":25,"losses":22,"wins":27},"deepseek/deepseek-v4-pro":{"draws":6,"losses":11,"wins":1},"google/gemini-3.1-flash-lite":{"draws":8,"losses":7,"wins":13},"google/gemini-3.5-flash":{"draws":4,"losses":9,"wins":3},"google/gemini-3.5-flash-lite":{"draws":13,"losses":17,"wins":10},"google/gemini-3.6-flash":{"draws":25,"losses":24,"wins":9},"google/gemma-4-31b-it":{"draws":4,"losses":10,"wins":8},"gpt-4.1":{"draws":4,"losses":4,"wins":8},"gpt-4.1-nano":{"draws":0,"losses":4,"wins":0},"gpt-5":{"draws":8,"losses":6,"wins":0},"gpt-5.4":{"draws":13,"losses":9,"wins":6},"gpt-5.4-mini":{"draws":40,"losses":28,"wins":36},"gpt-5.4-nano":{"draws":26,"losses":26,"wins":33},"gpt-5.5":{"draws":11,"losses":13,"wins":8},"gpt-5.6-luna":{"draws":13,"losses":3,"wins":6},"gpt-5.6-sol":{"draws":7,"losses":9,"wins":6},"gpt-5.6-terra":{"draws":12,"losses":5,"wins":9},"inclusionai/ling-3.0-flash":{"draws":21,"losses":19,"wins":26},"meituan/longcat-2.0":{"draws":15,"losses":17,"wins":18},"minimax/minimax-m3":{"draws":4,"losses":10,"wins":8},"mistralai/mistral-medium-3-5":{"draws":3,"losses":8,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":3,"wins":5},"moonshotai/kimi-k3":{"draws":7,"losses":18,"wins":7},"nex-agi/nex-n2-pro":{"draws":4,"losses":4,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":10,"wins":11},"o3":{"draws":5,"losses":5,"wins":6},"openai/gpt-oss-120b":{"draws":9,"losses":14,"wins":9},"poolside/laguna-s-2.1":{"draws":16,"losses":21,"wins":17},"qwen/qwen3.7-max":{"draws":9,"losses":8,"wins":3},"qwen/qwen3.7-plus":{"draws":5,"losses":8,"wins":7},"stepfun/step-3.7-flash":{"draws":5,"losses":14,"wins":9},"tencent/hy3-preview":{"draws":3,"losses":5,"wins":8},"thinkingmachines/inkling":{"draws":8,"losses":6,"wins":10},"x-ai/grok-4.5":{"draws":21,"losses":33,"wins":10},"x-ai/grok-build-0.1":{"draws":2,"losses":2,"wins":4},"xiaomi/mimo-v2.5":{"draws":18,"losses":33,"wins":13},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":9,"wins":1},"z-ai/glm-5.2":{"draws":27,"losses":26,"wins":23}},"x-ai/grok-4.5":{"claude-opus-4-5":{"draws":26,"losses":20,"wins":22},"claude-opus-4-8":{"draws":6,"losses":5,"wins":11},"claude-opus-5":{"draws":9,"losses":32,"wins":9},"claude-sonnet-5":{"draws":10,"losses":8,"wins":6},"cohere/north-mini-code":{"draws":4,"losses":1,"wins":7},"deepseek/deepseek-v4-flash":{"draws":10,"losses":5,"wins":29},"deepseek/deepseek-v4-pro":{"draws":7,"losses":4,"wins":11},"google/gemini-3.5-flash-lite":{"draws":30,"losses":18,"wins":30},"google/gemini-3.6-flash":{"draws":24,"losses":43,"wins":29},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":12},"gpt-4.1":{"draws":6,"losses":4,"wins":14},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5.4":{"draws":5,"losses":11,"wins":4},"gpt-5.4-mini":{"draws":29,"losses":4,"wins":29},"gpt-5.4-nano":{"draws":16,"losses":16,"wins":48},"gpt-5.5":{"draws":9,"losses":0,"wins":13},"gpt-5.6-luna":{"draws":8,"losses":2,"wins":10},"gpt-5.6-sol":{"draws":4,"losses":9,"wins":11},"gpt-5.6-terra":{"draws":5,"losses":5,"wins":14},"inclusionai/ling-3.0-flash":{"draws":18,"losses":6,"wins":12},"meituan/longcat-2.0":{"draws":14,"losses":10,"wins":22},"minimax/minimax-m3":{"draws":3,"losses":3,"wins":10},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":12},"moonshotai/kimi-k3":{"draws":46,"losses":56,"wins":42},"nex-agi/nex-n2-pro":{"draws":5,"losses":2,"wins":13},"o3":{"draws":8,"losses":16,"wins":22},"openai/gpt-oss-120b":{"draws":2,"losses":2,"wins":12},"poolside/laguna-s-2.1":{"draws":17,"losses":7,"wins":22},"qwen/qwen3.7-max":{"draws":7,"losses":6,"wins":11},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":8},"stepfun/step-3.7-flash":{"draws":1,"losses":2,"wins":9},"tencent/hy3-preview":{"draws":3,"losses":5,"wins":6},"thinkingmachines/inkling":{"draws":15,"losses":8,"wins":17},"x-ai/grok-4.5":{"draws":23,"losses":48,"wins":25},"xiaomi/mimo-v2.5":{"draws":9,"losses":4,"wins":19},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":9,"wins":8},"z-ai/glm-5.2":{"draws":1,"losses":1,"wins":2}},"xiaomi/mimo-v2.5":{"claude-fable-5":{"draws":1,"losses":7,"wins":0},"claude-opus-4-5":{"draws":19,"losses":25,"wins":18},"claude-opus-4-8":{"draws":13,"losses":25,"wins":6},"claude-opus-5":{"draws":5,"losses":25,"wins":2},"claude-sonnet-5":{"draws":16,"losses":15,"wins":7},"cohere/north-mini-code":{"draws":13,"losses":5,"wins":14},"deepseek/deepseek-v4-flash":{"draws":38,"losses":43,"wins":53},"deepseek/deepseek-v4-pro":{"draws":11,"losses":20,"wins":9},"google/gemini-3.1-flash-lite":{"draws":9,"losses":12,"wins":19},"google/gemini-3.5-flash":{"draws":13,"losses":3,"wins":2},"google/gemini-3.5-flash-lite":{"draws":3,"losses":8,"wins":3},"google/gemini-3.6-flash":{"draws":7,"losses":12,"wins":9},"google/gemma-4-31b-it":{"draws":6,"losses":15,"wins":17},"gpt-4.1":{"draws":6,"losses":9,"wins":5},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":6,"losses":5,"wins":5},"gpt-5.4":{"draws":12,"losses":25,"wins":3},"gpt-5.4-mini":{"draws":49,"losses":43,"wins":58},"gpt-5.4-nano":{"draws":53,"losses":56,"wins":51},"gpt-5.5":{"draws":16,"losses":15,"wins":5},"gpt-5.6-luna":{"draws":14,"losses":13,"wins":25},"gpt-5.6-sol":{"draws":8,"losses":24,"wins":10},"gpt-5.6-terra":{"draws":19,"losses":17,"wins":8},"inclusionai/ling-3.0-flash":{"draws":13,"losses":8,"wins":15},"meituan/longcat-2.0":{"draws":6,"losses":15,"wins":13},"minimax/minimax-m3":{"draws":8,"losses":14,"wins":14},"mistralai/mistral-medium-3-5":{"draws":4,"losses":7,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":3,"wins":2},"moonshotai/kimi-k3":{"draws":19,"losses":37,"wins":12},"nex-agi/nex-n2-pro":{"draws":11,"losses":11,"wins":12},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":12,"wins":12},"o3":{"draws":3,"losses":3,"wins":4},"openai/gpt-oss-120b":{"draws":15,"losses":16,"wins":17},"poolside/laguna-s-2.1":{"draws":6,"losses":14,"wins":6},"qwen/qwen3.7-max":{"draws":9,"losses":13,"wins":10},"qwen/qwen3.7-plus":{"draws":5,"losses":6,"wins":19},"stepfun/step-3.7-flash":{"draws":6,"losses":10,"wins":6},"tencent/hy3-preview":{"draws":10,"losses":12,"wins":10},"thinkingmachines/inkling":{"draws":3,"losses":9,"wins":18},"x-ai/grok-4.5":{"draws":13,"losses":27,"wins":4},"x-ai/grok-build-0.1":{"draws":4,"losses":7,"wins":1},"xiaomi/mimo-v2.5":{"draws":22,"losses":29,"wins":33},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":18,"wins":11},"z-ai/glm-5.2":{"draws":37,"losses":43,"wins":26}},"xiaomi/mimo-v2.5-pro":{"claude-opus-4-5":{"draws":5,"losses":9,"wins":10},"claude-opus-4-8":{"draws":6,"losses":4,"wins":6},"claude-opus-5":{"draws":3,"losses":26,"wins":1},"claude-sonnet-5":{"draws":6,"losses":5,"wins":5},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":6},"deepseek/deepseek-v4-flash":{"draws":12,"losses":15,"wins":21},"deepseek/deepseek-v4-pro":{"draws":2,"losses":6,"wins":6},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":9},"google/gemini-3.5-flash":{"draws":1,"losses":1,"wins":0},"google/gemini-3.5-flash-lite":{"draws":0,"losses":10,"wins":2},"google/gemini-3.6-flash":{"draws":3,"losses":7,"wins":2},"google/gemma-4-31b-it":{"draws":0,"losses":2,"wins":6},"gpt-4.1":{"draws":2,"losses":7,"wins":3},"gpt-5":{"draws":0,"losses":1,"wins":1},"gpt-5.4":{"draws":4,"losses":7,"wins":3},"gpt-5.4-mini":{"draws":16,"losses":19,"wins":15},"gpt-5.4-nano":{"draws":16,"losses":13,"wins":21},"gpt-5.5":{"draws":7,"losses":2,"wins":3},"gpt-5.6-luna":{"draws":5,"losses":0,"wins":7},"gpt-5.6-sol":{"draws":3,"losses":6,"wins":3},"gpt-5.6-terra":{"draws":8,"losses":4,"wins":4},"inclusionai/ling-3.0-flash":{"draws":5,"losses":6,"wins":9},"meituan/longcat-2.0":{"draws":3,"losses":7,"wins":8},"minimax/minimax-m3":{"draws":2,"losses":3,"wins":7},"mistralai/mistral-medium-3-5":{"draws":0,"losses":1,"wins":5},"moonshotai/kimi-k3":{"draws":7,"losses":11,"wins":6},"nex-agi/nex-n2-pro":{"draws":4,"losses":4,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":2,"wins":4},"o3":{"draws":1,"losses":3,"wins":4},"openai/gpt-oss-120b":{"draws":3,"losses":0,"wins":11},"poolside/laguna-s-2.1":{"draws":2,"losses":6,"wins":6},"qwen/qwen3.7-max":{"draws":4,"losses":8,"wins":2},"qwen/qwen3.7-plus":{"draws":6,"losses":0,"wins":8},"stepfun/step-3.7-flash":{"draws":2,"losses":4,"wins":6},"tencent/hy3-preview":{"draws":1,"losses":5,"wins":2},"thinkingmachines/inkling":{"draws":2,"losses":2,"wins":10},"x-ai/grok-4.5":{"draws":4,"losses":9,"wins":7},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":12,"losses":15,"wins":13},"z-ai/glm-5.2":{"draws":11,"losses":22,"wins":11}},"z-ai/glm-5.2":{"claude-fable-5":{"draws":1,"losses":20,"wins":3},"claude-opus-4-5":{"draws":25,"losses":42,"wins":25},"claude-opus-4-8":{"draws":21,"losses":30,"wins":25},"claude-opus-5":{"draws":14,"losses":74,"wins":10},"claude-sonnet-5":{"draws":25,"losses":38,"wins":31},"cohere/north-mini-code":{"draws":7,"losses":9,"wins":10},"deepseek/deepseek-v4-flash":{"draws":42,"losses":51,"wins":47},"deepseek/deepseek-v4-pro":{"draws":6,"losses":20,"wins":20},"google/gemini-3.1-flash-lite":{"draws":13,"losses":12,"wins":25},"google/gemini-3.5-flash":{"draws":6,"losses":14,"wins":10},"google/gemini-3.5-flash-lite":{"draws":6,"losses":2,"wins":2},"google/gemini-3.6-flash":{"draws":8,"losses":4,"wins":4},"google/gemma-4-31b-it":{"draws":7,"losses":8,"wins":5},"gpt-4.1":{"draws":9,"losses":9,"wins":16},"gpt-5":{"draws":12,"losses":20,"wins":18},"gpt-5.4":{"draws":32,"losses":16,"wins":16},"gpt-5.4-mini":{"draws":73,"losses":61,"wins":82},"gpt-5.4-nano":{"draws":55,"losses":67,"wins":78},"gpt-5.5":{"draws":23,"losses":25,"wins":18},"gpt-5.6-luna":{"draws":30,"losses":19,"wins":23},"gpt-5.6-sol":{"draws":16,"losses":35,"wins":17},"gpt-5.6-terra":{"draws":29,"losses":20,"wins":25},"inclusionai/ling-3.0-flash":{"draws":16,"losses":7,"wins":9},"meituan/longcat-2.0":{"draws":16,"losses":11,"wins":27},"minimax/minimax-m3":{"draws":12,"losses":11,"wins":15},"mistralai/mistral-medium-3-5":{"draws":0,"losses":12,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":9,"wins":9},"nex-agi/nex-n2-pro":{"draws":14,"losses":8,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":26,"wins":16},"o3":{"draws":2,"losses":5,"wins":13},"openai/gpt-oss-120b":{"draws":18,"losses":12,"wins":10},"poolside/laguna-s-2.1":{"draws":11,"losses":18,"wins":13},"qwen/qwen3.7-max":{"draws":13,"losses":16,"wins":19},"qwen/qwen3.7-plus":{"draws":16,"losses":9,"wins":13},"stepfun/step-3.7-flash":{"draws":4,"losses":9,"wins":11},"tencent/hy3-preview":{"draws":13,"losses":11,"wins":16},"thinkingmachines/inkling":{"draws":11,"losses":21,"wins":18},"x-ai/grok-4.5":{"draws":12,"losses":24,"wins":12},"x-ai/grok-build-0.1":{"draws":4,"losses":10,"wins":8},"xiaomi/mimo-v2.5":{"draws":42,"losses":43,"wins":45},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":15,"wins":20},"z-ai/glm-5.2":{"draws":68,"losses":73,"wins":73}}}}}